Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis

Current care in multiple sclerosis (MS) primarily relies on infrequently obtained data such as magnetic resonance imaging, clinical laboratory tests or clinical history, resulting in subtle changes that may occur between visits being missed. Mobile technology enables continual collection of data and...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 15; no. 1; pp. 18209 - 12
Main Authors: Roy, Subhrajit, Mincu, Diana, Proleev, Lev, Ghate, Chintan, Graves, Jennifer S., Steiner, David F., Hartsell, Fletcher Lee, Heller, Katherine
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 25.05.2025
Nature Publishing Group
Nature Portfolio
Subjects:
692/1807/1486
692/1807/2781
692/617/375/1666
Adult
Autoimmune diseases
Chronic illnesses
Data collection
Deep learning
Disease Progression
Fatigue
Female
Humanities and Social Sciences
Humans
Laboratory tests
Longitudinal Studies
Machine Learning
Magnetic Resonance Imaging
Male
Medical laboratories
Mental depression
Middle Aged
Mobile Applications
multidisciplinary
Multiple sclerosis
Multiple Sclerosis - diagnosis
Multiple Sclerosis - physiopathology
Nervous system
Observational studies
Portable computers
Retrospective Studies
Science
Science (multidisciplinary)
Severity of Illness Index
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Current care in multiple sclerosis (MS) primarily relies on infrequently obtained data such as magnetic resonance imaging, clinical laboratory tests or clinical history, resulting in subtle changes that may occur between visits being missed. Mobile technology enables continual collection of data and can pave the path for predicting complex aspects of MS such as symptoms and disease courses. To this end, we conducted a first-of-its-kind observational study called MS Mosaic. First, we developed and publicly launched a mobile app for collecting longitudinal data from MS subjects in the United States. Second, we ran the study across 3 years in order to capture complex patterns for this slow progressing disease. Finally, we retrospectively developed three classical ML methods and two deep learning models to accurately and continually predict the incidence of five high-severity symptoms (fatigue, sensory disturbance, walking instability, depression or anxiety and cramps/spasms) three months in advance.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Undefined-3
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-63888-x