Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Explainable machine learning-based identification of transcriptomic biomarkers in CD1c+ dendritic cells for non-infectious uveitis: an integrative analysis of bulk RNA-seq data.

Frontiers in bioinformatics·2026
Same author

An explainable ensemble machine learning framework for predicting cartilage biomechanical degradation from transcriptomic profiles: toward smart orthopedic device design.

Frontiers in bioengineering and biotechnology·2026
Same author

Corrigendum to "Clinical and cognitive outcomes in Ocrelizumab-treated MS patients: Insights into the wearing-off phenomenon" [Multiple Sclerosis and Related Disorders, Volume 103, November 2025, 106689].

Multiple sclerosis and related disorders·2026
Same author

SHAP-based explainable AI framework for autism severity classification using 3D motor biomarkers.

Frontiers in psychiatry·2026
Same author

Neuro-behcet's syndrome: epidemiology, mechanisms, and emerging strategies in diagnosis and treatment.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2026
Same author

An explainable ensemble machine learning model using baseline blood transcriptomics to predict Parkinson's disease motor progression.

Frontiers in digital health·2026

Related Experiment Video

Updated: Jun 23, 2026

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Exploratory analysis of pupillography-based machine learning for assessing autonomic dysfunction in multiple

Neslihan Parmak Yener1, Yelda Fırat2, Meral Seferoğlu1

  • 1Department of Ophthalmology, University of Health Sciences, Bursa Yuksek Ihtisas Training and Research Hospital, Bursa, Turkey.

Multiple Sclerosis and Related Disorders
|June 20, 2026
PubMed
Summary

Machine learning models using pupillography show high sensitivity for detecting Multiple sclerosis (MS) in patients. This noninvasive approach may aid in early diagnosis, though further validation is needed.

Keywords:
Adjunctive analysisAutonomic dysfunctionMachine learningMultiple sclerosisPupillometry

More Related Videos

Software for Analysis of Heart Rate and Blood Pressure Time-series Data from the Valsalva Maneuver
14:28

Software for Analysis of Heart Rate and Blood Pressure Time-series Data from the Valsalva Maneuver

Published on: June 27, 2025

Assessing Cerebral Autoregulation via Oscillatory Lower Body Negative Pressure and Projection Pursuit Regression
11:26

Assessing Cerebral Autoregulation via Oscillatory Lower Body Negative Pressure and Projection Pursuit Regression

Published on: December 10, 2014

Related Experiment Videos

Last Updated: Jun 23, 2026

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

Software for Analysis of Heart Rate and Blood Pressure Time-series Data from the Valsalva Maneuver
14:28

Software for Analysis of Heart Rate and Blood Pressure Time-series Data from the Valsalva Maneuver

Published on: June 27, 2025

Assessing Cerebral Autoregulation via Oscillatory Lower Body Negative Pressure and Projection Pursuit Regression
11:26

Assessing Cerebral Autoregulation via Oscillatory Lower Body Negative Pressure and Projection Pursuit Regression

Published on: December 10, 2014

Area of Science:

  • Ophthalmology
  • Neurology
  • Biomedical Engineering

Background:

  • The pupillary light reflex (PLR) is influenced by autonomic pathways and may serve as a noninvasive biomarker for Multiple sclerosis (MS).
  • Pupillography offers objective quantification of PLR dynamics, but its diagnostic value in MS is not well-established.
  • This study explored the feasibility of using machine learning (ML) on pupillographic features for MS assessment.

Purpose of the Study:

  • To investigate the potential of an ML-based analytical framework using pupillographic features for identifying Multiple sclerosis (MS).
  • To evaluate the diagnostic utility of pupillography in distinguishing relapsing-remitting MS (RRMS) patients from healthy controls.

Main Methods:

  • A random forest classifier was trained on 22 quantitative pupillographic features extracted from 692 images of 25 RRMS patients and 38 healthy controls.
  • The model was evaluated on separate test and independent validation datasets using metrics including accuracy, sensitivity, specificity, and AUC-ROC.
  • Features related to pupil size, shape, reflex dynamics, and symmetry were analyzed.

Main Results:

  • The ML model achieved 85.7% accuracy and 93.8% sensitivity (AUC-ROC: 0.945) on the test set, correctly identifying most MS cases.
  • Performance on the independent validation set was lower (75.0% accuracy, 88.9% sensitivity, 57.1% specificity; AUC-ROC: 0.627).
  • Quadrant-based PLR variations were the most significant features for classification.

Conclusions:

  • ML models utilizing pupillography demonstrate high sensitivity in differentiating RRMS patients from healthy controls, suggesting potential as noninvasive adjunctive diagnostic tools.
  • While specificity decreased in the independent dataset, sensitivity remained high, indicating promise for detecting MS.
  • Further validation with larger cohorts and disease controls is necessary due to the exploratory nature of the study.