{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T17:51:08Z","timestamp":1775929868469,"version":"3.50.1"},"posted":{"date-parts":[[2025,2,20]]},"group-title":"Bioengineering","reference-count":52,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,2,20]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>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 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 \u2018digital twin\u2019 of individual FSHD patients that can be leveraged in clinical trials.<\/jats:p>\n                <jats:p>Using a combined dataset of over 100 patients from seven studies, MRI-derived metrics\u2014including fat fraction, lean muscle volume, and fat spatial heterogeneity at baseline\u2014were 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 8.1ml in a holdout testing dataset. Feature analysis revealed that metrics fat heterogeneity within muscle predicts muscle-level progression. The stage 3 model that combined functional muscle groups and predicted change in TUG with a RMSE of 0.6 seconds, 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 varability and heterogeneity similar to FSHD, such approaches have broad applicability.<\/jats:p>","DOI":"10.1101\/2025.02.19.639046","type":"posted-content","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T10:50:22Z","timestamp":1740048622000},"source":"Crossref","is-referenced-by-count":3,"title":["Multi-scale machine learning model predicts muscle and functional disease progression in FSHD"],"prefix":"10.64898","author":[{"given":"Silvia S.","family":"Blemker","sequence":"first","affiliation":[{"name":"Springbok Analytics, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lara","family":"Riem","sequence":"additional","affiliation":[{"name":"Springbok Analytics, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivia","family":"DuCharme","sequence":"additional","affiliation":[{"name":"Springbok Analytics, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Megan","family":"Pinette","sequence":"additional","affiliation":[{"name":"Springbok Analytics, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kathryn Eve","family":"Costanzo","sequence":"additional","affiliation":[{"name":"Springbok Analytics, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emma","family":"Weatherley","sequence":"additional","affiliation":[{"name":"FSHD Global Research Foundation, Sydney, AU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0790-5315","authenticated-orcid":false,"given":"Jeff","family":"Statland","sequence":"additional","affiliation":[{"name":"University of Kansas Medical Center, Kansas City, KS USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0319-0968","authenticated-orcid":false,"given":"Stephen J.","family":"Tapscott","sequence":"additional","affiliation":[{"name":"Fred Hutchinson Cancer Center, Seattle, WA USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leo H.","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis W.W.","family":"Shaw","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA USA"},{"name":"Seattle Children\u2019s Hospital, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"The Move+ Investigator Team","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Song","sequence":"additional","affiliation":[{"name":"University of Missouri, Columbia, MO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2558-7798","authenticated-orcid":false,"given":"Doris","family":"Leung","sequence":"additional","affiliation":[{"name":"Kennedy Krieger Institute, Baltimore, MD USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seth","family":"Friedman","sequence":"additional","affiliation":[{"name":"Seattle Children\u2019s Hospital, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026041110350410000_2025.02.19.639046v1.1","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/7020295"},{"key":"2026041110350410000_2025.02.19.639046v1.2","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-016-8361-3"},{"key":"2026041110350410000_2025.02.19.639046v1.3","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-019-09242-y"},{"key":"2026041110350410000_2025.02.19.639046v1.4","first-page":"e1211","article-title":"Evaluation of inflammatory lesions over 2 years in facioscapulohumeral muscular dystrophy","volume":"95","year":"2020","journal-title":"Neurology"},{"key":"2026041110350410000_2025.02.19.639046v1.5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0183825"},{"key":"2026041110350410000_2025.02.19.639046v1.6","doi-asserted-by":"publisher","DOI":"10.1002\/mus.26038"},{"key":"2026041110350410000_2025.02.19.639046v1.7","doi-asserted-by":"publisher","DOI":"10.1002\/mus.23911"},{"key":"2026041110350410000_2025.02.19.639046v1.8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0085416"},{"key":"2026041110350410000_2025.02.19.639046v1.9","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.12473"},{"key":"2026041110350410000_2025.02.19.639046v1.10","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-021-04134-7"},{"key":"2026041110350410000_2025.02.19.639046v1.11","doi-asserted-by":"publisher","DOI":"10.1002\/mus.24287"},{"key":"2026041110350410000_2025.02.19.639046v1.12","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-006-0230-z"},{"key":"2026041110350410000_2025.02.19.639046v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.nmd.2009.02.009"},{"key":"2026041110350410000_2025.02.19.639046v1.14","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.1494"},{"key":"2026041110350410000_2025.02.19.639046v1.15","doi-asserted-by":"publisher","DOI":"10.1002\/mus.22342"},{"key":"2026041110350410000_2025.02.19.639046v1.16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0038779"},{"key":"2026041110350410000_2025.02.19.639046v1.17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0132717"},{"key":"2026041110350410000_2025.02.19.639046v1.18","doi-asserted-by":"publisher","DOI":"10.1002\/mus.24569"},{"key":"2026041110350410000_2025.02.19.639046v1.19","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-018-9037-y"},{"key":"2026041110350410000_2025.02.19.639046v1.20","doi-asserted-by":"publisher","DOI":"10.1093\/hmg\/ddy364"},{"key":"2026041110350410000_2025.02.19.639046v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-022-00217-1"},{"key":"2026041110350410000_2025.02.19.639046v1.22","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000201287"},{"key":"2026041110350410000_2025.02.19.639046v1.23","doi-asserted-by":"crossref","unstructured":"Widholm, P. , et al. Quantitative muscle analysis in facioscapulohumeral muscular dystrophy using whole-body fat-referenced MRI: Protocol development, multicenter feasibility, and repeatability. Muscle Nerve (2022).","DOI":"10.1002\/mus.27638"},{"key":"2026041110350410000_2025.02.19.639046v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-65802-x"},{"key":"2026041110350410000_2025.02.19.639046v1.25","first-page":"e2103","article-title":"Natural History of Facioscapulohumeral Dystrophy in Children: A 2-Year Follow-up","volume":"97","year":"2021","journal-title":"Neurology"},{"key":"2026041110350410000_2025.02.19.639046v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.nmd.2022.11.006"},{"key":"2026041110350410000_2025.02.19.639046v1.27","doi-asserted-by":"publisher","DOI":"10.1002\/ana.24599"},{"key":"2026041110350410000_2025.02.19.639046v1.28","doi-asserted-by":"crossref","unstructured":"Sampson, J.H. , et al. MDNA55 survival in recurrent glioblastoma (rGBM) patients expressing the interleukin-4 receptor (IL4R) as compared to a matched synthetic control. J Clin Oncol 38(2020).","DOI":"10.1200\/JCO.2020.38.15_suppl.2513"},{"key":"2026041110350410000_2025.02.19.639046v1.29","doi-asserted-by":"publisher","DOI":"10.1002\/acn3.51140"},{"key":"2026041110350410000_2025.02.19.639046v1.30","doi-asserted-by":"publisher","DOI":"10.1080\/17460441.2023.2273839"},{"key":"2026041110350410000_2025.02.19.639046v1.31","doi-asserted-by":"crossref","unstructured":"Wong, C.J. , et al. Regional and bilateral MRI and gene signatures in facioscapulohumeral dystrophy: implications for clinical trial design and mechanisms of disease progression. Hum Mol Genet (2024).","DOI":"10.1093\/hmg\/ddae007"},{"key":"2026041110350410000_2025.02.19.639046v1.32","first-page":"044009","article-title":"Automatic segmentation of all lower limb muscles from high-resolution magnetic resonance imaging using a cascaded three-dimensional deep convolutional neural network","volume":"6","year":"2019","journal-title":"J Med Imaging (Bellingham)"},{"key":"2026041110350410000_2025.02.19.639046v1.33","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-015-1488-z"},{"key":"2026041110350410000_2025.02.19.639046v1.34","doi-asserted-by":"crossref","unstructured":"Chang, R. , et al. Percentage fat fraction in magnetic resonance imaging: upgrading the osteoporosis-detecting parameter. BMC Med Imaging 20, 30 (2020).","DOI":"10.1186\/s12880-020-00423-0"},{"key":"2026041110350410000_2025.02.19.639046v1.35","doi-asserted-by":"publisher","DOI":"10.3109\/21678421.2014.893361"},{"key":"2026041110350410000_2025.02.19.639046v1.36","doi-asserted-by":"crossref","unstructured":"Ko, K.D. , El-Ghazawi, T. , Kim, D. , Morizono, H. & Pooled Resource Open-Access, A.L.S.C.T.C. Predicting the severity of motor neuron disease progression using electronic health record data with a cloud computing Big Data approach. IEEE Symp Comput Intell Bioinforma Comput Biol Proc 2014(2014).","DOI":"10.1109\/CIBCB.2014.6845506"},{"key":"2026041110350410000_2025.02.19.639046v1.37","unstructured":"Lundberg, S.M. & Lee, S.I . A Unified Approach to Interpreting Model Predictions. Adv Neur In 30 (2017)."},{"key":"2026041110350410000_2025.02.19.639046v1.38","doi-asserted-by":"publisher","DOI":"10.1111\/cts.70056"},{"key":"2026041110350410000_2025.02.19.639046v1.39","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2023.1105276"},{"key":"2026041110350410000_2025.02.19.639046v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurol.2016.08.002"},{"key":"2026041110350410000_2025.02.19.639046v1.41","doi-asserted-by":"publisher","DOI":"10.1212\/01.wnl.0000504577.93225.eb"},{"key":"2026041110350410000_2025.02.19.639046v1.42","doi-asserted-by":"crossref","unstructured":"Fionda, L. , et al. Comparison of quantitative muscle ultrasound and whole-body muscle MRI in facioscapulohumeral muscular dystrophy type 1 patients. Neurol Sci (2023).","DOI":"10.1007\/s10072-023-06842-5"},{"key":"2026041110350410000_2025.02.19.639046v1.43","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000004647"},{"key":"2026041110350410000_2025.02.19.639046v1.44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0100292"},{"key":"2026041110350410000_2025.02.19.639046v1.45","doi-asserted-by":"publisher","DOI":"10.1002\/jcsm.13250"},{"key":"2026041110350410000_2025.02.19.639046v1.46","doi-asserted-by":"publisher","DOI":"10.1093\/hmg\/ddae007"},{"key":"2026041110350410000_2025.02.19.639046v1.47","doi-asserted-by":"publisher","DOI":"10.1093\/hmg\/ddaa031"},{"key":"2026041110350410000_2025.02.19.639046v1.48","doi-asserted-by":"publisher","DOI":"10.1007\/s10875-010-9474-6"},{"key":"2026041110350410000_2025.02.19.639046v1.49","doi-asserted-by":"publisher","DOI":"10.3233\/JND-230063"},{"key":"2026041110350410000_2025.02.19.639046v1.50","doi-asserted-by":"publisher","DOI":"10.1007\/s12035-017-0563-x"},{"key":"2026041110350410000_2025.02.19.639046v1.51","doi-asserted-by":"crossref","unstructured":"Wang, L.H. , Johnstone, L.M. , Bindschadler, M. , Tapscott, S.J. & Friedman, S.D . Adapting MRI as a clinical outcome measure for a facioscapulohumeral muscular dystrophy trial of prednisone and tacrolimus: case report. BMC Musculoskelet Disord 22, 56 (2021).","DOI":"10.1186\/s12891-020-03910-1"},{"key":"2026041110350410000_2025.02.19.639046v1.52","doi-asserted-by":"publisher","DOI":"10.1186\/s12968-021-00812-6"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.02.19.639046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T17:35:15Z","timestamp":1775928915000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.02.19.639046"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,20]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1101\/2025.02.19.639046","relation":{},"subject":[],"published":{"date-parts":[[2025,2,20]]},"subtype":"preprint"}}