--- title: neos® Clinical Evidence and Peer-Reviewed Research | machineMD description: 30+ peer-reviewed studies and conference presentations focused on oculometrics and neos® --- [![MachineMD\_RGB\_C\_BrightBG](https://www.machinemd.com/hubfs/MachineMD_RGB_C_BrightBG.svg "MachineMD_RGB_C_BrightBG")](https://www.machinemd.com?hsLang=en) - [neos](https://www.machinemd.com/neos) - [pupillometry](https://www.machinemd.com/neos/quantitative-pupillometry) - [ocular alignment](https://www.machinemd.com/neos/ocular-alignment) - [science](https://www.machinemd.com/science) - [oculometrics](https://www.machinemd.com/oculometrics) - [Multiple Sclerosis](https://www.machinemd.com/multiple-sclerosis) - [Myasthenia Gravis](https://www.machinemd.com/myasthenia-gravis) - [Huntington's Disease](https://www.machinemd.com/huntingtons-disease) - [Parkinson's Disease](https://www.machinemd.com/parkinsons-disease) - [Progressive Supranuclear Palsy](https://www.machinemd.com/progressive-supranuclear-palsy) - [Alzheimer's Disease](https://www.machinemd.com/alzheimers-disease) - [Brain Tumors](https://www.machinemd.com/brain-tumors) - [Stroke](https://www.machinemd.com/stroke) - [Traumatic Brain Injury](https://www.machinemd.com/traumatic-brain-injury) - [Niemann Pick Type C](https://www.machinemd.com/niemann-pick-type-c) - [Gaucher Disease](https://www.machinemd.com/gaucher-disease) - [NAION](https://www.machinemd.com/naion) - [Idiopathic Intracranial Hypertension](https://www.machinemd.com/idiopathic-intracranial-hypertension) - [about](https://www.machinemd.com/about) - [news](https://www.machinemd.com/news) - [contact](https://www.machinemd.com/contact) [![MachineMD\_RGB\_C\_DarkBG\[5718\]](https://www.machinemd.com/hs-fs/hubfs/MachineMD_RGB_C_DarkBG%5B5718%5D.png?width=200&height=26&name=MachineMD_RGB_C_DarkBG%5B5718%5D.png "MachineMD_RGB_C_DarkBG[5718]")](https://www.machinemd.com?hsLang=en) [![MachineMD\_RGB\_C\_BrightBG](https://www.machinemd.com/hubfs/MachineMD_RGB_C_BrightBG.svg "MachineMD_RGB_C_BrightBG")](https://machinemd.com?hsLang=en) - [neos](https://www.machinemd.com/neos) - [pupillometry](https://www.machinemd.com/neos/quantitative-pupillometry) - [ocular alignment](https://www.machinemd.com/neos/ocular-alignment) - [science](https://www.machinemd.com/science) - [oculometrics](https://www.machinemd.com/oculometrics) - [Multiple Sclerosis](https://www.machinemd.com/multiple-sclerosis) - [Myasthenia Gravis](https://www.machinemd.com/myasthenia-gravis) - [Huntington's Disease](https://www.machinemd.com/huntingtons-disease) - [Parkinson's Disease](https://www.machinemd.com/parkinsons-disease) - [Progressive Supranuclear Palsy](https://www.machinemd.com/progressive-supranuclear-palsy) - [Alzheimer's Disease](https://www.machinemd.com/alzheimers-disease) - [Brain Tumors](https://www.machinemd.com/brain-tumors) - [Stroke](https://www.machinemd.com/stroke) - [Traumatic Brain Injury](https://www.machinemd.com/traumatic-brain-injury) - [Niemann Pick Type C](https://www.machinemd.com/niemann-pick-type-c) - [Gaucher Disease](https://www.machinemd.com/gaucher-disease) - [NAION](https://www.machinemd.com/naion) - [Idiopathic Intracranial Hypertension](https://www.machinemd.com/idiopathic-intracranial-hypertension) - [about](https://www.machinemd.com/about) - [news](https://www.machinemd.com/news) - [contact](https://www.machinemd.com/contact) [![MachineMD\_RGB\_C\_DarkBG\[5718\]](https://www.machinemd.com/hs-fs/hubfs/MachineMD_RGB_C_DarkBG%5B5718%5D.png?width=200&height=26&name=MachineMD_RGB_C_DarkBG%5B5718%5D.png "MachineMD_RGB_C_DarkBG[5718]")](https://www.machinemd.com?hsLang=en) - [neos](https://www.machinemd.com/neos) - [pupillometry](https://www.machinemd.com/neos/quantitative-pupillometry) - [ocular alignment](https://www.machinemd.com/neos/ocular-alignment) - [science](https://www.machinemd.com/science) - [oculometrics](https://www.machinemd.com/oculometrics) - [Multiple Sclerosis](https://www.machinemd.com/multiple-sclerosis) - [Myasthenia Gravis](https://www.machinemd.com/myasthenia-gravis) - [Huntington's Disease](https://www.machinemd.com/huntingtons-disease) - [Parkinson's Disease](https://www.machinemd.com/parkinsons-disease) - [Progressive Supranuclear Palsy](https://www.machinemd.com/progressive-supranuclear-palsy) - [Alzheimer's Disease](https://www.machinemd.com/alzheimers-disease) - [Brain Tumors](https://www.machinemd.com/brain-tumors) - [Stroke](https://www.machinemd.com/stroke) - [Traumatic Brain Injury](https://www.machinemd.com/traumatic-brain-injury) - [Niemann Pick Type C](https://www.machinemd.com/niemann-pick-type-c) - [Gaucher Disease](https://www.machinemd.com/gaucher-disease) - [NAION](https://www.machinemd.com/naion) - [Idiopathic Intracranial Hypertension](https://www.machinemd.com/idiopathic-intracranial-hypertension) - [about](https://www.machinemd.com/about) - [news](https://www.machinemd.com/news) - [contact](https://www.machinemd.com/contact) [LinkedIn](https://www.linkedin.com/company/machinemd/) [Follow us on Facebook](https://twitter.com/md_machine) ## Our Publications   Conference presentation ### Automated Detection of INO and RAPD in Multiple Sclerosis using neos: Uncovering Subclinical Neuro-Ophthalmic Dysfunction in a Real-World Cohort Dominik Brügger, Emilie Reuter, Justus Luerweg, Melina Katsimpoura, Bruno Hauser, Julian Lehmann, Johanna Haselon, David Bratek, Zacaria Assfoor, Caroline Schuetrumpf, Ralf Gold, Jeremias Motte, Ruth Schneider, Anke Salmen MS Toronto, ACTRIMS-ECTRIMS, 2026 Study details ![MSToronto\_A0\_landscape](https://www.machinemd.com/hubfs/MSToronto_A0_landscape.png) Click to enlarge **Background** Internuclear ophthalmoplegia (INO) and relative afferent pupillary defect (RAPD) are important manifestations of multiple sclerosis (MS), reflecting brainstem and optic nerve involvement. Both are frequently underrecognized in routine clinical practice, particularly in mild or subclinical forms. **Objectives** To evaluate automated detection of INO and RAPD using quantitative eye tracking and pupillometry, and to compare results with expert interpretation and routine clinical assessments in a real-world MS cohort. Methods We retrospectively analyzed 396 participants with MS from a real-world clinical cohort. Automated INO detection was performed using the Versional Main-Sequence Index (VMSI), which quantifies abducting– adducting asymmetry based on saccadic peak velocity–amplitude relationships. Automated RAPD quantification was performed using the [RAPD neoscore](https://www.machinemd.com/neos/quantitative-pupillometry?hsLang=en), a standardized measure of interocular pupillary response asymmetry. Automated classification thresholds were derived from prior analyses on partially overlapping datasets and applied without re-optimization to the current cohort. Automated results were compared with routine clinical documentation for RAPD and INO, and expert-rated INO based on interpretation of the oculography. Analyses were performed in participants with complete data for each modality (INO: n=312; RAPD: n=383). **Results** Among 396 participants with MS, 312 had complete INO data (mean age 43.8±12.5 years; 67.1% female). Expert-rated INO was present in 49 cases. Automated detection identified 45/49 cases (sensitivity 91.8%, specificity 96.2%, positive predictive value \[PPV\] 81.8%, negative predictive value \[NPV\] 98.4%). Routine clinical documentation identified fewer INO cases than expert assessment (19/49). For RAPD, 43/383 participants were positive by clinical assessment, whereas 118/383 were positive by automated analysis (sensitivity 74.4%, specificity 74.2%, PPV 27.1%, NPV 95.7%). **Conclusion** Quantitative assessment identified a higher burden of neuro-ophthalmic abnormalities than routine clinical evaluation, with strong agreement between automated and expert INO assessment of the automated measurement. For RAPD, interpretation is limited by the absence of an established gold-standard reference; therefore, differences between automated and clinical assessments may reflect increased sensitivity to subtle dysfunction, limitations of routine clinical evaluation, or potential misclassification by the device. Standardized quantitative measures may improve detection and characterization of neuro-ophthalmic involvement in MS. Conference presentation ### Validation of Automated Ocular Alignment Measurements Using a VR-Based Eye-Tracking Medical Device Feil M, Massatsch P, Coito A, Spychala B, Van Lidth De Jeude J, Hubbard I, Abegg, M American Academy of Ophthalmology, 2026 Study details ![Validation of Automated Ocular Alignment Measurements Using a VR-Based Eye-Tracking Device\_Poster\_AAO - mMD](https://www.machinemd.com/hubfs/Validation%20of%20Automated%20Ocular%20Alignment%20Measurements%20Using%20a%20VR-Based%20Eye-Tracking%20Device_Poster_AAO%20-%20mMD.png) Click to enlarge **Purpose** To validate automated strabismus angle measurements from a virtual reality (VR)-based eye-tracking medical device ([ne**o**s](https://www.machinemd.com/neos/ocular-alignment?hsLang=en)®) against standard clinical methods. **Methods** Retrospective study of 53 paired examinations with ne**o**s® and clinical measurements (primarily alternate prism cover test). Examinations performed within ≤2 months were matched by participant, gaze position, and measurement dimension. Agreement in horizontal and vertical deviations (prism diopters) was assessed using intraclass correlation coefficients (ICC), Bland-Altman analysis and Cohen's kappa. **Results** Agreement between ne**o**s® and APCT was strong, with the highest agreement in primary gaze. Primary-gaze ICCs were 0.95 (95% CI, 0.88–0.97) for horizontal and 0.91 (95% CI, 0.85–0.95) for vertical measurements. Across all gaze positions, ICCs were 0.92 and 0.88 for horizontal and vertical measurements, respectively. For small-angle deviations, defined as horizontal deviations ≤8Δ and vertical deviations \<3Δ, the mean ne**o**s®–APCT differences were +1.17Δ horizontally and −0.19Δ vertically, with median absolute differences of 0.86Δ and 0.44Δ, respectively. Categorical agreement for horizontal deviation direction was high, with Cohen’s κ of 0.90 in primary gaze and 0.91 across all positions. **Conclusion** Automated ocular alignment measurements with ne**o**s® show strong agreement with clinical standards, with best performance in primary gaze, supporting an examiner-independent approach for strabismus assessment. Conference presentation ### Automated and Objective Detection of Binocular Vision with a VR-based medical device Beate Spychala, Mathias Abegg Swiss Society of Ophthalmology Meeting, 2026 Study details ![20082026\_SOG2026\_Onovis-Poster\_final\_bs](https://www.machinemd.com/hubfs/20082026_SOG2026_Onovis-Poster_final_bs.png) Click to enlarge **Purpose** To evaluate the diagnostic accuracy of the [neos](https://www.machinemd.com/neos?hsLang=en) device — a head-mounted display with integrated eye tracking — for objective detection of binocular vision via disparity-induced vergence responses. **Methods** In this retrospective case series, 50 patients from a tertiary neuro-ophthalmology and strabismus centre (June 2025 – February 2026) underwent neos examination, including fusional amplitude measurement. Clinical binocular status was independently determined using standard tests (Bagolini striated glasses, Lang and TNO stereotests). A blinded grader then assessed neos pdf-reports alone, classifying binocular status based on the presence or absence of a motor vergence response. Diagnostic accuracy was quantified using sensitivity, specificity, and Cohen’s kappa coefficient. **Results** neos correctly identified 31 of 33 patients with binocular vision and 11 of 17 without. Observed accuracy was 84.0 %, with sensitivity of 93.9 % and specificity of 64.7 %. Cohen’s kappa indicated substantial agreement with clinical assessment (κ = 0.62, p \< 0.001). False positives largely occurred in patients with intermittent strabismus, suggesting transient binocular function. **Conclusions** neos demonstrates good diagnostic accuracy for objective detection of binocular vision, particularly exhibiting high sensitivity. Its automated assessment could serve as a valuable screening tool for patients unable to complete conventional subjective tests. Prospective studies with larger cohorts are warranted to further validate clinical utility.  Conference presentation ### Diagnostic Accuracy of an Eye-tracking based Automated Neuro-Ophthalmic Examination for the Detection of Infantile Nystagmus Syndrome: A Retrospective Case Series Karim El-Koussy, Colin Colmant, Mathias Abegg Swiss Society of Ophthalmology Meeting, 2026 Study details **Background** Infantile nystagmus syndrome (INS) is the most prevalent form of nystagmus encountered in ophthalmic practice. Today its diagnosis relies on clinical observations alone. Oculomotor characteristics have proven diagnostically but were only available in research settings. Here we test a recently introduced eye-movement recording device for its capacity to measure objectively all relevant features of infantile nystagmus syndrome. **Objective** To evaluate the diagnostic accuracy of the [neos](https://www.machinemd.com/neos?hsLang=en) eye-movement recording system for detecting INS in an ophthalmic practice, and to compare performance between an experienced neuro-ophthalmologist and a novice reviewer. Methods Retrospective cross-sectional single-centre case series. All patients with a diagnosis containing the keyword "nystagmus", a successful neos recording and informed consent were included. Two blinded reviewers — an expert with \>20 years' experience and a trained novice — independently classified each recording as INS, neurological nystagmus, other nystagmus, or healthy, based solely on the neos PDF report. Clinical diagnosis from routine tertiary care served as the reference standard. Sensitivity, specificity, accuracy, and Cohen's kappa (κ) were calculated. **Results** \>60 patients were included. Expert review achieved a sensitivity of 83.3%, specificity of 100%, accuracy of 95.3%, and κ = 0.88 (almost perfect agreement; p \< 0.0001). Novice review yielded a sensitivity of 61.1%, specificity of 97.8%, accuracy of 87.5%, and κ = 0.66 (substantial agreement; p \< 0.0001). **Conclusions** The neos device enables accurate, objective detection of INS from a certified medical device in an ophthalmic setting — a first for this clinical context. Expert review performance was almost perfect. Even brief novice training yielded substantial agreement, suggesting potential for broader clinical deployment. Prospective validation in larger multicentre cohorts is warranted.  Conference presentation ### Paradoxical Miosis in Darkness in a Child with Congenital Stationary Night Blindness: A Pupillometric Feature Suggesting Differentiation from Retinitis Pigmentosa Mathias Abegg Swiss Society of Ophthalmology Meeting, 2026 Study details ![Poster SOG 2026](https://www.machinemd.com/hubfs/Poster%20SOG%202026.jpg) Click to enlarge **Purpose** The diagnosis of congenital stationary night blindness (CSNB) may be difficult as retinal structure is relatively preserved. This case report shows how pupillography using a commercially available medical device may differentiate CSNB from retinitis pigmentosa and healthy.   **Methods** A 7-year-old with moderate myopia and subnormal vision despite correction presented with difficulty in darkness. Optical coherence tomography was unremarkable. ERG showed the typical pattern of CSNB. Pupillary responses were assessed using a head-mounted pupillometry system ([neos](https://www.machinemd.com/neos/quantitative-pupillometry?hsLang=en)®) measuring light response amplitude and responses to darkness onset. Data were then compared to an age-matched healthy control and a patient with retinitis pigmentosa. **Results** Both CSNB and retinitis pigmentosa patients exhibited reduced pupillary light response amplitudes compared to the healthy control. At darkness onset, the CSNB patient demonstrated a paradoxical transient miosis followed by delayed mydriasis, whereas the retinitis pigmentosa patient and healthy control showed immediate dilation. **Conclusion** Pupillometry revealed a distinct functional signature in CSNB, characterized by reduced light response amplitude with occasional paradoxical constriction at darkness onset. While reduced amplitude is non-specific, the paradoxical dark response may represent a potential disease-specific marker. Pupillometry may therefore serve as a rapid and accessible adjunctive option for the evaluation of suspected CSNB, particularly when ERG is unavailable. Further studies are needed to establish its diagnostic performance.  Conference presentation ### Artificial Intelligence-Driven Identification of Parkinson's Disease Using Oculometrics Erika Han, Ana Coito, Hassan Fadavi, Bruno Hauser, Pia Massatsch, Valentina Stozitzky, Dongli Li, Bettina Balint, Helen Dawes, Konrad P. Weber. European Academy of Neurology Meeting, 2026 doi: [10.1111/ene.70629](https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0015) Study details ![Screenshot 2026-06-28 at 09.05.14](https://www.machinemd.com/hubfs/Screenshot%202026-06-28%20at%2009.05.14.png) Click to enlarge **Introduction** To develop and evaluate AI models for Parkinson’s disease (PD) diagnosis using quantitative VR-derived ocular motor and pupillary measurements. **Methods** 102 PD patients were recruited in Zurich and Exeter; 89 PD patients were analysed. 133 individual PD examinations and 87 healthy-control examinations were included after curation. PD and control examinations were propensity matched on age and sex, treating each examination as separate data points. Participants completed standardized VR-based ocular motor assessments with the [neos](https://www.machinemd.com/neos?hsLang=en) medical device and clinical examinations. Seven AI models were trained. Model training, feature selection, hyperparameter optimisation, and calibration were performed within a nested cross-validation framework. Eye-movement domains assessed: fixation/alignment, pupil dynamics, saccades, smooth pursuit, and vergence. **Conclusion** Ocular motor and pupillometric features acquired with the neos medical device enable high-accuracy discrimination of Parkinson’s disease from healthy controls across multiple AI-modelling approaches. These findings support quantitative eye-movement assessment as a scalable, objective tool that may enhance PD diagnosis. A diagnostic accuracy study is needed to validate this modeling approach and establish clinical utility. Conference presentation ### Ocular Motor Characteristics of Infantile Nystagmus Syndrome in Clinical Practice Using Standardized Eye Movement Recordings Mathias Abegg, Ana Coito, Colin Colmant, Karim ElKoussy European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026 doi: [10.1080/01658107.2026.2651025](https://doi.org/10.1080/01658107.2026.2651025) Study details ![EUNOS Poster 2026\_Mathias](https://www.machinemd.com/hubfs/EUNOS%20Poster%202026_Mathias.jpg) Click to enlarge **Introduction** Diagnosis of infantile nystagmus syndrome (INS) is usually based on manual examination, dependent on examiner experience. Objective and quantitative measures may ease diagnosis. **Objective** To evaluate the diagnostic accuracy of the neos clas IIa eye-movement recording system for detecting INS in a tertiary ophthalmic practice. **Methods** - Retrospective cross-sectional case series - Inclusion: patients with and without nystagmus diagnosis - Analysis: expert and novice blinded reviewers classified each recording as INS, neurological nystagmus, other nystagmus, or healthy, based solely on the [neos](https://www.machinemd.com/neos?hsLang=en) PDF report. Clinical diagnosis from routine tertiary served as reference. Sensitivity, specificity, accuracy, and Cohen's kappa (k) were calculated. **Results** - Sixty-four patients included, 18 INS, 46 non-INS (11 other nystagmus, 35 non-nystagmus) ![](https://www.machinemd.com/hs-fs/hubfs/image-png-2.png?width=372&height=505&name=image-png-2.png) **Conclusion /Discussion** Diagnostic accuracy was high, even in a novice with only 5 minutes of training. neos-based eye movement recording and report review enables accurate, objective  detection of INS in an ophthalmic practice setting. This represents the first demonstration of a certified medical device capable of addressing all core diagnostic criteria of INS.  Conference presentation ### Triangulating Relative Afferent Pupillary Defect Assessment: Functional, Structural and Clinical Perspectives Dominik Brügger, Melina Katsimpoura, Julian Lehmann, Bruno Hauser, Emilie Reuter, Justus Luerweg, Johanna Haselon, David Bratek, Ralf Gold, Jeremias Motte, Ruth Schneider, Anke Salmen European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026 doi: [10.1080/01658107.2026.2651025](https://doi.org/10.1080/01658107.2026.2651025) Study details **Introduction** Relative afferent pupillary defect (RAPD) is a key clinical sign of asymmetric optic nerve dysfunction. Its assessment is limited by the subjectivity of clinical examination and the restricted sensitivity of structural imaging using optical coherence tomography (OCT),  particularly in the acute phase. In the absence of a reliable gold standard, discordance between clinical, structural, and functional measures is expected. This study aimed to compare these  modalities and to assess the contribution of quantitative pupillometry as a continuous functional measure for interpreting RAPD under real-world diagnostic conditions. **Methods** Data from 520 subjects were analyzed, including 132 healthy controls, 265 patients with multiple sclerosis–related disorders, 58 with other demyelinating diseases, and 38 with neurodegenerative conditions. RAPD was assessed clinically and quantified using the RAPD neoscore derived from binocular pupillometry ([neos](https://www.machinemd.com/neos/quantitative-pupillometry?hsLang=en)®, machineMD). Clinical RAPD assessment was derived from prospectively collected routine clinical documentation, reflecting real-world neurological practice rather than a standardized examination protocol within a clinical trial setting. Peripapillary retinal nerve fibre layer (pRNFL) thickness asymmetry was available in a subset of participants (n=103). Abnormality was defined separately for each modality using predefined thresholds. Patterns of concordance and discordance between clinical assessment, RAPD neoscore, and OCT were analyzed to characterize complementary detection across modalities rather than accuracy against a reference standard. **Results** RAPD neoscore showed concordance with clinical RAPD assessment, demonstrating good discriminative performance relative to clinician impression (ROC AUC 0.82). In addition, functional afferent asymmetry as reflected by RAPD neoscore was observed in cases without OCT-detectable unilateral RNFL thinning, including cases with and without concordant clinical RAPD assessment. In clinically borderline or uncertain examinations, RAPD neoscore yields a continuous directional representation of afferent asymmetry without reliance on dichotomizing thresholds. Overall, overlap between modalities was partial, with each method identifying distinct but intersecting subsets of cases. **Conclusions** Clinical examination, structural OCT, and quantitative pupillometry capture different aspects of afferent visual pathway dysfunction, and no single modality provides a complete assessment of RAPD. In the absence of a definitive gold standard, analysis of detection overlap highlights the complementary nature of these approaches. RAPD neoscore contributes objective functional information beyond both clinical impression and structural imaging, supporting its role as a clinically useful adjunct in routine RAPD assessment, including situations characterized by diagnostic uncertainty. Conference presentation ### Automated Detection of Internuclear Ophthalmoplegia Using VR-based Eye Tracking Brügger D, Reuter E, Leurweg J, Katsimpoura M, Hauser B, Lehmann J, Haselon J, Bratek D, Assfoor Z, Schuetrumpf C, Klimas R, Saft C, Ayzenberg I, Fisse A, Pitarokoili K, Schneider-Gold C, Gold R, Motte J, Schneider R, Salmen A. Association for Research in Vision and Ophthalmology (ARVO) Annual Meeting, 2026 doi: [2815264](https://iovs.arvojournals.org/article.aspx?articleid=2815264) Study details ![ARVO 2026 poster](https://www.machinemd.com/hubfs/ARVO%202026%20poster.png) Click to enlarge **Purpose** Internuclear ophthalmoplegia (INO) is a characteristic ocular motor sign of multiple sclerosis (MS) resulting from small inflammatory lesions in the medial longitudinal fasciculus (MLF). Subtle variants, such as mild adduction slowing, frequently escape clinical detection. Virtual reality (VR)–based oculography enables objective and quantitative assessment of ocular motor function. This work evaluated whether a Versional Main-Sequence Index (VMSI), based on abducting–adducting asymmetry in the saccadic main-sequence velocity, can automatically detect INO when compared with expert ratings. **Methods** Eye movements were recorded with a commercially available medical device ([neos](https://www.machinemd.com/neos?hsLang=en)/PRET, machineMD) during 10° and 20° horizontal saccades. Using all detected saccades for each eye, we estimated the main-sequence parameter k by fitting the relationship peak velocity = k sqrt(amplitude). The Versional Main-Sequence Index (VMSI) was defined as the ratio of the main-sequence parameter *k* for the abducting eye to *k* for the adducting eye. For comparison, two additional asymmetry measures were evaluated: Versional Dysconjugacy Index (VDI) area under the curve (AUC) and VDI peak velocity / amplitude (PV/AM). Binary INO classification used thresholds derived through ROC analysis. Data were obtained from 687 participants (mean age 44.8 ± 14.4 years; range 18–83; 259 male/428 female), including 556 with neurological disease (predominantly MS subtypes) and 131 healthy controls. INO was rated as present by masked clinicians in 53 participants (right n=20, left n=16, bilateral n=17). **Results** VMSI-based classification achieved a maximum AUC of 0.97. Screening, balanced, and confirmatory thresholds were defined by ROC analysis within the same cohort, yielding sensitivities of 0.94/0.87/0.87 and specificities of 0.75/0.97/0.95, respectively. Misclassifications were primarily associated with high-noise recordings. VMSI outperformed VDI AUC, VDI PV/AM, and combinations of these metrics. **Conclusions** VR-based eye tracking enables objective, automated detection of INO using VMSI and shows strong discriminative performance relative to established asymmetry metrics. This approach may provide a quick, objective, and scalable functional biomarker of brainstem involvement in MS, complementing clinical examination and MRI. Conference presentation ### Artificial Intelligence-Based Classification of Parkinson’s Disease Using Virtual Reality-Derived Oculometrics Erika Han, Ana Coito, Hassan Fadavi, Bruno Hauser, Pia Massatsch, Valentina Stozitzky, Dongli Li, Bettina Balint, Helen Dawes, Konrad P. Weber. European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026 doi: [10.1080/01658107.2026.2651025](https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#d1e171) Study details **Introduction** Parkinson’s disease (PD) diagnosis remains largely based on clinical evaluation, creating a need for objective and quantifiable biomarkers to enhance diagnostic accuracy, enable earlier detection, and support longitudinal monitoring. Eye movement and pupillary abnormalities are increasingly recognized as sensitive indicators of PD-related dysfunction in ocular motor control pathways. Advances in virtual reality (VR)–based eye tracking allow standardized measurement of such parameters (“oculometrics”) and provide promising inputs for artificial intelligence (AI)–driven classification models. This study aimed to develop and evaluate machine learning approaches for distinguishing PD from healthy individuals using quantitative ocular motor and pupillary metrics acquired with a VR-based medical eye-tracking device. **Methods** Individuals with idiopathic PD were recruited at two clinical centres: Zurich (Switzerland) and Exeter (United Kingdom). Participants completed two study visits including standardized VR-based ocular motor testing ([neos](https://www.machinemd.com/neos?hsLang=en)®, machineMD) alongside routine clinical examinations. Recordings with poor tracking quality or excessive signal loss were excluded. The analysis included 132 PD examinations and 148 examinations from an independent healthy control dataset. Each PD case was matched to an age- and sex-matched control using a globally optimal matching algorithm. Group differences were quantified using standardized mean differences (SMDs) and Welch’s t-tests. A supervised machine learning classifier was trained using the most discriminative oculometric features to distinguish PD from controls. Model performance was assessed separately for each site. **Results** The strongest PD–control differences were observed in fixation instability, ocular alignment, blink rate, saccadic measures (accuracy, peak velocity, and main sequence relationships), and pupillary dynamics including constriction/dilation velocity and response latency. The classifier demonstrated high diagnostic discrimination across both sites, with combined AUROC of 0.94. **Discussion** These preliminary findings suggest that VR-derived oculometrics provide robust biomarkers capable of differentiating individuals with PD from healthy controls. AI-based analysis of ocular motor and pupillary features may offer a scalable and objective tool to complement clinical assessment. Future work will focus on expanding cohorts, integrating datasets across centres, and correlating oculometric parameters with clinical disease measures to further improve diagnostic performance. Peer-reviewed ### Advances in ocular motor and pupil biomarkers for neurological disorders Coito A, Brügger D, Brémovà-Ertl T, Massatsch P, Abegg M, Weber K, Salmen A Brain Communications, Volume 8, Issue 2, 2026 doi: [10.1093/braincomms/fcag102](https://doi.org/10.1093/braincomms/fcag102) Study details ![BRAIN graphical abstract\_white](https://www.machinemd.com/hubfs/BRAIN%20graphical%20abstract_white.png) Click to enlarge Neurological disorders are often difficult to diagnose and monitor, particularly in the early stages when symptoms may be subtle or nonspecific. Because the visual system engages a large portion of the cerebral cortex and relies on well-defined neural pathways, it offers a unique and accessible window into brain function. In this context, the concepts of oculomics and oculometrics have gained increasing attention. Oculomics refers to the study of systemic and neurological diseases through ocular biomarkers, while oculometrics involves the computational quantification of eye and pupil parameters. Together, these approaches provide noninvasive, objective, and reproducible methods to assess neurological function, with strong potential to improve diagnostic precision, monitor disease progression, and guide individualized care. This review synthesizes recent advances in ocular motor and pupillary biomarkers in three major neurological conditions: multiple sclerosis, Parkinson’s disease, and Alzheimer’s disease. In multiple sclerosis, early ocular motor disturbances such as internuclear ophthalmoplegia, saccadic dysmetria, and impaired smooth pursuit are frequently observed and may reflect brainstem and cerebellar involvement. Relative afferent pupillary defect, objectively measured with pupillometry, is a strong indicator of optic neuritis. In Parkinson’s disease, impaired saccadic initiation, hypometric saccades, and convergence abnormalities reflect basal ganglia dysfunction, while pupil irregularities suggest underlying autonomic imbalance. In Alzheimer’s disease, impairments in saccades, smooth pursuit, fixation instability, and the pupillary light reflex have been associated with early cortical and brainstem pathology, reflecting deficits in attention, executive control, and cholinergic function. We also discuss the integration of eye-tracking data with neuroimaging and electrophysiology biomarkers to support multimodal diagnostic frameworks with the potential to improve diagnostic accuracy and disease monitoring. In addition, we highlight how recent technological developments in virtual reality-based eye-tracking could offer immersive, standardized testing conditions to enable scalable implementation of oculometric assessments in clinical practice. As the fields of oculomics and oculometrics continue to evolve, these approaches hold promise to bridge the gap between research and clinical application. However, large-scale validation studies, standardized protocols, and normative datasets are essential for broader clinical adoption. By embedding ocular motor and pupillary biomarkers into routine neurological assessments, clinicians may be able to detect disease earlier, differentiate between overlapping syndromes, and monitor therapeutic outcomes more effectively. Conference presentation ### AI-Based Classification of Parkinson's Disease Using Quantitative Ocular Motor Biomarkers Han E, Fadavi H, Massatsch P, Li D, Dawes H, Coito A, Hauser B, Stozitzky V, Balint B, Weber K P. North American Neuro-Ophthalmology Society (NANOS) Annual Meeting, 2026 Study details ![Parkinson's AI Classification](https://www.machinemd.com/hubfs/Screenshot%202026-03-20%20at%2017.14.02.png) Click to enlarge **Objective**: The development of artificial intelligence (AI) models for diagnosing Parkinson’s disease (PD) using ocular motor parameters obtained from a virtual reality (VR)-based medical device. **Background**: PD diagnosis currently relies largely on clinical examination, underscoring the need for objective biomarkers to enhance diagnostic accuracy, early detection and disease monitoring. Eye movement and pupil function abnormalities have emerged as promising candidates, reflecting PD-related dysfunction in ocular motor control pathways. **Design/Methods**: Eighty-one patients with idiopathic PD were enrolled in Zurich (Switzerland) and Exeter (UK). Each participant underwent two visits, including standardized ocular motor testing with the VR-based medical eye tracker ([neos](https://www.machinemd.com/neos?hsLang=en)®, machineMD) and corresponding manual examination. Data with poor tracking quality or excessive signal loss were excluded. The present analysis included 132 PD examinations and 148 healthy control examinations from an independent dataset. Each PD patient was matched to one control of similar age and sex using a globally optimal matching algorithm. For each parameter, standardized mean differences (SMDs) and Welch’s tests were computed. A supervised machine learning model was trained to classify PD versus controls based on the most discriminative parameters. Site-specific analyses were conducted for Zurich and Exeter. **Results**: Parameters showing the largest PD–control differences included saccades (accuracy, velocity, main sequence), vergence, ocular alignment, and pupil dynamics (constriction/dilation velocity and latency). The machine learning model achieved strong discrimination: Zurich—AUC 0.96 (F1: 0.92, sensitivity: 0.96, specificity: 0.89); Exeter—AUC 0.91 (F1: 0.84, sensitivity: 0.89, specificity: 0.79). **Conclusions**: Preliminary findings demonstrate that quantitative ocular motor and pupillary metrics can robustly distinguish PD from healthy individuals. Next steps include expanding the patient and control cohorts, merging datasets across sites, and correlating ocular motor parameters with clinical measures to refine diagnostic performance. Conference presentation ### Recovery of the Pupillary Light Reflex in Diabetic Retinopathy Assessed by Automatic Pupillometry Fierz F, Shamshiev M, Brügger D, Abegg M. North American Neuro-Ophthalmology Society (NANOS) Annual Meeting, 2026 Study details ![nanos2026 Fierz](https://www.machinemd.com/hubfs/nanos2026%20Fierz.png) Click to enlarge **Introduction** - **Diabetic Retinopathy** (DR) causes retinal ischemia, leading to impaired dark adaptation due to high oxygen demand. - **Hypothesis:** Recovery of the pupillary light reflex (PLR) is delayed in DR patients compared with healthy controls. **Methods** - **Design**: Multi-center, non-interventional pilot study comparing PLR recovery in DR patients with healthy controls (HC) and retinitis pigmentosa (RP) patients (positive controls). - **Procedure**: Pupillometry examination using the PRET™ VR headset (machineMD AG, Bern, Switzerland)[5](https://www.machinemd.com/science#footnote). - **Stimulus protocol**: Alternating bright and dark stimuli across 50 cycles (dark phase increased by 100ms per cycle) while recording pupil size. - **Analysis**: Linear regression and a linear mixed-effects model were used to test whether pupil responses at different time points and changes in PLR amplitude over time differ between groups. **Results** - Analysis included 10 patients with DR, 10 patients with RP, and 11 healthy controls. - In all groups, PLR amplitude increased with longer dark adaptation across the 50 stimulus cycles (Fig. 2). - Adaptation dynamics (Fig. 2) and maximal PLR amplitudes (Fig. 3) were significantly lower in DR and RP patients. **Conclusion** - PLR amplitudes may enable detection of DR using a simple pupillary test with a commercial VR headset, likely reflecting oxygen deprivation in DR. - PLR may serve as a simple diagnostic test for retinal dystrophies, similar to ERG, but easier to perform. Conference presentation ### Validation of RAPD neoscore: A Novel Digital Biomarker for detecting Relative Afferent Pupillary Defect Brügger D, Katsimpoura M, Lehmann J, Hauser B, Reuter E, Luerweg J, Haselon J, Bratek D, Gold R, Motte J, Schneider R, Salmen A Multiple Sclerosis Journal. 2025;31(3\_suppl):136-762. doi: [10.1177/13524585251358344](https://journals.sagepub.com/doi/epub/10.1177/13524585251358344) Study details **Objectives**: To validate the RAPD neoscore, a simple and objective metric for detecting RAPD, by comparing its diagnostic accuracy with traditional clinical evaluations. **Methods**: A cohort of 164 individuals, comprising healthy controls and patients clinically diagnosed with RAPD, underwent neuro-ophthalmic evaluation using a PRET device (machineMD, Switzerland)[3](https://www.machinemd.com/science#footnote) alongside standard clinical assessments. Diagnoses included relapsing-remitting multiple sclerosis (RRMS, n=35), primary progressive multiple sclerosis (PPMS, n=2), secondary progressive multiple sclerosis (SPMS, n=2), and other demyelinating disorders (n=5). RAPD neoscore calculations were performed independently and blinded at a separate site. Diagnostic performance was evaluated using receiver operating characteristic (ROC) curve analysis to determine sensitivity, specificity, and area under the curve (AUC). **Results**: ROC analysis revealed an AUC of 0.80 ± 0.02 for RAPD neoscore across all RAPD cases. When clinically ambiguous cases were excluded, the discriminative performance improved, with an AUC of 0.83 ± 0.02, indicating good diagnostic accuracy. **Conclusions**: The RAPD neoscore demonstrates robust agreement with traditional clinical assessments, highlighting its strong potential as a digital biomarker. Given the proposal to include optic nerve evaluation in diagnostic criteria for multiple sclerosis (MS), RAPD neoscore’s standardized and objective measurement could fulfill the dissemination-in-space criterion. This may significantly enhance diagnostic accuracy, facilitate monitoring, and support clinical decision-making in neuro-ophthalmology and multiple sclerosis diagnostics, ultimately improving patient outcomes. Peer-reviewed ### Detection of Relative Afferent Pupillary Defects Using Eye Tracking and a VR Headset Bruegger D, Grabe HM, Vicini R, Dysli M, Lussi D, Abegg M. Translational Vision Science and Technology. 2023;12(6):22. doi: [10.1167/tvst.12.6.22](https://doi.org/10.1167/tvst.12.6.22) Study details **Purpose**: The purpose of this study was to assess the feasibility of detecting relative afferent pupillary defects (RAPDs) using a commercial virtual reality headset equipped with an eye tracker. **Methods**: This is a cross-sectional study in which we compare the new computerized RAPD test with the traditional clinical standard using the swinging flashlight test. Eighty-two participants including 20 healthy volunteers aged 10 to 88 years were enrolled in this study. We present a bright/dark stimulus alternating between the eyes every 3 seconds using a virtual reality headset, and we simultaneously record changes in pupil size[4](https://www.machinemd.com/science#footnote). To determine the presence of an RAPD, we developed an algorithm analyzing the pupil size differences. For the assessment of the performance of the automated and the manual measurement a post hoc impression based on all available data is created. The accuracy of the manual clinical evaluation and the computerized method is compared using confusion matrices and the gold standard of the post hoc impression. The latter is based on all available clinical information. **Results**: We found that the computerized method detected RAPD with a sensitivity of 90.2% and an accuracy of 84.4%, as compared to the post hoc impression. This was not significantly different from the clinical evaluation with a sensitivity of 89.1% and an accuracy of 88.3%. **Conclusions**: The presented method offers an accurate, easy to use, and fast method to measure an RAPD. In contrast to today's clinical practice, the measures are quantitative and objective. Peer-reviewed ### Use of a Novel Virtual Reality-Based Pupillography Device for Glaucoma Management: Cross-Sectional Cohort Pilot Study El-Koussy K, Höhn R, Falcão MBL, Hauser B, Naidu A, Abegg M. Klin Monbl Augenheilkd. 2025;242(4):379-383. doi: [10.1055/a-2460-0147](https://doi.org/10.1055/a-2460-0147) Study details **Background**: Current standard methods in monitoring glaucoma progression, like optical coherence tomography (OCT) and standard automated perimetry (SAP), have limitations in certain cases. Automated relative afferent pupillary defect (RAPD) and pupillary light reflex (PLR) testing may offer more objective alternatives. This pilot study aimed to evaluate whether RAPD could sufficiently distinguish between the two eyes in asymmetrical glaucoma, and thus could lay the foundation for using the PLR of a single eye to monitor progression longitudinally. **Methods**: Twenty-one patients underwent quantitative PLR measurements using a virtual reality headset ([neos](https://www.machinemd.com/neos/quantitative-pupillometry?hsLang=en)®, machineMD). RAPD was calculated by subtracting the amplitude of PLRs between eyes. Both RAPD and relative SAP (measured using the mean defect or MD) results were correlated to the thickness of the peripapillary retinal nerve fiber layer (RNFL), as measured by OCT. **Results**: Data from 18 patients was analyzed after exclusions. RAPD significantly correlated with differences between the two eyes as measured by RNFL thickness (Pearson r = 0.79, p = 0.05). MD differences correlated slightly better with RNFL differences (Pearson r = 0.87, p \< 0.05). RAPD and MD combined yielded an improved prediction of RNFL differences by 5% compared to using MD only. **Conclusions**: RAPD measurements reliably detected asymmetries in optic nerve damage in glaucoma patients. SAP measurements correlated better with OCT results than RAPD results. However, SAP and RAPD combined led to an improved prediction of RNFL thickness. This could possibly allow us to use PLR only over longer periods of time to monitor glaucomatous optic nerve damage in a single eye in the future. Peer-reviewed ### Test-retest reliability of gaze precision of a novel virtual reality-based medical device Coito A, Naidu A, Lehmann J, Hauser B, Brügger D, Abegg M. Frontiers in Virtual Reality. 2025;Volume 6. doi: [10.3389/frvir.2025.1502679](https://doi.org/10.3389/frvir.2025.1502679) Study details **Purpose**: In virtual reality (VR) systems that track eye movements using infra-red cameras, the precision of gaze measurement is crucial for reliable detection of eye movement disorders. **Methods**: To assess gaze measurement ability and gaze precision consistency of an HMD VR-based medical device system, [neos](https://www.machinemd.com/neos?hsLang=en)™, under optimal conditions, we used a robotized setup that provides the advantage of mimicking human eye movements with minimal movement variability. We assessed neos™’s gaze examination test twice for thirteen simulated conditions with different noise levels, and then assessed gaze precision and gaze consistency for each by computing the intraclass correlation coefficient (ICC), standard error of measurements (SEM) and Bland-Altman analysis. **Results**: We found excellent test-retest reliability (ICC \> 0.99, SEM = 0.04) for neos™’s gaze precision, with good agreements between first and second gaze precision measurements observed via Bland-Altman analysis. The high ICC and low SEM of neos™ in all nine cardinal directions of gaze demonstrates its eye tracking reliability and measurement consistency. This is a crucial feature for eye-tracking applications for HMD-based VR devices when used in clinical settings. **Conclusions**: The use of a robotic eye to objectively validate a VR-based eye tracker can be applicable to other devices. Future research will investigate the longitudinal stability of the measurements in different human populations. Conference presentation ### Validation of a novel neuro-ophthalmological measurement device based on virtual reality and eye tracking ARVO 2025: Investigative Ophthalmology & Visual Science. June 2025, Vol.66, 3228. doi: [2806844](https://iovs.arvojournals.org/article.aspx?articleid=2806844) Study details **Purpose**: Eye and pupil movements are critical biomarkers for assessing neurological conditions. Most functional eye exams are manually performed making them subjective and error-prone; contributing to an estimated 50% misdiagnosis referral rates for neuro-ophthalmic conditions. [neos](https://www.machinemd.com/neos?hsLang=en)™ (machineMD, Switzerland) is a novel virtual reality (VR) based measurement device, utilizing a head-mounted VR display and stimuli with infra-red eye tracking and proprietary algorithms to perform neuro-ophthalmological based tests in a non-invasive, automated, and quantitative way. However, validation of eye-tracking-based tools like neos™ poses inherent challenges, particularly in separating the device’s performance characteristics from those of the examinee. This study outlines a methodology to isolate and evaluate neos’s performance independent of external influences to ensure measurement reliability and robustness. **Methods**: We evaluated neos’s gaze precision and pupil size measurement outputs independently using a customized eye-robot that simulates human eye movements and in human participants. We used test-retest reliability as a robust, calibration-independent surrogate metric of gaze precision of robot data that was further analyzed using intraclass correlation coefficients (ICCs), standard error of measurements (SEM), and Bland-Altman analysis. For human participants, we assessed pupil size by comparing neos’s eye tracker measurements and infrared images to visual light images calibrated with a physical scale, using the iris diameter as a reference. **Results**:  In robotic trials, neos™ achieved excellent test-retest reliability for gaze precision (ICC \> 0.99, SEM = 0.04), with high agreement between repeated measurements. Bland-Altman plots confirmed minimal bias and narrow variability across measurements, demonstrating robustness even in noisy conditions. Human trials revealed a mean pupil size difference of 0.38 ± 0.20 mm and iris size difference of 1.66 ± 0.38 mm between eye tracker and reference measurements. **Conclusions**: The neos™ device has the potential to automate functional eye movement and pupil response measurements with high precision and minimal operator dependency, which can enhance neuro-ophthalmic diagnostic accuracy in clinical settings. Future studies will investigate its performance in detecting a range of specific biomarkers. Peer-reviewed ### Automated Measurement of Strabismus Angles Using a Commercial Virtual Reality Headset Vicini R, Brügger D, Grabe H, Abegg M. Klin Monbl Augenheilkd.. 2025;242(4):485-488. doi: [10.1055/a-2466-0284](https://doi.org/10.1055/a-2466-0284) Study details **Purpose**: Current clinical measurements of strabismus angles (SAs) are manual and require a skilled examiner and active cooperation by patients. This results in high interexaminer variability, and clinical use is limited by the availability of trained examiners. An objective and automated procedure, independent of the examiner, would be useful. **Methods**: This single-center, prospective, diagnostic feasibility study compared the vertical and horizontal SA of patients, as measured with a commercially available virtual reality headset (VRH) and custom software[4](https://www.machinemd.com/science#footnote) with the gold standard measurements performed manually with the Harms tangent screen (HW) and the alternate prism cover test (ACT). We implemented the ACT by showing the patient a fixation target on each eye alternatively with the VRH while recording the eye position of the patient. We then processed the data with custom written software to calculate the SA of the patients. These measurements were then compared to the SA measured with HW and the clinical ACT. Thirty-three patients took part in our study. **Results**: We found good correlation between the VRH method and the HW as well as the clinical ACT. Best correlation was found for horizontal SA in the primary position, with the vertical SA in the primary position also correlating well. Peripheral gaze resulted in a slightly lower correlation due to the overestimation of horizontal SA and underestimation of vertical SA; cyclorotation was not measured with the VRH. Overall, VRH, HW, and clinical ACT correlated similarly well as the published interexaminer correlation for ACT. **Conclusions**: The automated measurement of strabismus with a VRH is feasible, easily applicable, fast, accurate, and can be run on consumer hardware that is affordable and increasingly available. Peer-reviewed ### New Diagnostic Options in the Diagnosis of Brain Disorders Coito A, Abegg M, Campell L. Neuro-Ophthalmology Japan.. 2023;40(3):265-278. doi: [10.11476/shinkeiganka.40.265](https://www.jstage.jst.go.jp/article/shinkeiganka/40/3/40_265/_article/-char/en) Study details Eye and pupil movements are sensitive biomarkers for brain disorders affecting the visual- and the oculomotor pathways. Today, neuro-ophthalmological examinations are usually performed manually. They are time-consuming, require well-trained specialists and the results are mostly qualitative. A new generation of diagnostic tools is need- ed to perform a fast, high-quality, automated, and easy-to-use examination of brain function that provides quantifiable and reproducible data. machineMD, a Swiss medical device company, is developing neos™, a non-invasive diagnostic device intended to provide an automatic and quantitative full neuro-ophthalmic work-up. It includes eight measures: visual field, efferent pupillary function, afferent pupillary function, ocular alignment, smooth pursuit, saccades, gaze holding, and fusional amplitudes. --- ## Independent Publications   Conference presentation ### Vertical saccadic peak velocities measured by virtual reality based oculography as a potential biomarker in early Huntington’s disease Caroline Schuetrumpf, David Bratek, Zacaria Assfoor, Melina Katsimpoura, Johanna Haselon, Emilie Reuter, Justus Luerweg, Anneke Horstkotte, Julia Jessen, Helene Moskalew, Ruth Schneider, Ralf Gold, Jeremias Motte, Carsten Saft, Anke Salmen. European Huntington's Disease Network Clinical Research Congress, 2026 Study details ![EHDN\_Poster\_CS\_2026\_AS\_neu](https://www.machinemd.com/hubfs/EHDN_Poster_CS_2026_AS_neu.png) Click to enlarge **Background** Huntington’s disease (HD) is a progressive neurodegenerative disorder characterized by motor, cognitive, and psychiatric symptoms. Oculomotor abnormalities may appear before motor diagnosis and could serve as objective biomarkers of disease progression. This exploratory pilot study investigated whether vertical saccadic peak velocities (SPV), measured using virtual reality (VR)-based oculography, can differentiate healthy controls from individuals at different stages of Huntington’s disease. **Methods** In this prospective study, 108 participants were included: 54 healthy controls, 23 premanifest HD gene carriers (11 far from onset and 12 near onset), and 31 participants with manifest HD. Participants underwent standardized clinical examination and VR-based eye-tracking using [neos](https://www.machinemd.com/neos?hsLang=en)® (machineMD, Switzerland). Vertical saccadic peak velocities were measured in upward and downward directions using 10° and 20° visual stimuli. Measurements from both eyes were combined to calculate weighted mean peak velocities. Group differences were evaluated using ANOVA with Bonferroni post-hoc tests. Associations with disease burden were assessed using the CAP-score (CAG-age-product score). **Results** Upward saccadic peak velocities showed significant differences between participants far from disease onset and those with manifest HD at both 10° and 20° stimulus amplitudes, as well as between healthy controls and manifest HD participants at 10°. Downward saccadic peak velocities showed significant differences only between healthy controls and manifest HD participants at 10° and 20°. Upward saccadic peak velocities were negatively correlated with disease burden (CAP-score), with Spearman correlations of −0.48 at 10° and −0.63 at 20° (both p \< 0.001). Differences in vertical saccadic velocities suggest that VR-based oculography may provide quantitative measures of oculomotor dysfunction across Huntington’s disease stages. **Conclusion** This exploratory pilot study indicates that VR-based eye-tracking can detect differences in vertical saccadic peak velocities between healthy controls and individuals at different stages of Huntington’s disease. Upward saccadic velocities were associated with CAP-score, supporting their potential as objective measures of disease burden. If confirmed in larger, independent longitudinal studies, VR-based oculometrics may serve as biomarkers for Huntington’s disease. Conference presentation ### Functional Proof of Visual System Involvement in Preclinical Multiple Sclerosis Using Virtual Reality-Based Oculometrics Emilie Reuter, David Bratek, Melina Katsimpoura, Justus Luerweg, Caroline Schuetrumpf, Zacaria Assfoor, Johanna Haselon, Anneke Ida Horstkotte, Ralf Gold, Jeremias Motte, Ruth Schneider, Anke Salmen MS Toronto, ACTRIMS-ECTRIMS, 2026 Study details ![MSToronto2026\_Poster\_EmilieSophieReuter\_RIS\_26092026 (1)](https://www.machinemd.com/hubfs/MSToronto2026_Poster_EmilieSophieReuter_RIS_26092026%20(1).png) Click to enlarge **Introduction** The 2024 revision of the McDonald criteria introduced several key changes, including recognition of the optic nerve as a fifth anatomical location for dissemination in space and the possibility of diagnosing people with radiologically isolated syndrome (pwRIS) as having multiple sclerosis (MS) under specific conditions. Subclinical involvement of the visual pathway may therefore contribute to establishing an MS diagnosis. Reliable detection of oculometric changes could support earlier diagnosis and timely treatment. **Objectives** To quantify relative afferent pupillary defect (RAPD) as a subclinical manifestation in pwRIS compared with people with MS (pwMS) and healthy controls (HCs); to identify oculometric differences between groups using virtual reality (VR)-based oculography; and to correlate VR-based oculometrics with established biomarkers. **Methods** This prospective monocentric study included 36 pwRIS, 65 pwMS with a history of unilateral optic neuritis, and 126 HCs. PwRIS and pwMS underwent visual evoked potential (VEP), optical coherence tomography (OCT), and VR-based pupillometry. Pupillometry was performed using [neos](https://www.machinemd.com/neos/quantitative-pupillometry?hsLang=en)® (machineMD, Bern, Switzerland), with alternating light stimuli to assess direct and consensual pupillary light reflexes. The proprietary RAPD neoscore™ was used as a quantitative measure of afferent visual pathway dysfunction, with a cut-off of ±16.47. **Results** The highest median RAPD neoscore™ was observed in pwMS, whereas pwRIS and HCs showed comparable median scores. A subgroup of pwRIS exceeded the RAPD neoscore™ cut-off; none of these participants reached the VEP or OCT threshold for a significant interocular difference. The RAPD neoscore™ correlated positively with VEP and OCT measurements. **Conclusions** VR-based pupillometry robustly detected RAPD in pwMS with a history of optic neuritis, and established measures of visual system involvement, including VEP and OCT, correlated with the RAPD neoscore™. Importantly, the method identified a subgroup of pwRIS with subclinical visual pathway involvement that was not detected by VEP or OCT. Pending further validation, the RAPD neoscore™ may serve as a complementary marker of optic nerve involvement. Conference presentation ### Acute Horner Syndrome identified by Pupillography revealing Internal Carotid Artery Dissection Victoria Borisova, Muriel Dysli European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026 doi: [10.1080/01658107.2026.2651025](https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0021) Study details ![EUNOS\_Muriel](https://www.machinemd.com/hubfs/EUNOS_Muriel.png) Click to enlarge **Introduction** Acute anisocoria with ipsilateral ptosis, particularly when the pupillary asymmetry is greater in the dark, should raise suspicion for Horner syndrome and prompt urgent evaluation for potentially life-threatening causes such as internal carotid artery (ICA) dissection. Early recognition in the neuro-ophthalmology setting is critical to prevent cerebral ischemic complications. **Case Report** - A 38-year-old woman presented with a smaller right pupil and mild right ptosis for 5 days, accompanied by right neck pain and facial pressure. She had recently been physically active. Exam showed right miosis (more pronounced in dim light) with briskly reactive pupils and mild ptosis. - Pupillography ([neos](https://www.machinemd.com/neos/quantitative-pupillometry?hsLang=en)® system) demonstrated a clear right-sided dilatation lag, providing objective confirmation of oculosympathetic dysfunction. Pharmacological testing for Horner syndrome was not pursued because the lopidine test could not be realiably interpreted in cases of recent onset. ![](https://www.machinemd.com/hs-fs/hubfs/image-png-3.png?width=324&height=370&name=image-png-3.png) - Contrast-enhanced computed tomography (CT) of the head and CT angiography (CTA) revealed a short-segment mural hematoma consistent with right ICA dissection, extending from the distal cervical segment to the transition into the petrous segment. No intracranial hemorrhage or cerebral ischemia was detected. ![](https://www.machinemd.com/hs-fs/hubfs/image-png-4.png?width=790&height=532&name=image-png-4.png) **Management** - The patient was admitted for monitoring and started on antiplatelet therapy with Aspirin 100mg. - Cervical artery duplex ultrasound showed no significant stenosis - With no signs of connective tissue disorder and a history of intense physical activity, the dissection was considered likely provoked. - MR angiography (MRA) at 6-month follow-up showed normalization of the vessel lumen. ![](https://www.machinemd.com/hs-fs/hubfs/image-png-Jun-09-2026-09-19-09-3182-AM.png?width=793&height=456&name=image-png-Jun-09-2026-09-19-09-3182-AM.png) **Discussion** - Acute Horner syndrome with ipsilateral neck/facial pain is a classic red flag for ICA dissection. - As pupillary findings may be subtle, objective testing (e.g., pupillography) can support clinical suspicion, expedite emergency imaging, and occasionally a pharmacologic testing is not necessary any more due to the characteristic appearance with dilation lag in pupillography. - Prompt vascular imaging with CTA or MRA is essential for diagnosis. - Early antithrombotic therapy (antiplatelet or anticoagulaton, depending on clinical context) reduces thromboembolic and ischemic risk. - Painful acute Horner syndrome should be treated as an emergency until ICA dissection is excluded. Peer-reviewed ### Virtual reality‑based oculography detects internuclear ophthalmoplegia in multiple sclerosis and other neurological disorders Reuter E, Leurweg J, Katsimpoura M, Haselon J, Bratek D, Assfoor Z, Schuetrumpf C, Klimas R, Jessen J, Saft C, Ayzenberg I, Fisse A, Pitarokoili K, Schneider-Gold C, Gold R, Motte J, Schneider R, Salmen A. Journal of Neurology, 2026 doi: [10.1007/s00415-026-13906-x](https://doi.org/10.1007/s00415-026-13906-x) Study details **Background** Clinical–neurological examination may underestimate internuclear ophthalmoplegia (INO). We investigated immersive virtual reality (VR)-based eye-tracking ([neos](https://www.machinemd.com/neos?hsLang=en)®, machineMD) in patients with multiple sclerosis (MS), other neurological disorders (ND), and healthy controls (HC) to detect INO.   **Methods** In this prospective monocentric study, 471 participants (243 MS, 104 ND, 124 HC) underwent horizontal prosaccade testing (± 10°, ± 20°) using VR-based oculography. INO was determined in a blinded manner based on software-generated reports comparing adduction and abduction velocities. VR-based and clinical assessments were compared using Cohen’s kappa (κ). Associations with demographic and clinical variables were analyzed using logistic regression.   **Results** VR-based assessment identified 43 cases of INO (40 ND, 3 HC). Agreement between VR-based and clinical assessment was moderate (κ = 0.42; 92.5% observer agreement; n = 414). Three cases were identified clinically only, whereas 28 were detected by VR-based assessment only.   Within MS, agreement was similar (κ = 0.45; 89.1% agreement; n = 238), with 23 cases detected by VR only and three clinically only. In MS, VR-based INO was associated with male sex (p = 0.035), higher expanded disability status scale (EDSS) and brainstem functional system scores (p \< 0.001), longer disease duration and older age (p = 0.002), and visual complaints (p = 0.007). In multivariable analysis, disease duration (OR 1.12, 95% CI 1.01–1.24), brainstem involvement (OR 21.59, 1.30–358.07), and clinical INO (OR 8.18, 1.43–46.96) were associated with VR-based INO.   **Conclusions** VR-based eye-tracking showed moderate agreement with clinical assessment and identified additional cases of INO associated with markers of disease burden. These findings support further evaluation of VR-derived measures as complementary digital biomarkers of brainstem dysfunction. Conference presentation ### Virtual Reality-Based Optokinetic After-Nystagmus as an Objective Diagnostic Tool for PPPD: A Pilot Study Reynders M, Van Der Sypt L, Bertolini G, Foulon I. Association for Research in Vision and Ophthalmology (ARVO) Annual Meeting, 2026 doi: [2816915](https://iovs.arvojournals.org/article.aspx?articleid=2816915) Study details **Background**: Persistent Postural-Perceptual Dizziness (PPPD) is a common chronic vertigo disorder triggered by postural changes, motion, and complex visual environments. The diagnostic criteria defined by the Bárány Society in 2017 are entirely subjective, and no objective biomarkers are currently available. This makes accurate diagnosis challenging, despite the condition’s substantial impact on quality of life. Optokinetic after-nystagmus (OKAN) has recently been proposed as a potential objective marker for visual dependence and functional vestibular disorders, including PPPD. However, traditional OKAN measurement techniques require specialized full-field optokinetic drums and are not feasible for routine clinical practice. The aim of this study is to determine whether Virtual Reality (VR) can reliably induced and measure the OKAN, and whether VR-derived OKAN parameters can distinguish PPPD patients from healthy controls.  **Methods**: In this prospective cross-sectional pilot study, twelve healthy participants and thirteen PPPD patients underwent VR-based optokinetic stimulation with integrated eye-tracking[5](https://www.machinemd.com/science#footnote). The optokinetic stimulus consisted of a 40°/s full-field visual motion pattern presented for 60 seconds. All patients received standard clinical audiovestibular testing (vHIT, VNG, audiometry) and MRI. Outcome measures included OKAN presence, OKAN time constant (TC, s), OKN nystagmus score (%), test acceptability questionnaires (Likert /5) and test wellbeing questionnaires (Likert /5).  **Results**: PPPD patients demonstrated significantly lower OKAN TC (3.05s vs. 19.72s in controls, p = 0.003) and lower OKN nystagmus scores (70.21% vs. 77.03% in controls, p = 0.032). The OKAN TC showed a sensitivity of 79% and a specificity of 83%. Test acceptability and wellbeing scores did not differ significantly between groups and consistently met predefined minimal viable product (MVP) thresholds (wellbeing: 3.0 vs. 3.3, MVP\>3; acceptability: 4.3 vs. 4.7, MVP \>4; both p \> 0.05).  **Conclusion**: The pilot study demonstrated that VR-based OKAN measurement is technically feasible, well tolerated, and enables OKAN assessment without specialized rotation chairs or optokinetic drums. The significant differences in optokinetic parameters between PPPD patients and healthy controls suggest that VR-OKAN could serve as a promising objective diagnostic tool. Further validation in larger and longitudinal cohorts is warranted to determine its clinical potential. Conference presentation ### Reality Check: Virtual Tools in Functional Vision Disorders Kotay M, Eggenberger E. European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026; American Academy of Neurology (AAN) Annual Meeting, 2026 doi: [10.1080/01658107.2026.2651025](https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0017) Study details **Purpose** Describe the utility of virtual perimetry in workup of patients with functional visual loss (FVL). **Methods** Retrospective review of 9 patients ages 19-60 years presenting with visual defects on automated perimetry due to functional visual loss. The patients presented with varied visual symptoms including abnormal automated perimetry in contrast to intact confrontational perimetry and normal structural exam. Virtual perimetry ([neos](https://www.machinemd.com/neos?hsLang=en)®, machineMD) was performed and compared to automated perimetry. **Results** While standard automated perimetry revealed varied defects, VR perimetry documented largely normal visual fields, one patient had a deficit inconsistent with AF. 2 patients had monocular deficits on perimetry and normal virtual perimetry; 2 patients with monocular deficit on automated perimetry showed a homonymous pattern on virtual;1 patients with right homonymous defects on automated perimetry had normal virtual perimetry; 2 patient showed bilateral constriction AF with normal VR; 1 had central scotoma OU with normal VR; and 1 had variable deficits measured over time on AF with normal VR. **Conclusion** VR-based perimetry provides a novel tool for assessing visual function and may be a valuable adjunct in evaluating patients with suspected functional visual loss. The usefulness of virtual perimetry in functional patients may be related to a binocular paradigm with monocular data acquisition. Conference presentation ### Resolution of Post-Concussion Horner’s Syndrome and Oculomotor Dysfunction Documented by Virtual Reality Diagnostics Stetson G. North American Neuro-Ophthalmology Association (NANOS) Annual Meeting, 2026 Study details ![Horner's NANOS 2026](https://www.machinemd.com/hubfs/Screenshot%202026-03-21%20at%2017.51.14.png) Click to enlarge **Purpose** Concussion frequently disrupts visual pathways, making neuro-ophthalmic assessment critical for both diagnosis and monitoring recovery. The purpose of this case study is to describe what appears to be, after literature searches on PubMed and Google Scholar, one of the first reported cases of post-concussive Horner’s syndrome, as well as oculomotor dysfunction, and to illustrate its resolution using a virtual-reality (VR) neuro-ophthalmic diagnostic platform.  **Case Report** A 44-year-old man developed frontal-temporal headaches provoked by near-vision tasks—scrolling on phone, reading, and gaming—after a ball struck his face several months earlier. While the patient demonstrated normal best-corrected visual acuity, his initial examination revealed left-eye Horner’s syndrome (upper-lid ptosis, lower-lid “reverse” ptosis, anisocoria with dilation lag) and saccadic intrusions on near-point-of-convergence testing. Ocular health was otherwise unremarkable.  VR-based neuro-ophthalmic testing showed a comitant eso deviation, left-eye dilation lag without relative afferent pupillary defect, saccadic inaccuracies and corrections, reduced saccadic velocity in down going saccades \> up going saccades, saccadic intrusions and endgaze nystagmus during smooth pursuit, mildly inaccurate convergence beyond 5°, and limited divergence (≈1.5°).  Six months later the clinical signs of Horner’s syndrome had completely resolved, along with some signs of oculomotor dysfunction. Repeat VR testing demonstrated normal pupillary function, more accurate saccades, fewer saccadic intrusions and less endgaze nystagmus on pursuits, improved convergence, and absent divergence fusion; vertical-saccade velocities were unchanged.  **Conclusion** This case demonstrates that Horner’s syndrome can occur as a transient sequela of concussion and may resolve within months. Serial assessment with a VR neuro-ophthalmic platform objectively captured both the presence and the resolution of sympathetic dysfunction as well as broader oculomotor recovery. This helps underscore the technology’s value in the diagnosis and monitoring of concussion and, by extension, more severe traumatic brain injury.  Conference presentation ### Precision of VR-Based Eye Tracking for Gaze and Pupil Measurements in Children Spychala B, Vossenkaul A, Brémovà-Ertl T. American Association for Pediatric Ophthalmology and Strabismus (AAPOS) Annual Meeting, 2026 Study details ![16032025\_AAPOS-2026\_mMD-Poster\_Bis\_final](https://www.machinemd.com/hubfs/16032025_AAPOS-2026_mMD-Poster_Bis_final.png) Click to enlarge **Introduction**:  Virtual reality (VR) eye-tracking headsets are increasingly used in neuro-ophthalmology, allowing precise measurements in a controlled environment. This study evaluates their performance in measuring gaze direction and pupil size in children. **Methods**:  For this study (swissethics-BASEC project-ID: 2023-D0055) 22 healthy children (12 female, 10 male; 3-12 years) and 145 adults and adolescents (76 female, 69 male, 13-92 years) were assessed with the VR- based medical eye-tracking device ([neos](https://www.machinemd.com/neos/ocular-alignment?hsLang=en)®). The device examines oculomotor parameters by measuring pupil size and gaze directions. Descriptive statistics were conducted comparing the measurement precision in children with adolescents and adults. **Results**:  The precision of gaze direction was lower in children (median 0.97°, 95th percentile 3.81°) compared with adolescents and adults (median 0.35°, 95th percentile 0.84°). Pupil size measurements were similarly precise in children (median 0.09 mm, 95th percentile 0.18 mm) compared with adolescents and adults (median 0.05 mm, 95th percentile 0.16 mm). Unstable eye-tracking and low task-compliance were more frequently observed in children than in adults and adolescents. **Conclusion/Relevance**:  The VR-based neos™ eye-tracking system can be utilized for precise assessments of pupillary function in children, whereas the assessments relying on eye-gaze should be interpreted with caution. The measurement precision in children could further be improved by adapting the hardware to fit smaller heads better and by optimising the stimuli for children. Preliminary data in 20 children (with Galactosemia and healthy controls; swissethics-BASEC 202300714) support these findings and emphasize the need for larger pediatric studies.  Conference presentation ### Automated oculography using a VR-headset in moderately to severely disabled MS patients Katsimpoura M, Haselon J, Klimas R, Gold R, Motte J, Salmen A ECTRIMS 2024. Multiple Sclerosis Journal. 2024;30(3\_suppl):125-680. doi: [10.1177/13524585241269219](https://doi.org/10.1177/13524585241269219) Study details **Introduction**: Although frequently reported by Multiple Sclerosis patients (MS), it is hard to objectify subtle changes in oculomotor function. An objective measure of oculomotor involvement might represent a biomarker alleviating lesion localization, assessing disease progression and response to treatment. We applied a novel eye-tracking tool (PRET™, machineMD AG, Switzerland)[3](https://www.machinemd.com/science#footnote) to objectively assess a quantitative neuroophthalmological status in moderately to severely disabled MS and healthy controls (HC). **Objectives**: We aim to i) demonstrate feasibility of PRET™ in neurological conditions and ii) provide an objective measure of deviations in primary gaze and horizontal/vertical saccades. **Methods**: MS and HC were recruited for a pilot study using PRET™, a virtual reality (VR-)headset-based oculography tool (ethics approval no. 23-7934-BR, Ruhr-University Bochum). We examined MS with an expanded disability status scale (EDSS) of ⩾3.0 and sex- and age-matched HC. PRET™ runs an automated programme examining gaze holding and horizontal and vertical saccades, among other parameters not evaluated, here. Descriptive statistics include median \[interquartile range, IQR\] and absolute frequencies. Fisher’s exact and Mann-Whitney test were used for comparisons. Exact p-values are given. **Results**: We examined 17 MS (47.1 \[41.2-56.6\] years; n=12 female, n=5 male; n=12 relapsing-remitting MS (RRMS), n=4 secondary progressive MS (SPMS), n=1 primary progressive MS (PPMS); EDSS 4.0 \[3.0-5.5\]) and 17 HC (47.4 \[40.5-56.1\] years; n=12 female, n=5 male). None of HC and 8/17 MS reported subjective ocular complaints. All participants underwent PRET™ examination without patient-sided abortion due to discomfort or motion sickness. Primary gaze abnormalities were detected in 7/16 MS and 2/16 HC (data missing in n=1 each, p=0.1134). Saccadic abnormalities were present in 10/17 MS and 3/17 HC (p=0.0324), mostly driven by horizontal saccadic abnormalities, such as subtle internuclear ophthalmoplegia (INO; 8/17 MS, 1/17 HC, p=0.0167; vertical: 5/17 MS, 3/17 HC, p=0.6880). In HC, presence of saccadic abnormalities was not associated with age (p=0.5088). **Conclusions**: VR-examination was feasible and well-tolerated by all MS and HC. Primary gaze and saccadic abnormalities were detected in a higher proportion of MS with moderate to severe disability than HC with some specific patterns such as INO not detected during routine clinical examination. VR-based oculography may serve as an outcome tool if further confirmed during our study in different MS stages. Peer-reviewed ### Case Report: Improvement of diplopia due to severe internuclear ophthalmoplegia by 4-aminopyridine documented using a novel virtual reality-based oculography headset Reuter E, Luerweg J, Schneider R, Klimas R, Motte J, Gold R, Salmen A Frontiers in Virtual Reality. Volume 6, 2025 doi: [10.3389/frvir.2025.1595694](https://doi.org/10.3389/frvir.2025.1595694) Study details **Background**: Internuclear ophthalmoplegia (INO) is an eye movement disorder that occurs in approximately one-third of people with multiple sclerosis (MS). **Methods**: We used a novel, head-mounted, virtual reality (VR)-based oculography device (PRET™, machineMD AG, Switzerland)[3](https://www.machinemd.com/science#footnote) to objectively measure oculomotor symptoms reported by a patient with MS to aid in the clinical diagnosis confirmation of INO. **Conclusions**: The patient’s symptoms, primarily diplopia, were managed successfully with 4-aminopyridine. The VR-based eye-tracking tool documented the subjective improvement in oculomotor function tracking treatment effects. Conference presentation ### AI-supported oculography using a VR-headset in severe generalized Myasthenia Gravis patients Katsimpoura M, Haselon J, Klimas R, Gold R, Schneider-Gold C, Motte J, Salmen A EUNOS 2024. Neuro-Ophthalmology. 48(sup1):1-165, 2024 doi: [10.1080/01658107.2024.2342769](https://doi.org/10.1080/01658107.2024.2342769) Study details **Background**: Oculomotor symptoms are frequent in Myasthenia Gravis (MG) and significantly contribute to the burden of disease in affected patients. Nevertheless, reporting of performance-dependent occurrence of double vision can often not directly be reproduced during short-term clinical examination. Here, we applied a novel AI-supported tool (PRET™)[3](https://www.machinemd.com/science#footnote) to objectively assess a quantitative neuroophthalmological status in patients with severe generalized MG and to demonstrate feasibility of PRET™ in neurological conditions affecting the oculomotor system. **Methods**: Patients with different neurological conditions and healthy controls are currently recruited for a prospective pilot study using PRET™, a novel virtual reality (VR-) headset-based oculography tool (ethics approval no. 23-7934-BR, 15-Nov-2023, ethics committee of the Medical Faculty of Ruhr-University Bochum). Within this framework, patients with severe generalized MG have been examined clinically and using PRET™ and scored (activities of daily living MG-ADL, quality of life MG-QoL). PRET™ runs an automated programme examining gaze holding and eye movements including horizontal and vertical saccades and horizontal smooth pursuit as well as ocular alignment, fusional amplitudes, visual fields and pupillary function (the latter not evaluated, here) within less than 12 minutes. We qualitatively summarize the data of the first three patients. **Results**: We present the baseline data of three MG patients prior to their first infusion of an ongoing efgartigimod treatment, all of whom reporting end-of-dose symptom worsening before reinfusion (Pat. 1: male, 63 years; Pat. 2: male, 43 years; Pat. 3: female, 21 years). All patients reported double vision of varying degrees. They fully underwent PRET™ examination without patient-sided interruption or abortion due to discomfort or motion sickness. As compared to three healthy participants with only few, patients 1 and 2 showed several saccadic intrusions during gaze holding, yet still being able to fixate with only minor intereye horizontal gaze position difference (below 2°). Patient 3 complaining constant double vision was not able to binocularly fixate in all positions except for right-up gaze (intereye horizontal gaze position difference ranging from 5 to 10° except for right-up gaze with 0-3°). During smooth horizontal pursuit, performed approximately 7 minutes after start of the examination, the intereye difference is higher as compared to the initial phase of the examination in all three patients hampering binocular fixation. This phenomenon of exhaustion is not seen in either of the healthy participants. **Conclusions**: The automated neuroophthalmological examination was feasible in all three patients and informed objectively about performance-dependent worsening of MG-associated oculomotor symptoms during the 12-minute examination. It clearly outperformed sole clinical examination and may serve as a novel outcome tool if further confirmed during our ongoing study. Peer-reviewed ### Usability of a Virtual Reality Goggle as a New Diagnostic Device in Ophthalmological Practice Job O, Spoerri M, Golla K, et al. Klin Monbl Augenheilkd. 242(4):495-497, 2025 doi: [10.1055/a-2511-6090](https://doi.org/10.1055/a-2511-6090) Study details **Background**: PRET[3](https://www.machinemd.com/science#footnote) is a novel diagnostic device based on a commercially available virtual reality goggle and has been recently introduced by the company machineMD to serve as a neuro-ophthalmological assessment tool. Although the introduction of innovative devices such as PRET has the potential to improve ophthalmological practice, their clinical practicability and tolerability is not always guaranteed. The aim of this study was therefore to assess the usability and tolerability of PRET. **Methods**: A 6-week, prospective study was conducted at our institution in 2024. We included both healthy subjects from our institution and patients from the neuro-ophthalmological clinic. Data on demographics, participants' perception, and evaluation of the assessment (measured using a visual analog scale \[good, mediocre, poor\]), the technician's impression of the device's technical performance, as well as the need for surveillance over the assessment, were obtained via a standardized questionnaire by the same technician. The study was approved by the ETH Zurich Ethics Commission (EK 2024-N-177) and informed consent was obtained. **Results**: There were 43 participants included in the study, of whom 39 were healthy subjects from our institution and 4 patients from our neuro-ophthalmological practice. Of the total cohort, 20 were women and the median age was 37 years (range 20 - 84). Overall, 86% of participants rated the device as good. Approximately 70% of participants reported no issues with the assessment, 6.2% perceived the exam as strenuous, and only one felt dizzy (without nausea) during the assessment. From a technician's perspective, PRET performed very well in most cases, with technical difficulties occurring during testing in 16% of cases and either before or after testing in 4% of cases. Of the participants, 49% were left with transient goggle marks after the examination, which was considered an acceptable adverse effect. **Conclusions**: In this study, neuro-ophthalmological assessment with PRET demonstrated promising results in terms of clinical practicability and patient tolerance. However, in its current form, PRET is not self-explanatory and requires supervised care by a technician. Further studies are needed to corroborate our findings in a patient-based cohort. 1 The RAPD neoscore™ is available in the neos® report. Intended use and availability vary by region. 2 The INO neoscore™ is not available as part of neos® in any region. 3 The Precision Research Eye Tracker (PRET™) is a Research Use Only device manufactured by machineMD AG. The virtual reality modality and test paradigms are consistent with those used in neos®.   4 The device used for this study was a lab prototype of neos®. The virtual reality modality and test paradigms are comparable with those now used in neos®.   5 The device used for this study was a lab prototype based on the virtual reality modality used in neos®. The test paradigms are not available as part of neos® in any region. neos® is a certified Class IIa medical device in accordance with the European Union Medical Device Regulation (EU-2017/745 MDR) by TÜV SÜD Danmark (NB 2443) ; EUDAMED Actor ID: CH-MF-000041378; Basic UDI-DI: 7649989541-neos-0XX-F5. MHRA Reference Number: 33043. Swiss manufacturer number: CHRN-MF-20003868 neos® is registered as a Class I medical device in the USA by machineMD AG, Registered Establishment Number: 3029906225, Owner Operator Number: 10089071.  ## Investigator Initiated Studies Are you interested in initiating your own oculometric research using neos®? Complete the form below to connect with the machineMD team: ![MachineMD\_RGB\_C\_DarkBG\[5718\]](https://www.machinemd.com/hs-fs/hubfs/MachineMD_RGB_C_DarkBG%5B5718%5D.png?width=200&height=26&name=MachineMD_RGB_C_DarkBG%5B5718%5D.png "MachineMD_RGB_C_DarkBG[5718]") [career](https://www.machinemd.com/career?hsLang=en) [certifications](https://www.machinemd.com/quality-policy?hsLang=en) [imprint and privacy policy](https://www.machinemd.com/imprint?hsLang=en) [Follow us on LinkedIn](https://www.linkedin.com/company/machinemd) ![](https://f.hubspotusercontent00.net/hubfs/7712601/back-to-top.png) © machineMD AG 2026 | All rights reserved. ```json { "@context" : "https://schema.org", "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "logo" : "https://www.machinemd.com/hubfs/MachineMD_RGB_C_BrightBG.svg", "name" : "machineMD", "sameAs" : [ "https://www.linkedin.com/company/machinemd/", "https://x.com/md_machine", "https://www.youtube.com/@machinemd-neos" ], "url" : "https://www.machinemd.com" } ``` ```json { "@context" : "https://schema.org", "@id" : "https://www.machinemd.com/neos#medicaldevice", "@type" : "MedicalDevice", "alternateName" : "machineMD PRET", "brand" : { "@type" : "Brand", "name" : "machineMD" }, "category" : "Neuro-ophthalmic diagnostic medical device", "description" : "neos is a reusable medical device system intended to present visual stimuli to both eyes individually, and measures the resulting eye movements and pupillary changes of each eye.", "intendedUse" : "neos is intended to provide objective and quantifiable information concerning the afferent and efferent visual system.", "manufacturer" : { "@id" : "https://www.machinemd.com/#organization" }, "model" : "neos", "name" : "neos®", "regulatoryStatus" : { "@type" : "MedicalDevicePurpose", "name" : "Clinical investigational use" }, "url" : "https://www.machinemd.com/neos" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Background Internuclear ophthalmoplegia (INO) and relative afferent pupillary defect (RAPD) are important manifestations of multiple sclerosis (MS), reflecting brainstem and optic nerve involvement. Both are frequently underrecognized in routine clinical practice, particularly in mild or subclinical forms. Objectives To evaluate automated detection of INO and RAPD using quantitative eye tracking and pupillometry, and to compare results with expert interpretation and routine clinical assessments in a real-world MS cohort. Methods We retrospectively analyzed 396 participants with MS from a real-world clinical cohort. Automated INO detection was performed using the Versional Main-Sequence Index (VMSI), which quantifies abducting– adducting asymmetry based on saccadic peak velocity–amplitude relationships. Automated RAPD quantification was performed using the RAPD neoscore, a standardized me", "author" : [ { "@type" : "Person", "name" : "Dominik Brügger" }, { "@type" : "Person", "name" : "Emilie Reuter" }, { "@type" : "Person", "name" : "Justus Luerweg" }, { "@type" : "Person", "name" : "Melina Katsimpoura" }, { "@type" : "Person", "name" : "Bruno Hauser" }, { "@type" : "Person", "name" : "Julian Lehmann" }, { "@type" : "Person", "name" : "Johanna Haselon" }, { "@type" : "Person", "name" : "David Bratek" }, { "@type" : "Person", "name" : "Zacaria Assfoor" }, { "@type" : "Person", "name" : "Caroline Schuetrumpf" }, { "@type" : "Person", "name" : "Ralf Gold" }, { "@type" : "Person", "name" : "Jeremias Motte" }, { "@type" : "Person", "name" : "Ruth Schneider" }, { "@type" : "Person", "name" : "Anke Salmen" } ], "datePublished" : "2026", "description" : "Background Internuclear ophthalmoplegia (INO) and relative afferent pupillary defect (RAPD) are important manifestations of multiple sclerosis (MS), reflecting brainstem and optic nerve involvement. Both are frequently underrecognized in routine clinical practice, particularly in mild or subclinical", "headline" : "Automated Detection of INO and RAPD in Multiple Sclerosis using neos: Uncovering Subclinical Neuro-Ophthalmic Dysfunction in a Real-World Cohort", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/MSToronto_A0_landscape.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "MS Toronto, ACTRIMS-ECTRIMS, 2026" }, "name" : "Automated Detection of INO and RAPD in Multiple Sclerosis using neos: Uncovering Subclinical Neuro-Ophthalmic Dysfunction in a Real-World Cohort", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Purpose To validate automated strabismus angle measurements from a virtual reality (VR)-based eye-tracking medical device (neos®) against standard clinical methods. Methods Retrospective study of 53 paired examinations with neos® and clinical measurements (primarily alternate prism cover test). Examinations performed within ≤2 months were matched by participant, gaze position, and measurement dimension. Agreement in horizontal and vertical deviations (prism diopters) was assessed using intraclass correlation coefficients (ICC), Bland-Altman analysis and Cohen's kappa. Results Agreement between neos® and APCT was strong, with the highest agreement in primary gaze. Primary-gaze ICCs were 0.95 (95% CI, 0.88–0.97) for horizontal and 0.91 (95% CI, 0.85–0.95) for vertical measurements. Across all gaze positions, ICCs were 0.92 and 0.88 for horizontal and vertical measurements, respectively. Fo", "author" : [ { "@type" : "Person", "name" : "Feil M" }, { "@type" : "Person", "name" : "Massatsch P" }, { "@type" : "Person", "name" : "Coito A" }, { "@type" : "Person", "name" : "Spychala B" }, { "@type" : "Person", "name" : "Van Lidth De Jeude J" }, { "@type" : "Person", "name" : "Hubbard I" }, { "@type" : "Person", "name" : "Abegg" }, { "@type" : "Person", "name" : "M" } ], "datePublished" : "2026", "description" : "Purpose To validate automated strabismus angle measurements from a virtual reality (VR)-based eye-tracking medical device (neos®) against standard clinical methods. Methods Retrospective study of 53 paired examinations with neos® and clinical measurements (primarily alternate prism cover test). Exam", "headline" : "Validation of Automated Ocular Alignment Measurements Using a VR-Based Eye-Tracking Medical Device", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/Validation%20of%20Automated%20Ocular%20Alignment%20Measurements%20Using%20a%20VR-Based%20Eye-Tracking%20Device_Poster_AAO%20-%20mMD.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "American Academy of Ophthalmology, 2026" }, "name" : "Validation of Automated Ocular Alignment Measurements Using a VR-Based Eye-Tracking Medical Device", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Purpose To evaluate the diagnostic accuracy of the neos device — a head-mounted display with integrated eye tracking — for objective detection of binocular vision via disparity-induced vergence responses. Methods In this retrospective case series, 50 patients from a tertiary neuro-ophthalmology and strabismus centre (June 2025 – February 2026) underwent neos examination, including fusional amplitude measurement. Clinical binocular status was independently determined using standard tests (Bagolini striated glasses, Lang and TNO stereotests). A blinded grader then assessed neos pdf-reports alone, classifying binocular status based on the presence or absence of a motor vergence response. Diagnostic accuracy was quantified using sensitivity, specificity, and Cohen’s kappa coefficient. Results neos correctly identified 31 of 33 patients with binocular vision and 11 of 17 without. Observed acc", "author" : [ { "@type" : "Person", "name" : "Beate Spychala" }, { "@type" : "Person", "name" : "Mathias Abegg" } ], "datePublished" : "2026", "description" : "Purpose To evaluate the diagnostic accuracy of the neos device — a head-mounted display with integrated eye tracking — for objective detection of binocular vision via disparity-induced vergence responses. Methods In this retrospective case series, 50 patients from a tertiary neuro-ophthalmology and ", "headline" : "Automated and Objective Detection of Binocular Vision with a VR-based medical device", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/20082026_SOG2026_Onovis-Poster_final_bs.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Swiss Society of Ophthalmology Meeting, 2026" }, "name" : "Automated and Objective Detection of Binocular Vision with a VR-based medical device", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Background Infantile nystagmus syndrome (INS) is the most prevalent form of nystagmus encountered in ophthalmic practice. Today its diagnosis relies on clinical observations alone. Oculomotor characteristics have proven diagnostically but were only available in research settings. Here we test a recently introduced eye-movement recording device for its capacity to measure objectively all relevant features of infantile nystagmus syndrome. Objective To evaluate the diagnostic accuracy of the neos eye-movement recording system for detecting INS in an ophthalmic practice, and to compare performance between an experienced neuro-ophthalmologist and a novice reviewer. Methods Retrospective cross-sectional single-centre case series. All patients with a diagnosis containing the keyword \"nystagmus\", a successful neos recording and informed consent were included. Two blinded reviewers — an expert wi", "author" : [ { "@type" : "Person", "name" : "Karim El-Koussy" }, { "@type" : "Person", "name" : "Colin Colmant" }, { "@type" : "Person", "name" : "Mathias Abegg" } ], "datePublished" : "2026", "description" : "Background Infantile nystagmus syndrome (INS) is the most prevalent form of nystagmus encountered in ophthalmic practice. Today its diagnosis relies on clinical observations alone. Oculomotor characteristics have proven diagnostically but were only available in research settings. Here we test a rece", "headline" : "Diagnostic Accuracy of an Eye-tracking based Automated Neuro-Ophthalmic Examination for the Detection of Infantile Nystagmus Syndrome: A Retrospective Case Series", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Swiss Society of Ophthalmology Meeting, 2026" }, "name" : "Diagnostic Accuracy of an Eye-tracking based Automated Neuro-Ophthalmic Examination for the Detection of Infantile Nystagmus Syndrome: A Retrospective Case Series", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Purpose The diagnosis of congenital stationary night blindness (CSNB) may be difficult as retinal structure is relatively preserved. This case report shows how pupillography using a commercially available medical device may differentiate CSNB from retinitis pigmentosa and healthy. Methods A 7-year-old with moderate myopia and subnormal vision despite correction presented with difficulty in darkness. Optical coherence tomography was unremarkable. ERG showed the typical pattern of CSNB. Pupillary responses were assessed using a head-mounted pupillometry system (neos®) measuring light response amplitude and responses to darkness onset. Data were then compared to an age-matched healthy control and a patient with retinitis pigmentosa. Results Both CSNB and retinitis pigmentosa patients exhibited reduced pupillary light response amplitudes compared to the healthy control. At darkness onset, th", "author" : [ { "@type" : "Person", "name" : "Mathias Abegg" } ], "datePublished" : "2026", "description" : "Purpose The diagnosis of congenital stationary night blindness (CSNB) may be difficult as retinal structure is relatively preserved. This case report shows how pupillography using a commercially available medical device may differentiate CSNB from retinitis pigmentosa and healthy. Methods A 7-year-o", "headline" : "Paradoxical Miosis in Darkness in a Child with Congenital Stationary Night Blindness: A Pupillometric Feature Suggesting Differentiation from Retinitis Pigmentosa", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/Poster%20SOG%202026.jpg", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Swiss Society of Ophthalmology Meeting, 2026" }, "name" : "Paradoxical Miosis in Darkness in a Child with Congenital Stationary Night Blindness: A Pupillometric Feature Suggesting Differentiation from Retinitis Pigmentosa", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction To develop and evaluate AI models for Parkinson’s disease (PD) diagnosis using quantitative VR-derived ocular motor and pupillary measurements. Methods 102 PD patients were recruited in Zurich and Exeter; 89 PD patients were analysed. 133 individual PD examinations and 87 healthy-control examinations were included after curation. PD and control examinations were propensity matched on age and sex, treating each examination as separate data points. Participants completed standardized VR-based ocular motor assessments with the neos medical device and clinical examinations. Seven AI models were trained. Model training, feature selection, hyperparameter optimisation, and calibration were performed within a nested cross-validation framework. Eye-movement domains assessed: fixation/alignment, pupil dynamics, saccades, smooth pursuit, and vergence. Conclusion Ocular motor and pupill", "author" : [ { "@type" : "Person", "name" : "Erika Han" }, { "@type" : "Person", "name" : "Ana Coito" }, { "@type" : "Person", "name" : "Hassan Fadavi" }, { "@type" : "Person", "name" : "Bruno Hauser" }, { "@type" : "Person", "name" : "Pia Massatsch" }, { "@type" : "Person", "name" : "Valentina Stozitzky" }, { "@type" : "Person", "name" : "Dongli Li" }, { "@type" : "Person", "name" : "Bettina Balint" }, { "@type" : "Person", "name" : "Helen Dawes" }, { "@type" : "Person", "name" : "Konrad P. Weber." } ], "datePublished" : "2026", "description" : "Introduction To develop and evaluate AI models for Parkinson’s disease (PD) diagnosis using quantitative VR-derived ocular motor and pupillary measurements. Methods 102 PD patients were recruited in Zurich and Exeter; 89 PD patients were analysed. 133 individual PD examinations and 87 healthy-contro", "headline" : "Artificial Intelligence-Driven Identification of Parkinson's Disease Using Oculometrics", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/Screenshot%202026-06-28%20at%2009.05.14.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "European Academy of Neurology Meeting, 2026" }, "name" : "Artificial Intelligence-Driven Identification of Parkinson's Disease Using Oculometrics", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0015", "url" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0015" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction Diagnosis of infantile nystagmus syndrome (INS) is usually based on manual examination, dependent on examiner experience. Objective and quantitative measures may ease diagnosis. Objective To evaluate the diagnostic accuracy of the neos clas IIa eye-movement recording system for detecting INS in a tertiary ophthalmic practice. Methods Retrospective cross-sectional case series Inclusion: patients with and without nystagmus diagnosis Analysis: expert and novice blinded reviewers classified each recording as INS, neurological nystagmus, other nystagmus, or healthy, based solely on the neos PDF report. Clinical diagnosis from routine tertiary served as reference. Sensitivity, specificity, accuracy, and Cohen's kappa (k) were calculated. Results Sixty-four patients included, 18 INS, 46 non-INS (11 other nystagmus, 35 non-nystagmus) Conclusion /Discussion Diagnostic accuracy was hi", "author" : [ { "@type" : "Person", "name" : "Mathias Abegg" }, { "@type" : "Person", "name" : "Ana Coito" }, { "@type" : "Person", "name" : "Colin Colmant" }, { "@type" : "Person", "name" : "Karim ElKoussy" } ], "datePublished" : "2026", "description" : "Introduction Diagnosis of infantile nystagmus syndrome (INS) is usually based on manual examination, dependent on examiner experience. Objective and quantitative measures may ease diagnosis. Objective To evaluate the diagnostic accuracy of the neos clas IIa eye-movement recording system for detectin", "headline" : "Ocular Motor Characteristics of Infantile Nystagmus Syndrome in Clinical Practice Using Standardized Eye Movement Recordings", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/EUNOS%20Poster%202026_Mathias.jpg", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026" }, "name" : "Ocular Motor Characteristics of Infantile Nystagmus Syndrome in Clinical Practice Using Standardized Eye Movement Recordings", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1080/01658107.2026.2651025", "url" : "https://doi.org/10.1080/01658107.2026.2651025" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction Relative afferent pupillary defect (RAPD) is a key clinical sign of asymmetric optic nerve dysfunction. Its assessment is limited by the subjectivity of clinical examination and the restricted sensitivity of structural imaging using optical coherence tomography (OCT), particularly in the acute phase. In the absence of a reliable gold standard, discordance between clinical, structural, and functional measures is expected. This study aimed to compare these modalities and to assess the contribution of quantitative pupillometry as a continuous functional measure for interpreting RAPD under real-world diagnostic conditions. Methods Data from 520 subjects were analyzed, including 132 healthy controls, 265 patients with multiple sclerosis–related disorders, 58 with other demyelinating diseases, and 38 with neurodegenerative conditions. RAPD was assessed clinically and quantified us", "author" : [ { "@type" : "Person", "name" : "Dominik Brügger" }, { "@type" : "Person", "name" : "Melina Katsimpoura" }, { "@type" : "Person", "name" : "Julian Lehmann" }, { "@type" : "Person", "name" : "Bruno Hauser" }, { "@type" : "Person", "name" : "Emilie Reuter" }, { "@type" : "Person", "name" : "Justus Luerweg" }, { "@type" : "Person", "name" : "Johanna Haselon" }, { "@type" : "Person", "name" : "David Bratek" }, { "@type" : "Person", "name" : "Ralf Gold" }, { "@type" : "Person", "name" : "Jeremias Motte" }, { "@type" : "Person", "name" : "Ruth Schneider" }, { "@type" : "Person", "name" : "Anke Salmen" } ], "datePublished" : "2026", "description" : "Introduction Relative afferent pupillary defect (RAPD) is a key clinical sign of asymmetric optic nerve dysfunction. Its assessment is limited by the subjectivity of clinical examination and the restricted sensitivity of structural imaging using optical coherence tomography (OCT), particularly in th", "headline" : "Triangulating Relative Afferent Pupillary Defect Assessment: Functional, Structural and Clinical Perspectives", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026" }, "name" : "Triangulating Relative Afferent Pupillary Defect Assessment: Functional, Structural and Clinical Perspectives", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1080/01658107.2026.2651025", "url" : "https://doi.org/10.1080/01658107.2026.2651025" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Purpose Internuclear ophthalmoplegia (INO) is a characteristic ocular motor sign of multiple sclerosis (MS) resulting from small inflammatory lesions in the medial longitudinal fasciculus (MLF). Subtle variants, such as mild adduction slowing, frequently escape clinical detection. Virtual reality (VR)–based oculography enables objective and quantitative assessment of ocular motor function. This work evaluated whether a Versional Main-Sequence Index (VMSI), based on abducting–adducting asymmetry in the saccadic main-sequence velocity, can automatically detect INO when compared with expert ratings. Methods Eye movements were recorded with a commercially available medical device (neos/PRET, machineMD) during 10° and 20° horizontal saccades. Using all detected saccades for each eye, we estimated the main-sequence parameter k by fitting the relationship peak velocity = k sqrt(amplitude). The ", "author" : [ { "@type" : "Person", "name" : "Brügger D" }, { "@type" : "Person", "name" : "Reuter E" }, { "@type" : "Person", "name" : "Leurweg J" }, { "@type" : "Person", "name" : "Katsimpoura M" }, { "@type" : "Person", "name" : "Hauser B" }, { "@type" : "Person", "name" : "Lehmann J" }, { "@type" : "Person", "name" : "Haselon J" }, { "@type" : "Person", "name" : "Bratek D" }, { "@type" : "Person", "name" : "Assfoor Z" }, { "@type" : "Person", "name" : "Schuetrumpf C" }, { "@type" : "Person", "name" : "Klimas R" }, { "@type" : "Person", "name" : "Saft C" }, { "@type" : "Person", "name" : "Ayzenberg I" }, { "@type" : "Person", "name" : "Fisse A" }, { "@type" : "Person", "name" : "Pitarokoili K" }, { "@type" : "Person", "name" : "Schneider-Gold C" }, { "@type" : "Person", "name" : "Gold R" }, { "@type" : "Person", "name" : "Motte J" }, { "@type" : "Person", "name" : "Schneider R" }, { "@type" : "Person", "name" : "Salmen A." } ], "datePublished" : "2026", "description" : "Purpose Internuclear ophthalmoplegia (INO) is a characteristic ocular motor sign of multiple sclerosis (MS) resulting from small inflammatory lesions in the medial longitudinal fasciculus (MLF). Subtle variants, such as mild adduction slowing, frequently escape clinical detection. Virtual reality (V", "headline" : "Automated Detection of Internuclear Ophthalmoplegia Using VR-based Eye Tracking", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/ARVO%202026%20poster.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Association for Research in Vision and Ophthalmology (ARVO) Annual Meeting, 2026" }, "name" : "Automated Detection of Internuclear Ophthalmoplegia Using VR-based Eye Tracking", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://iovs.arvojournals.org/article.aspx?articleid=2815264", "url" : "https://iovs.arvojournals.org/article.aspx?articleid=2815264" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction Parkinson’s disease (PD) diagnosis remains largely based on clinical evaluation, creating a need for objective and quantifiable biomarkers to enhance diagnostic accuracy, enable earlier detection, and support longitudinal monitoring. Eye movement and pupillary abnormalities are increasingly recognized as sensitive indicators of PD-related dysfunction in ocular motor control pathways. Advances in virtual reality (VR)–based eye tracking allow standardized measurement of such parameters (“oculometrics”) and provide promising inputs for artificial intelligence (AI)–driven classification models. This study aimed to develop and evaluate machine learning approaches for distinguishing PD from healthy individuals using quantitative ocular motor and pupillary metrics acquired with a VR-based medical eye-tracking device. Methods Individuals with idiopathic PD were recruited at two clin", "author" : [ { "@type" : "Person", "name" : "Erika Han" }, { "@type" : "Person", "name" : "Ana Coito" }, { "@type" : "Person", "name" : "Hassan Fadavi" }, { "@type" : "Person", "name" : "Bruno Hauser" }, { "@type" : "Person", "name" : "Pia Massatsch" }, { "@type" : "Person", "name" : "Valentina Stozitzky" }, { "@type" : "Person", "name" : "Dongli Li" }, { "@type" : "Person", "name" : "Bettina Balint" }, { "@type" : "Person", "name" : "Helen Dawes" }, { "@type" : "Person", "name" : "Konrad P. Weber." } ], "datePublished" : "2026", "description" : "Introduction Parkinson’s disease (PD) diagnosis remains largely based on clinical evaluation, creating a need for objective and quantifiable biomarkers to enhance diagnostic accuracy, enable earlier detection, and support longitudinal monitoring. Eye movement and pupillary abnormalities are increasi", "headline" : "Artificial Intelligence-Based Classification of Parkinson’s Disease Using Virtual Reality-Derived Oculometrics", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026" }, "name" : "Artificial Intelligence-Based Classification of Parkinson’s Disease Using Virtual Reality-Derived Oculometrics", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#d1e171", "url" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#d1e171" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Neurological disorders are often difficult to diagnose and monitor, particularly in the early stages when symptoms may be subtle or nonspecific. Because the visual system engages a large portion of the cerebral cortex and relies on well-defined neural pathways, it offers a unique and accessible window into brain function. In this context, the concepts of oculomics and oculometrics have gained increasing attention. Oculomics refers to the study of systemic and neurological diseases through ocular biomarkers, while oculometrics involves the computational quantification of eye and pupil parameters. Together, these approaches provide noninvasive, objective, and reproducible methods to assess neurological function, with strong potential to improve diagnostic precision, monitor disease progression, and guide individualized care. This review synthesizes recent advances in ocular motor and pupil", "author" : [ { "@type" : "Person", "name" : "Coito A" }, { "@type" : "Person", "name" : "Brügger D" }, { "@type" : "Person", "name" : "Brémovà-Ertl T" }, { "@type" : "Person", "name" : "Massatsch P" }, { "@type" : "Person", "name" : "Abegg M" }, { "@type" : "Person", "name" : "Weber K" }, { "@type" : "Person", "name" : "Salmen A" } ], "datePublished" : "2026", "description" : "Neurological disorders are often difficult to diagnose and monitor, particularly in the early stages when symptoms may be subtle or nonspecific. Because the visual system engages a large portion of the cerebral cortex and relies on well-defined neural pathways, it offers a unique and accessible wind", "headline" : "Advances in ocular motor and pupil biomarkers for neurological disorders", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/BRAIN%20graphical%20abstract_white.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Brain Communications, Volume 8, Issue 2, 2026" }, "name" : "Advances in ocular motor and pupil biomarkers for neurological disorders", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1093/braincomms/fcag102", "url" : "https://doi.org/10.1093/braincomms/fcag102" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Objective: The development of artificial intelligence (AI) models for diagnosing Parkinson’s disease (PD) using ocular motor parameters obtained from a virtual reality (VR)-based medical device. Background: PD diagnosis currently relies largely on clinical examination, underscoring the need for objective biomarkers to enhance diagnostic accuracy, early detection and disease monitoring. Eye movement and pupil function abnormalities have emerged as promising candidates, reflecting PD-related dysfunction in ocular motor control pathways. Design/Methods: Eighty-one patients with idiopathic PD were enrolled in Zurich (Switzerland) and Exeter (UK). Each participant underwent two visits, including standardized ocular motor testing with the VR-based medical eye tracker (neos®, machineMD) and corresponding manual examination. Data with poor tracking quality or excessive signal loss were excluded.", "author" : [ { "@type" : "Person", "name" : "Han E" }, { "@type" : "Person", "name" : "Fadavi H" }, { "@type" : "Person", "name" : "Massatsch P" }, { "@type" : "Person", "name" : "Li D" }, { "@type" : "Person", "name" : "Dawes H" }, { "@type" : "Person", "name" : "Coito A" }, { "@type" : "Person", "name" : "Hauser B" }, { "@type" : "Person", "name" : "Stozitzky V" }, { "@type" : "Person", "name" : "Balint B" }, { "@type" : "Person", "name" : "Weber K P." } ], "datePublished" : "2026", "description" : "Objective: The development of artificial intelligence (AI) models for diagnosing Parkinson’s disease (PD) using ocular motor parameters obtained from a virtual reality (VR)-based medical device. Background: PD diagnosis currently relies largely on clinical examination, underscoring the need for obje", "headline" : "AI-Based Classification of Parkinson's Disease Using Quantitative Ocular Motor Biomarkers", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/Screenshot%202026-03-20%20at%2017.14.02.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "North American Neuro-Ophthalmology Society (NANOS) Annual Meeting, 2026" }, "name" : "AI-Based Classification of Parkinson's Disease Using Quantitative Ocular Motor Biomarkers", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction Diabetic Retinopathy (DR) causes retinal ischemia, leading to impaired dark adaptation due to high oxygen demand. Hypothesis: Recovery of the pupillary light reflex (PLR) is delayed in DR patients compared with healthy controls. Methods Design: Multi-center, non-interventional pilot study comparing PLR recovery in DR patients with healthy controls (HC) and retinitis pigmentosa (RP) patients (positive controls). Procedure: Pupillometry examination using the PRET™ VR headset (machineMD AG, Bern, Switzerland)5. Stimulus protocol: Alternating bright and dark stimuli across 50 cycles (dark phase increased by 100ms per cycle) while recording pupil size. Analysis: Linear regression and a linear mixed-effects model were used to test whether pupil responses at different time points and changes in PLR amplitude over time differ between groups. Results Analysis included 10 patients wit", "author" : [ { "@type" : "Person", "name" : "Fierz F" }, { "@type" : "Person", "name" : "Shamshiev M" }, { "@type" : "Person", "name" : "Brügger D" }, { "@type" : "Person", "name" : "Abegg M." } ], "datePublished" : "2026", "description" : "Introduction Diabetic Retinopathy (DR) causes retinal ischemia, leading to impaired dark adaptation due to high oxygen demand. Hypothesis: Recovery of the pupillary light reflex (PLR) is delayed in DR patients compared with healthy controls. Methods Design: Multi-center, non-interventional pilot stu", "headline" : "Recovery of the Pupillary Light Reflex in Diabetic Retinopathy Assessed by Automatic Pupillometry", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/nanos2026%20Fierz.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "North American Neuro-Ophthalmology Society (NANOS) Annual Meeting, 2026" }, "name" : "Recovery of the Pupillary Light Reflex in Diabetic Retinopathy Assessed by Automatic Pupillometry", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Objectives: To validate the RAPD neoscore, a simple and objective metric for detecting RAPD, by comparing its diagnostic accuracy with traditional clinical evaluations. Methods: A cohort of 164 individuals, comprising healthy controls and patients clinically diagnosed with RAPD, underwent neuro-ophthalmic evaluation using a PRET device (machineMD, Switzerland)3 alongside standard clinical assessments. Diagnoses included relapsing-remitting multiple sclerosis (RRMS, n=35), primary progressive multiple sclerosis (PPMS, n=2), secondary progressive multiple sclerosis (SPMS, n=2), and other demyelinating disorders (n=5). RAPD neoscore calculations were performed independently and blinded at a separate site. Diagnostic performance was evaluated using receiver operating characteristic (ROC) curve analysis to determine sensitivity, specificity, and area under the curve (AUC). Results: ROC analys", "author" : [ { "@type" : "Person", "name" : "Brügger D" }, { "@type" : "Person", "name" : "Katsimpoura M" }, { "@type" : "Person", "name" : "Lehmann J" }, { "@type" : "Person", "name" : "Hauser B" }, { "@type" : "Person", "name" : "Reuter E" }, { "@type" : "Person", "name" : "Luerweg J" }, { "@type" : "Person", "name" : "Haselon J" }, { "@type" : "Person", "name" : "Bratek D" }, { "@type" : "Person", "name" : "Gold R" }, { "@type" : "Person", "name" : "Motte J" }, { "@type" : "Person", "name" : "Schneider R" }, { "@type" : "Person", "name" : "Salmen A" } ], "description" : "Objectives: To validate the RAPD neoscore, a simple and objective metric for detecting RAPD, by comparing its diagnostic accuracy with traditional clinical evaluations. Methods: A cohort of 164 individuals, comprising healthy controls and patients clinically diagnosed with RAPD, underwent neuro-opht", "headline" : "Validation of RAPD neoscore: A Novel Digital Biomarker for detecting Relative Afferent Pupillary Defect", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Multiple Sclerosis Journal. 2025;31(3_suppl):136-762." }, "name" : "Validation of RAPD neoscore: A Novel Digital Biomarker for detecting Relative Afferent Pupillary Defect", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://journals.sagepub.com/doi/epub/10.1177/13524585251358344", "url" : "https://journals.sagepub.com/doi/epub/10.1177/13524585251358344" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Purpose: The purpose of this study was to assess the feasibility of detecting relative afferent pupillary defects (RAPDs) using a commercial virtual reality headset equipped with an eye tracker. Methods: This is a cross-sectional study in which we compare the new computerized RAPD test with the traditional clinical standard using the swinging flashlight test. Eighty-two participants including 20 healthy volunteers aged 10 to 88 years were enrolled in this study. We present a bright/dark stimulus alternating between the eyes every 3 seconds using a virtual reality headset, and we simultaneously record changes in pupil size4. To determine the presence of an RAPD, we developed an algorithm analyzing the pupil size differences. For the assessment of the performance of the automated and the manual measurement a post hoc impression based on all available data is created. The accuracy of the ma", "author" : [ { "@type" : "Person", "name" : "Bruegger D" }, { "@type" : "Person", "name" : "Grabe HM" }, { "@type" : "Person", "name" : "Vicini R" }, { "@type" : "Person", "name" : "Dysli M" }, { "@type" : "Person", "name" : "Lussi D" }, { "@type" : "Person", "name" : "Abegg M." } ], "description" : "Purpose: The purpose of this study was to assess the feasibility of detecting relative afferent pupillary defects (RAPDs) using a commercial virtual reality headset equipped with an eye tracker. Methods: This is a cross-sectional study in which we compare the new computerized RAPD test with the trad", "headline" : "Detection of Relative Afferent Pupillary Defects Using Eye Tracking and a VR Headset", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Translational Vision Science and Technology. 2023;12(6):22." }, "name" : "Detection of Relative Afferent Pupillary Defects Using Eye Tracking and a VR Headset", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1167/tvst.12.6.22", "url" : "https://doi.org/10.1167/tvst.12.6.22" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Background: Current standard methods in monitoring glaucoma progression, like optical coherence tomography (OCT) and standard automated perimetry (SAP), have limitations in certain cases. Automated relative afferent pupillary defect (RAPD) and pupillary light reflex (PLR) testing may offer more objective alternatives. This pilot study aimed to evaluate whether RAPD could sufficiently distinguish between the two eyes in asymmetrical glaucoma, and thus could lay the foundation for using the PLR of a single eye to monitor progression longitudinally. Methods: Twenty-one patients underwent quantitative PLR measurements using a virtual reality headset (neos®, machineMD). RAPD was calculated by subtracting the amplitude of PLRs between eyes. Both RAPD and relative SAP (measured using the mean defect or MD) results were correlated to the thickness of the peripapillary retinal nerve fiber layer (", "author" : [ { "@type" : "Person", "name" : "El-Koussy K" }, { "@type" : "Person", "name" : "Höhn R" }, { "@type" : "Person", "name" : "Falcão MBL" }, { "@type" : "Person", "name" : "Hauser B" }, { "@type" : "Person", "name" : "Naidu A" }, { "@type" : "Person", "name" : "Abegg M." } ], "description" : "Background: Current standard methods in monitoring glaucoma progression, like optical coherence tomography (OCT) and standard automated perimetry (SAP), have limitations in certain cases. Automated relative afferent pupillary defect (RAPD) and pupillary light reflex (PLR) testing may offer more obje", "headline" : "Use of a Novel Virtual Reality-Based Pupillography Device for Glaucoma Management: Cross-Sectional Cohort Pilot Study", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Klin Monbl Augenheilkd. 2025;242(4):379-383." }, "name" : "Use of a Novel Virtual Reality-Based Pupillography Device for Glaucoma Management: Cross-Sectional Cohort Pilot Study", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1055/a-2460-0147", "url" : "https://doi.org/10.1055/a-2460-0147" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Purpose: In virtual reality (VR) systems that track eye movements using infra-red cameras, the precision of gaze measurement is crucial for reliable detection of eye movement disorders. Methods: To assess gaze measurement ability and gaze precision consistency of an HMD VR-based medical device system, neos™, under optimal conditions, we used a robotized setup that provides the advantage of mimicking human eye movements with minimal movement variability. We assessed neos™’s gaze examination test twice for thirteen simulated conditions with different noise levels, and then assessed gaze precision and gaze consistency for each by computing the intraclass correlation coefficient (ICC), standard error of measurements (SEM) and Bland-Altman analysis. Results: We found excellent test-retest reliability (ICC > 0.99, SEM = 0.04) for neos™’s gaze precision, with good agreements between first an", "author" : [ { "@type" : "Person", "name" : "Coito A" }, { "@type" : "Person", "name" : "Naidu A" }, { "@type" : "Person", "name" : "Lehmann J" }, { "@type" : "Person", "name" : "Hauser B" }, { "@type" : "Person", "name" : "Brügger D" }, { "@type" : "Person", "name" : "Abegg M." } ], "description" : "Purpose: In virtual reality (VR) systems that track eye movements using infra-red cameras, the precision of gaze measurement is crucial for reliable detection of eye movement disorders. Methods: To assess gaze measurement ability and gaze precision consistency of an HMD VR-based medical device syste", "headline" : "Test-retest reliability of gaze precision of a novel virtual reality-based medical device", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Frontiers in Virtual Reality. 2025;Volume 6." }, "name" : "Test-retest reliability of gaze precision of a novel virtual reality-based medical device", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.3389/frvir.2025.1502679", "url" : "https://doi.org/10.3389/frvir.2025.1502679" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Purpose: Eye and pupil movements are critical biomarkers for assessing neurological conditions. Most functional eye exams are manually performed making them subjective and error-prone; contributing to an estimated 50% misdiagnosis referral rates for neuro-ophthalmic conditions. neos™ (machineMD, Switzerland) is a novel virtual reality (VR) based measurement device, utilizing a head-mounted VR display and stimuli with infra-red eye tracking and proprietary algorithms to perform neuro-ophthalmological based tests in a non-invasive, automated, and quantitative way. However, validation of eye-tracking-based tools like neos™ poses inherent challenges, particularly in separating the device’s performance characteristics from those of the examinee. This study outlines a methodology to isolate and evaluate neos’s performance independent of external influences to ensure measurement reliability and", "description" : "Purpose: Eye and pupil movements are critical biomarkers for assessing neurological conditions. Most functional eye exams are manually performed making them subjective and error-prone; contributing to an estimated 50% misdiagnosis referral rates for neuro-ophthalmic conditions. neos™ (machineMD, Swi", "headline" : "Validation of a novel neuro-ophthalmological measurement device based on virtual reality and eye tracking", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "ARVO 2025: Investigative Ophthalmology & Visual Science. June 2025, Vol.66, 3228." }, "name" : "Validation of a novel neuro-ophthalmological measurement device based on virtual reality and eye tracking", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://iovs.arvojournals.org/article.aspx?articleid=2806844", "url" : "https://iovs.arvojournals.org/article.aspx?articleid=2806844" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Purpose: Current clinical measurements of strabismus angles (SAs) are manual and require a skilled examiner and active cooperation by patients. This results in high interexaminer variability, and clinical use is limited by the availability of trained examiners. An objective and automated procedure, independent of the examiner, would be useful. Methods: This single-center, prospective, diagnostic feasibility study compared the vertical and horizontal SA of patients, as measured with a commercially available virtual reality headset (VRH) and custom software4 with the gold standard measurements performed manually with the Harms tangent screen (HW) and the alternate prism cover test (ACT). We implemented the ACT by showing the patient a fixation target on each eye alternatively with the VRH while recording the eye position of the patient. We then processed the data with custom written softwa", "author" : [ { "@type" : "Person", "name" : "Vicini R" }, { "@type" : "Person", "name" : "Brügger D" }, { "@type" : "Person", "name" : "Grabe H" }, { "@type" : "Person", "name" : "Abegg M." } ], "description" : "Purpose: Current clinical measurements of strabismus angles (SAs) are manual and require a skilled examiner and active cooperation by patients. This results in high interexaminer variability, and clinical use is limited by the availability of trained examiners. An objective and automated procedure, ", "headline" : "Automated Measurement of Strabismus Angles Using a Commercial Virtual Reality Headset", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Klin Monbl Augenheilkd.. 2025;242(4):485-488." }, "name" : "Automated Measurement of Strabismus Angles Using a Commercial Virtual Reality Headset", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1055/a-2466-0284", "url" : "https://doi.org/10.1055/a-2466-0284" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Eye and pupil movements are sensitive biomarkers for brain disorders affecting the visual- and the oculomotor pathways. Today, neuro-ophthalmological examinations are usually performed manually. They are time-consuming, require well-trained specialists and the results are mostly qualitative. A new generation of diagnostic tools is need- ed to perform a fast, high-quality, automated, and easy-to-use examination of brain function that provides quantifiable and reproducible data. machineMD, a Swiss medical device company, is developing neos™, a non-invasive diagnostic device intended to provide an automatic and quantitative full neuro-ophthalmic work-up. It includes eight measures: visual field, efferent pupillary function, afferent pupillary function, ocular alignment, smooth pursuit, saccades, gaze holding, and fusional amplitudes.", "author" : [ { "@type" : "Person", "name" : "Coito A" }, { "@type" : "Person", "name" : "Abegg M" }, { "@type" : "Person", "name" : "Campell L." } ], "description" : "Eye and pupil movements are sensitive biomarkers for brain disorders affecting the visual- and the oculomotor pathways. Today, neuro-ophthalmological examinations are usually performed manually. They are time-consuming, require well-trained specialists and the results are mostly qualitative. A new g", "headline" : "New Diagnostic Options in the Diagnosis of Brain Disorders", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Neuro-Ophthalmology Japan.. 2023;40(3):265-278." }, "name" : "New Diagnostic Options in the Diagnosis of Brain Disorders", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://www.jstage.jst.go.jp/article/shinkeiganka/40/3/40_265/_article/-char/en", "url" : "https://www.jstage.jst.go.jp/article/shinkeiganka/40/3/40_265/_article/-char/en" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Background Huntington’s disease (HD) is a progressive neurodegenerative disorder characterized by motor, cognitive, and psychiatric symptoms. Oculomotor abnormalities may appear before motor diagnosis and could serve as objective biomarkers of disease progression. This exploratory pilot study investigated whether vertical saccadic peak velocities (SPV), measured using virtual reality (VR)-based oculography, can differentiate healthy controls from individuals at different stages of Huntington’s disease. Methods In this prospective study, 108 participants were included: 54 healthy controls, 23 premanifest HD gene carriers (11 far from onset and 12 near onset), and 31 participants with manifest HD. Participants underwent standardized clinical examination and VR-based eye-tracking using neos® (machineMD, Switzerland). Vertical saccadic peak velocities were measured in upward and downward dir", "author" : [ { "@type" : "Person", "name" : "Caroline Schuetrumpf" }, { "@type" : "Person", "name" : "David Bratek" }, { "@type" : "Person", "name" : "Zacaria Assfoor" }, { "@type" : "Person", "name" : "Melina Katsimpoura" }, { "@type" : "Person", "name" : "Johanna Haselon" }, { "@type" : "Person", "name" : "Emilie Reuter" }, { "@type" : "Person", "name" : "Justus Luerweg" }, { "@type" : "Person", "name" : "Anneke Horstkotte" }, { "@type" : "Person", "name" : "Julia Jessen" }, { "@type" : "Person", "name" : "Helene Moskalew" }, { "@type" : "Person", "name" : "Ruth Schneider" }, { "@type" : "Person", "name" : "Ralf Gold" }, { "@type" : "Person", "name" : "Jeremias Motte" }, { "@type" : "Person", "name" : "Carsten Saft" }, { "@type" : "Person", "name" : "Anke Salmen." } ], "datePublished" : "2026", "description" : "Background Huntington’s disease (HD) is a progressive neurodegenerative disorder characterized by motor, cognitive, and psychiatric symptoms. Oculomotor abnormalities may appear before motor diagnosis and could serve as objective biomarkers of disease progression. This exploratory pilot study invest", "headline" : "Vertical saccadic peak velocities measured by virtual reality based oculography as a potential biomarker in early Huntington’s disease", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/EHDN_Poster_CS_2026_AS_neu.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "European Huntington's Disease Network Clinical Research Congress, 2026" }, "name" : "Vertical saccadic peak velocities measured by virtual reality based oculography as a potential biomarker in early Huntington’s disease", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction The 2024 revision of the McDonald criteria introduced several key changes, including recognition of the optic nerve as a fifth anatomical location for dissemination in space and the possibility of diagnosing people with radiologically isolated syndrome (pwRIS) as having multiple sclerosis (MS) under specific conditions. Subclinical involvement of the visual pathway may therefore contribute to establishing an MS diagnosis. Reliable detection of oculometric changes could support earlier diagnosis and timely treatment. Objectives To quantify relative afferent pupillary defect (RAPD) as a subclinical manifestation in pwRIS compared with people with MS (pwMS) and healthy controls (HCs); to identify oculometric differences between groups using virtual reality (VR)-based oculography; and to correlate VR-based oculometrics with established biomarkers. Methods This prospective monoce", "author" : [ { "@type" : "Person", "name" : "Emilie Reuter" }, { "@type" : "Person", "name" : "David Bratek" }, { "@type" : "Person", "name" : "Melina Katsimpoura" }, { "@type" : "Person", "name" : "Justus Luerweg" }, { "@type" : "Person", "name" : "Caroline Schuetrumpf" }, { "@type" : "Person", "name" : "Zacaria Assfoor" }, { "@type" : "Person", "name" : "Johanna Haselon" }, { "@type" : "Person", "name" : "Anneke Ida Horstkotte" }, { "@type" : "Person", "name" : "Ralf Gold" }, { "@type" : "Person", "name" : "Jeremias Motte" }, { "@type" : "Person", "name" : "Ruth Schneider" }, { "@type" : "Person", "name" : "Anke Salmen" } ], "datePublished" : "2026", "description" : "Introduction The 2024 revision of the McDonald criteria introduced several key changes, including recognition of the optic nerve as a fifth anatomical location for dissemination in space and the possibility of diagnosing people with radiologically isolated syndrome (pwRIS) as having multiple scleros", "headline" : "Functional Proof of Visual System Involvement in Preclinical Multiple Sclerosis Using Virtual Reality-Based Oculometrics", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/MSToronto2026_Poster_EmilieSophieReuter_RIS_26092026%20(1).png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "MS Toronto, ACTRIMS-ECTRIMS, 2026" }, "name" : "Functional Proof of Visual System Involvement in Preclinical Multiple Sclerosis Using Virtual Reality-Based Oculometrics", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction Acute anisocoria with ipsilateral ptosis, particularly when the pupillary asymmetry is greater in the dark, should raise suspicion for Horner syndrome and prompt urgent evaluation for potentially life-threatening causes such as internal carotid artery (ICA) dissection. Early recognition in the neuro-ophthalmology setting is critical to prevent cerebral ischemic complications. Case Report A 38-year-old woman presented with a smaller right pupil and mild right ptosis for 5 days, accompanied by right neck pain and facial pressure. She had recently been physically active. Exam showed right miosis (more pronounced in dim light) with briskly reactive pupils and mild ptosis. Pupillography (neos® system) demonstrated a clear right-sided dilatation lag, providing objective confirmation of oculosympathetic dysfunction. Pharmacological testing for Horner syndrome was not pursued becaus", "author" : [ { "@type" : "Person", "name" : "Victoria Borisova" }, { "@type" : "Person", "name" : "Muriel Dysli" } ], "datePublished" : "2026", "description" : "Introduction Acute anisocoria with ipsilateral ptosis, particularly when the pupillary asymmetry is greater in the dark, should raise suspicion for Horner syndrome and prompt urgent evaluation for potentially life-threatening causes such as internal carotid artery (ICA) dissection. Early recognition", "headline" : "Acute Horner Syndrome identified by Pupillography revealing Internal Carotid Artery Dissection", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/EUNOS_Muriel.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026" }, "name" : "Acute Horner Syndrome identified by Pupillography revealing Internal Carotid Artery Dissection", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0021", "url" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0021" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Background Clinical–neurological examination may underestimate internuclear ophthalmoplegia (INO). We investigated immersive virtual reality (VR)-based eye-tracking (neos®, machineMD) in patients with multiple sclerosis (MS), other neurological disorders (ND), and healthy controls (HC) to detect INO. Methods In this prospective monocentric study, 471 participants (243 MS, 104 ND, 124 HC) underwent horizontal prosaccade testing (± 10°, ± 20°) using VR-based oculography. INO was determined in a blinded manner based on software-generated reports comparing adduction and abduction velocities. VR-based and clinical assessments were compared using Cohen’s kappa (κ). Associations with demographic and clinical variables were analyzed using logistic regression. Results VR-based assessment identified 43 cases of INO (40 ND, 3 HC). Agreement between VR-based and clinical assessment was moderate (κ =", "author" : [ { "@type" : "Person", "name" : "Reuter E" }, { "@type" : "Person", "name" : "Leurweg J" }, { "@type" : "Person", "name" : "Katsimpoura M" }, { "@type" : "Person", "name" : "Haselon J" }, { "@type" : "Person", "name" : "Bratek D" }, { "@type" : "Person", "name" : "Assfoor Z" }, { "@type" : "Person", "name" : "Schuetrumpf C" }, { "@type" : "Person", "name" : "Klimas R" }, { "@type" : "Person", "name" : "Jessen J" }, { "@type" : "Person", "name" : "Saft C" }, { "@type" : "Person", "name" : "Ayzenberg I" }, { "@type" : "Person", "name" : "Fisse A" }, { "@type" : "Person", "name" : "Pitarokoili K" }, { "@type" : "Person", "name" : "Schneider-Gold C" }, { "@type" : "Person", "name" : "Gold R" }, { "@type" : "Person", "name" : "Motte J" }, { "@type" : "Person", "name" : "Schneider R" }, { "@type" : "Person", "name" : "Salmen A." } ], "datePublished" : "2026", "description" : "Background Clinical–neurological examination may underestimate internuclear ophthalmoplegia (INO). We investigated immersive virtual reality (VR)-based eye-tracking (neos®, machineMD) in patients with multiple sclerosis (MS), other neurological disorders (ND), and healthy controls (HC) to detect INO", "headline" : "Virtual reality‑based oculography detects internuclear ophthalmoplegia in multiple sclerosis and other neurological disorders", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Journal of Neurology, 2026" }, "name" : "Virtual reality‑based oculography detects internuclear ophthalmoplegia in multiple sclerosis and other neurological disorders", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1007/s00415-026-13906-x", "url" : "https://doi.org/10.1007/s00415-026-13906-x" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Background: Persistent Postural-Perceptual Dizziness (PPPD) is a common chronic vertigo disorder triggered by postural changes, motion, and complex visual environments. The diagnostic criteria defined by the Bárány Society in 2017 are entirely subjective, and no objective biomarkers are currently available. This makes accurate diagnosis challenging, despite the condition’s substantial impact on quality of life. Optokinetic after-nystagmus (OKAN) has recently been proposed as a potential objective marker for visual dependence and functional vestibular disorders, including PPPD. However, traditional OKAN measurement techniques require specialized full-field optokinetic drums and are not feasible for routine clinical practice. The aim of this study is to determine whether Virtual Reality (VR) can reliably induced and measure the OKAN, and whether VR-derived OKAN parameters can distinguish P", "author" : [ { "@type" : "Person", "name" : "Reynders M" }, { "@type" : "Person", "name" : "Van Der Sypt L" }, { "@type" : "Person", "name" : "Bertolini G" }, { "@type" : "Person", "name" : "Foulon I." } ], "datePublished" : "2026", "description" : "Background: Persistent Postural-Perceptual Dizziness (PPPD) is a common chronic vertigo disorder triggered by postural changes, motion, and complex visual environments. The diagnostic criteria defined by the Bárány Society in 2017 are entirely subjective, and no objective biomarkers are currently av", "headline" : "Virtual Reality-Based Optokinetic After-Nystagmus as an Objective Diagnostic Tool for PPPD: A Pilot Study", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Association for Research in Vision and Ophthalmology (ARVO) Annual Meeting, 2026" }, "name" : "Virtual Reality-Based Optokinetic After-Nystagmus as an Objective Diagnostic Tool for PPPD: A Pilot Study", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://iovs.arvojournals.org/article.aspx?articleid=2816915", "url" : "https://iovs.arvojournals.org/article.aspx?articleid=2816915" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Purpose Describe the utility of virtual perimetry in workup of patients with functional visual loss (FVL). Methods Retrospective review of 9 patients ages 19-60 years presenting with visual defects on automated perimetry due to functional visual loss. The patients presented with varied visual symptoms including abnormal automated perimetry in contrast to intact confrontational perimetry and normal structural exam. Virtual perimetry (neos®, machineMD) was performed and compared to automated perimetry. Results While standard automated perimetry revealed varied defects, VR perimetry documented largely normal visual fields, one patient had a deficit inconsistent with AF. 2 patients had monocular deficits on perimetry and normal virtual perimetry; 2 patients with monocular deficit on automated perimetry showed a homonymous pattern on virtual;1 patients with right homonymous defects on automat", "author" : [ { "@type" : "Person", "name" : "Kotay M" }, { "@type" : "Person", "name" : "Eggenberger E." } ], "datePublished" : "2026", "description" : "Purpose Describe the utility of virtual perimetry in workup of patients with functional visual loss (FVL). Methods Retrospective review of 9 patients ages 19-60 years presenting with visual defects on automated perimetry due to functional visual loss. The patients presented with varied visual sympto", "headline" : "Reality Check: Virtual Tools in Functional Vision Disorders", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "European Neuro-Ophthalmology Society (EUNOS) Meeting, 2026; American Academy of Neurology (AAN) Annual Meeting, 2026" }, "name" : "Reality Check: Virtual Tools in Functional Vision Disorders", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0017", "url" : "https://www.tandfonline.com/doi/full/10.1080/01658107.2026.2651025#s0017" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Purpose Concussion frequently disrupts visual pathways, making neuro-ophthalmic assessment critical for both diagnosis and monitoring recovery. The purpose of this case study is to describe what appears to be, after literature searches on PubMed and Google Scholar, one of the first reported cases of post-concussive Horner’s syndrome, as well as oculomotor dysfunction, and to illustrate its resolution using a virtual-reality (VR) neuro-ophthalmic diagnostic platform. Case Report A 44-year-old man developed frontal-temporal headaches provoked by near-vision tasks—scrolling on phone, reading, and gaming—after a ball struck his face several months earlier. While the patient demonstrated normal best-corrected visual acuity, his initial examination revealed left-eye Horner’s syndrome (upper-lid ptosis, lower-lid “reverse” ptosis, anisocoria with dilation lag) and saccadic intrusions on near-po", "author" : [ { "@type" : "Person", "name" : "Stetson G." } ], "datePublished" : "2026", "description" : "Purpose Concussion frequently disrupts visual pathways, making neuro-ophthalmic assessment critical for both diagnosis and monitoring recovery. The purpose of this case study is to describe what appears to be, after literature searches on PubMed and Google Scholar, one of the first reported cases of", "headline" : "Resolution of Post-Concussion Horner’s Syndrome and Oculomotor Dysfunction Documented by Virtual Reality Diagnostics", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/Screenshot%202026-03-21%20at%2017.51.14.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "North American Neuro-Ophthalmology Association (NANOS) Annual Meeting, 2026" }, "name" : "Resolution of Post-Concussion Horner’s Syndrome and Oculomotor Dysfunction Documented by Virtual Reality Diagnostics", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction: Virtual reality (VR) eye-tracking headsets are increasingly used in neuro-ophthalmology, allowing precise measurements in a controlled environment. This study evaluates their performance in measuring gaze direction and pupil size in children. Methods: For this study (swissethics-BASEC project-ID: 2023-D0055) 22 healthy children (12 female, 10 male; 3-12 years) and 145 adults and adolescents (76 female, 69 male, 13-92 years) were assessed with the VR- based medical eye-tracking device (neos®). The device examines oculomotor parameters by measuring pupil size and gaze directions. Descriptive statistics were conducted comparing the measurement precision in children with adolescents and adults. Results: The precision of gaze direction was lower in children (median 0.97°, 95th percentile 3.81°) compared with adolescents and adults (median 0.35°, 95th percentile 0.84°). Pupil siz", "author" : [ { "@type" : "Person", "name" : "Spychala B" }, { "@type" : "Person", "name" : "Vossenkaul A" }, { "@type" : "Person", "name" : "Brémovà-Ertl T." } ], "datePublished" : "2026", "description" : "Introduction: Virtual reality (VR) eye-tracking headsets are increasingly used in neuro-ophthalmology, allowing precise measurements in a controlled environment. This study evaluates their performance in measuring gaze direction and pupil size in children. Methods: For this study (swissethics-BASEC ", "headline" : "Precision of VR-Based Eye Tracking for Gaze and Pupil Measurements in Children", "image" : "https://19556649.fs1.hubspotusercontent-na1.net/hubfs/19556649/16032025_AAPOS-2026_mMD-Poster_Bis_final.png", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "American Association for Pediatric Ophthalmology and Strabismus (AAPOS) Annual Meeting, 2026" }, "name" : "Precision of VR-Based Eye Tracking for Gaze and Pupil Measurements in Children", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" } } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Introduction: Although frequently reported by Multiple Sclerosis patients (MS), it is hard to objectify subtle changes in oculomotor function. An objective measure of oculomotor involvement might represent a biomarker alleviating lesion localization, assessing disease progression and response to treatment. We applied a novel eye-tracking tool (PRET™, machineMD AG, Switzerland)3 to objectively assess a quantitative neuroophthalmological status in moderately to severely disabled MS and healthy controls (HC). Objectives: We aim to i) demonstrate feasibility of PRET™ in neurological conditions and ii) provide an objective measure of deviations in primary gaze and horizontal/vertical saccades. Methods: MS and HC were recruited for a pilot study using PRET™, a virtual reality (VR-)headset-based oculography tool (ethics approval no. 23-7934-BR, Ruhr-University Bochum). We examined MS with an ex", "author" : [ { "@type" : "Person", "name" : "Katsimpoura M" }, { "@type" : "Person", "name" : "Haselon J" }, { "@type" : "Person", "name" : "Klimas R" }, { "@type" : "Person", "name" : "Gold R" }, { "@type" : "Person", "name" : "Motte J" }, { "@type" : "Person", "name" : "Salmen A" } ], "description" : "Introduction: Although frequently reported by Multiple Sclerosis patients (MS), it is hard to objectify subtle changes in oculomotor function. An objective measure of oculomotor involvement might represent a biomarker alleviating lesion localization, assessing disease progression and response to tre", "headline" : "Automated oculography using a VR-headset in moderately to severely disabled MS patients", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "ECTRIMS 2024. Multiple Sclerosis Journal. 2024;30(3_suppl):125-680." }, "name" : "Automated oculography using a VR-headset in moderately to severely disabled MS patients", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1177/13524585241269219", "url" : "https://doi.org/10.1177/13524585241269219" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Background: Internuclear ophthalmoplegia (INO) is an eye movement disorder that occurs in approximately one-third of people with multiple sclerosis (MS). Methods: We used a novel, head-mounted, virtual reality (VR)-based oculography device (PRET™, machineMD AG, Switzerland)3 to objectively measure oculomotor symptoms reported by a patient with MS to aid in the clinical diagnosis confirmation of INO. Conclusions: The patient’s symptoms, primarily diplopia, were managed successfully with 4-aminopyridine. The VR-based eye-tracking tool documented the subjective improvement in oculomotor function tracking treatment effects.", "author" : [ { "@type" : "Person", "name" : "Reuter E" }, { "@type" : "Person", "name" : "Luerweg J" }, { "@type" : "Person", "name" : "Schneider R" }, { "@type" : "Person", "name" : "Klimas R" }, { "@type" : "Person", "name" : "Motte J" }, { "@type" : "Person", "name" : "Gold R" }, { "@type" : "Person", "name" : "Salmen A" } ], "datePublished" : "2025", "description" : "Background: Internuclear ophthalmoplegia (INO) is an eye movement disorder that occurs in approximately one-third of people with multiple sclerosis (MS). Methods: We used a novel, head-mounted, virtual reality (VR)-based oculography device (PRET™, machineMD AG, Switzerland)3 to objectively measure o", "headline" : "Case Report: Improvement of diplopia due to severe internuclear ophthalmoplegia by 4-aminopyridine documented using a novel virtual reality-based oculography headset", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Frontiers in Virtual Reality. Volume 6, 2025" }, "name" : "Case Report: Improvement of diplopia due to severe internuclear ophthalmoplegia by 4-aminopyridine documented using a novel virtual reality-based oculography headset", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.3389/frvir.2025.1595694", "url" : "https://doi.org/10.3389/frvir.2025.1595694" } ``` ```json { "@context" : "https://schema.org", "@type" : "ScholarlyArticle", "abstract" : "Background: Oculomotor symptoms are frequent in Myasthenia Gravis (MG) and significantly contribute to the burden of disease in affected patients. Nevertheless, reporting of performance-dependent occurrence of double vision can often not directly be reproduced during short-term clinical examination. Here, we applied a novel AI-supported tool (PRET™)3 to objectively assess a quantitative neuroophthalmological status in patients with severe generalized MG and to demonstrate feasibility of PRET™ in neurological conditions affecting the oculomotor system. Methods: Patients with different neurological conditions and healthy controls are currently recruited for a prospective pilot study using PRET™, a novel virtual reality (VR-) headset-based oculography tool (ethics approval no. 23-7934-BR, 15-Nov-2023, ethics committee of the Medical Faculty of Ruhr-University Bochum). Within this framework,", "author" : [ { "@type" : "Person", "name" : "Katsimpoura M" }, { "@type" : "Person", "name" : "Haselon J" }, { "@type" : "Person", "name" : "Klimas R" }, { "@type" : "Person", "name" : "Gold R" }, { "@type" : "Person", "name" : "Schneider-Gold C" }, { "@type" : "Person", "name" : "Motte J" }, { "@type" : "Person", "name" : "Salmen A" } ], "datePublished" : "2024", "description" : "Background: Oculomotor symptoms are frequent in Myasthenia Gravis (MG) and significantly contribute to the burden of disease in affected patients. Nevertheless, reporting of performance-dependent occurrence of double vision can often not directly be reproduced during short-term clinical examination.", "headline" : "AI-supported oculography using a VR-headset in severe generalized Myasthenia Gravis patients", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "EUNOS 2024. Neuro-Ophthalmology. 48(sup1):1-165, 2024" }, "name" : "AI-supported oculography using a VR-headset in severe generalized Myasthenia Gravis patients", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1080/01658107.2024.2342769", "url" : "https://doi.org/10.1080/01658107.2024.2342769" } ``` ```json { "@context" : "https://schema.org", "@type" : "MedicalScholarlyArticle", "abstract" : "Background: PRET3 is a novel diagnostic device based on a commercially available virtual reality goggle and has been recently introduced by the company machineMD to serve as a neuro-ophthalmological assessment tool. Although the introduction of innovative devices such as PRET has the potential to improve ophthalmological practice, their clinical practicability and tolerability is not always guaranteed. The aim of this study was therefore to assess the usability and tolerability of PRET. Methods: A 6-week, prospective study was conducted at our institution in 2024. We included both healthy subjects from our institution and patients from the neuro-ophthalmological clinic. Data on demographics, participants' perception, and evaluation of the assessment (measured using a visual analog scale [good, mediocre, poor]), the technician's impression of the device's technical performance, as well as", "author" : [ { "@type" : "Person", "name" : "Job O" }, { "@type" : "Person", "name" : "Spoerri M" }, { "@type" : "Person", "name" : "Golla K" }, { "@type" : "Person", "name" : "et al." } ], "datePublished" : "2025", "description" : "Background: PRET3 is a novel diagnostic device based on a commercially available virtual reality goggle and has been recently introduced by the company machineMD to serve as a neuro-ophthalmological assessment tool. Although the introduction of innovative devices such as PRET has the potential to im", "headline" : "Usability of a Virtual Reality Goggle as a New Diagnostic Device in Ophthalmological Practice", "inLanguage" : "en", "isPartOf" : { "@type" : "CreativeWork", "name" : "Klin Monbl Augenheilkd. 242(4):495-497, 2025" }, "name" : "Usability of a Virtual Reality Goggle as a New Diagnostic Device in Ophthalmological Practice", "publisher" : { "@id" : "https://www.machinemd.com/#organization", "@type" : "Organization", "name" : "machineMD", "url" : "https://www.machinemd.com" }, "sameAs" : "https://doi.org/10.1055/a-2511-6090", "url" : "https://doi.org/10.1055/a-2511-6090" } ```