Related Experiment Video
Updated: May 7, 2026
11:35
The Multiple Sclerosis Performance Test MSPT: An iPad-Based Disability Assessment Tool
Published on: June 30, 2014
58.0K
Validated, Quantitative, Machine Learning-Generated Neurologic Assessment of Multiple Sclerosis Using a Mobile
Sharon Stoll1,2, Charisse Litchman1,2, Noah Rubin3
1From the Department of Neurology, Yale School of Medicine, Yale University, New Haven, CT (SS, CL).
International Journal of MS Care
|March 14, 2024
Summary
The BeCare MS Link mobile app accurately replicates the Expanded Disability Status Scale (EDSS) assessment for multiple sclerosis (MS) patients. This digital tool may provide a more comprehensive evaluation of MS disability.
Area of Science:
- Neurology
- Digital Health
- Machine Learning
Background:
- The BeCare MS Link mobile app collects patient-reported data for multiple sclerosis (MS) assessment.
- It aims to digitally replicate established clinical metrics like the Expanded Disability Status Scale (EDSS).
Purpose of the Study:
- To compare EDSS scores derived from the BeCare MS Link app with those from standard neurologist assessments.
- To evaluate the accuracy of machine learning algorithms in predicting EDSS scores using app-derived data.
Main Methods:
- 35 MS patients' app-derived EDSS data were compared to neurologist-derived EDSS scores.
- Four distinct machine learning algorithms (MLAs) predicted EDSS scores from app data.
- Accuracy was assessed by comparing predicted scores to clinical scores.
Main Results:
- The most accurate MLA achieved exact EDSS score matches in 19 cases and within 0.5 points in 21 cases.
- Over 80% of all MLA-predicted scores were within 1 EDSS point of the clinical assessment.
- Mean squared error ranged from 1.05 to 1.37 across the MLAs.
Conclusions:
- The BeCare MS Link app effectively replicates the clinical EDSS assessment for MS patients.
- This mobile application holds potential for a more thorough evaluation of disability in multiple sclerosis.
