Multi-scale machine learning model predicts muscle and functional disease progression

Abstract Facioscapulohumeral muscular dystrophy (FSHD) is a genetic neuromuscular disorder characterized by progressive muscle degeneration with substantial variability in severity and progression patterns. FSHD is a highly heterogeneous disease; however, current clinical metrics used for tracking d...

Full description

Saved in:
Bibliographic Details
Main Authors: Silvia S. Blemker, Lara Riem, Olivia DuCharme, Megan Pinette, Kathryn Eve Costanzo, Emma Weatherley, Jeff Statland, Stephen J. Tapscott, Leo H. Wang, Dennis W. W. Shaw, Xing Song, Doris Leung, Seth D. Friedman
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-09516-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333300880998400
author Silvia S. Blemker
Lara Riem
Olivia DuCharme
Megan Pinette
Kathryn Eve Costanzo
Emma Weatherley
Jeff Statland
Stephen J. Tapscott
Leo H. Wang
Dennis W. W. Shaw
Xing Song
Doris Leung
Seth D. Friedman
author_facet Silvia S. Blemker
Lara Riem
Olivia DuCharme
Megan Pinette
Kathryn Eve Costanzo
Emma Weatherley
Jeff Statland
Stephen J. Tapscott
Leo H. Wang
Dennis W. W. Shaw
Xing Song
Doris Leung
Seth D. Friedman
author_sort Silvia S. Blemker
collection DOAJ
description Abstract Facioscapulohumeral muscular dystrophy (FSHD) is a genetic neuromuscular disorder characterized by progressive muscle degeneration with substantial variability in severity and progression patterns. FSHD is a highly heterogeneous disease; however, current clinical metrics used for tracking disease progression lack sensitivity for personalized assessment, which greatly limits the design and execution of clinical trials. This study introduces a multi-scale machine learning framework leveraging whole-body magnetic resonance imaging (MRI) and clinical data to predict regional, muscle, joint, and functional progression in FSHD. The goal this work is to create a ‘digital twin’ of individual FSHD patients that can be leveraged in clinical trials. Using a combined dataset of over 100 patients from seven studies, MRI-derived metrics—including fat fraction, lean muscle volume, and fat spatial heterogeneity at baseline—were integrated with clinical and functional measures. A three-stage random forest model was developed to predict annualized changes in muscle composition and a functional outcome (timed up-and-go (TUG)). All model stages revealed strong predictive performance in separate holdout datasets. After training, the models predicted fat fraction change with a root mean square error (RMSE) of 2.16% and lean volume change with a RMSE of 8.1 ml in a holdout testing dataset. Feature analysis revealed that metrics of fat heterogeneity within muscle predicts muscle-level progression. The stage 3 model, which combined functional muscle groups, predicted change in TUG with a RMSE of 0.6 s in the holdout testing dataset. This study demonstrates the machine learning models incorporating individual muscle and performance data can effectively predict MRI disease progression and functional performance of complex tasks, addressing the heterogeneity and nonlinearity inherent in FSHD. Further studies incorporating larger longitudinal cohorts, as well as comprehensive clinical and functional measures, will allow for expanding and refining this model. As many neuromuscular diseases are characterized by variability and heterogeneity similar to FSHD, such approaches have broad applicability.
format Article
id doaj-art-89917543fc324e15addf9782ac8b8a6e
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-89917543fc324e15addf9782ac8b8a6e2025-08-20T03:45:55ZengNature PortfolioScientific Reports2045-23222025-07-0115111410.1038/s41598-025-09516-8Multi-scale machine learning model predicts muscle and functional disease progressionSilvia S. Blemker0Lara Riem1Olivia DuCharme2Megan Pinette3Kathryn Eve Costanzo4Emma Weatherley5Jeff Statland6Stephen J. Tapscott7Leo H. Wang8Dennis W. W. Shaw9Xing Song10Doris Leung11Seth D. Friedman12Springbok AnalyticsSpringbok AnalyticsSpringbok AnalyticsSpringbok AnalyticsSpringbok AnalyticsFSHD Global Research FoundationUniversity of Kansas Medical CenterFred Hutchinson Cancer CenterUniversity of WashingtonUniversity of WashingtonUniversity of MissouriKennedy Krieger InstituteSeattle Children’s HospitalAbstract Facioscapulohumeral muscular dystrophy (FSHD) is a genetic neuromuscular disorder characterized by progressive muscle degeneration with substantial variability in severity and progression patterns. FSHD is a highly heterogeneous disease; however, current clinical metrics used for tracking disease progression lack sensitivity for personalized assessment, which greatly limits the design and execution of clinical trials. This study introduces a multi-scale machine learning framework leveraging whole-body magnetic resonance imaging (MRI) and clinical data to predict regional, muscle, joint, and functional progression in FSHD. The goal this work is to create a ‘digital twin’ of individual FSHD patients that can be leveraged in clinical trials. Using a combined dataset of over 100 patients from seven studies, MRI-derived metrics—including fat fraction, lean muscle volume, and fat spatial heterogeneity at baseline—were integrated with clinical and functional measures. A three-stage random forest model was developed to predict annualized changes in muscle composition and a functional outcome (timed up-and-go (TUG)). All model stages revealed strong predictive performance in separate holdout datasets. After training, the models predicted fat fraction change with a root mean square error (RMSE) of 2.16% and lean volume change with a RMSE of 8.1 ml in a holdout testing dataset. Feature analysis revealed that metrics of fat heterogeneity within muscle predicts muscle-level progression. The stage 3 model, which combined functional muscle groups, predicted change in TUG with a RMSE of 0.6 s in the holdout testing dataset. This study demonstrates the machine learning models incorporating individual muscle and performance data can effectively predict MRI disease progression and functional performance of complex tasks, addressing the heterogeneity and nonlinearity inherent in FSHD. Further studies incorporating larger longitudinal cohorts, as well as comprehensive clinical and functional measures, will allow for expanding and refining this model. As many neuromuscular diseases are characterized by variability and heterogeneity similar to FSHD, such approaches have broad applicability.https://doi.org/10.1038/s41598-025-09516-8
spellingShingle Silvia S. Blemker
Lara Riem
Olivia DuCharme
Megan Pinette
Kathryn Eve Costanzo
Emma Weatherley
Jeff Statland
Stephen J. Tapscott
Leo H. Wang
Dennis W. W. Shaw
Xing Song
Doris Leung
Seth D. Friedman
Multi-scale machine learning model predicts muscle and functional disease progression
Scientific Reports
title Multi-scale machine learning model predicts muscle and functional disease progression
title_full Multi-scale machine learning model predicts muscle and functional disease progression
title_fullStr Multi-scale machine learning model predicts muscle and functional disease progression
title_full_unstemmed Multi-scale machine learning model predicts muscle and functional disease progression
title_short Multi-scale machine learning model predicts muscle and functional disease progression
title_sort multi scale machine learning model predicts muscle and functional disease progression
url https://doi.org/10.1038/s41598-025-09516-8
work_keys_str_mv AT silviasblemker multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT larariem multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT oliviaducharme multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT meganpinette multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT kathrynevecostanzo multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT emmaweatherley multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT jeffstatland multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT stephenjtapscott multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT leohwang multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT denniswwshaw multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT xingsong multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT dorisleung multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression
AT sethdfriedman multiscalemachinelearningmodelpredictsmuscleandfunctionaldiseaseprogression