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

Abstract 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Subhrajit Roy, Diana Mincu, Lev Proleev, Chintan Ghate, Jennifer S. Graves, David F. Steiner, Fletcher Lee Hartsell, Katherine Heller
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-63888-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850140377517916160
author Subhrajit Roy
Diana Mincu
Lev Proleev
Chintan Ghate
Jennifer S. Graves
David F. Steiner
Fletcher Lee Hartsell
Katherine Heller
author_facet Subhrajit Roy
Diana Mincu
Lev Proleev
Chintan Ghate
Jennifer S. Graves
David F. Steiner
Fletcher Lee Hartsell
Katherine Heller
author_sort Subhrajit Roy
collection DOAJ
description Abstract 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.
format Article
id doaj-art-0c98e2d8297843b8838a8d9e2aa1da1f
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0c98e2d8297843b8838a8d9e2aa1da1f2025-08-20T02:29:51ZengNature PortfolioScientific Reports2045-23222025-05-0115111210.1038/s41598-024-63888-xPerformance of machine learning models for predicting high-severity symptoms in multiple sclerosisSubhrajit Roy0Diana Mincu1Lev Proleev2Chintan Ghate3Jennifer S. Graves4David F. Steiner5Fletcher Lee Hartsell6Katherine Heller7Google ResearchGoogle ResearchGoogle ResearchGoogle ResearchDepartment of Neurosciences, University of California, San DiegoGoogle HealthDuke University School of MedicineGoogle ResearchAbstract 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.https://doi.org/10.1038/s41598-024-63888-x
spellingShingle Subhrajit Roy
Diana Mincu
Lev Proleev
Chintan Ghate
Jennifer S. Graves
David F. Steiner
Fletcher Lee Hartsell
Katherine Heller
Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis
Scientific Reports
title Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis
title_full Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis
title_fullStr Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis
title_full_unstemmed Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis
title_short Performance of machine learning models for predicting high-severity symptoms in multiple sclerosis
title_sort performance of machine learning models for predicting high severity symptoms in multiple sclerosis
url https://doi.org/10.1038/s41598-024-63888-x
work_keys_str_mv AT subhrajitroy performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis
AT dianamincu performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis
AT levproleev performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis
AT chintanghate performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis
AT jennifersgraves performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis
AT davidfsteiner performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis
AT fletcherleehartsell performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis
AT katherineheller performanceofmachinelearningmodelsforpredictinghighseveritysymptomsinmultiplesclerosis