{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T15:16:20Z","timestamp":1787670980070,"version":"build-2736575974"},"reference-count":27,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:00:00Z","timestamp":1778889600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["RS-2024-00337352"],"award-info":[{"award-number":["RS-2024-00337352"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"award":["RS-2024-00337352"],"award-info":[{"award-number":["RS-2024-00337352"]}],"id":[{"id":"https:\/\/ror.org\/013aysd81","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/Objectives: Recovery of upper limb function after stroke is highly heterogeneous, and accurate prediction of clinically meaningful functional transition remains a major challenge in rehabilitation medicine. We developed and temporally validated machine learning (ML)-based prognostic models for predicting transition from non-functional movement to functionally usable upper limb capacity in patients undergoing intensive inpatient rehabilitation during the early subacute phase of stroke. Methods: This retrospective cohort study included 960 patients with ischemic or hemorrhagic stroke admitted to a tertiary rehabilitation center between 2010 and 2025. Three functional recovery outcomes were defined: motor impairment recovery, defined as Fugl-Meyer Assessment for Upper Extremity score \u2265 32; gross manual dexterity recovery, defined as Box and Block Test score \u2265 2 blocks\/min; and functional pinch strength recovery, defined as pinch strength \u2265 1.1 kgf. Multidimensional predictors spanning demographic, clinical, neurophysiological, neuroimaging, and rehabilitation-related domains were integrated. Four ML algorithms were evaluated using stratified 5-fold cross-validation and temporal validation in a chronologically independent cohort (2024\u20132025). Models were developed under two tracks: Track A, incorporating only baseline variables available at admission (primary prognostic model), and Track B, additionally incorporating cumulative rehabilitation-related variables (exploratory). Results: Random Forest demonstrated the best overall performance. During temporal validation, models achieved AUROC of 0.800 for motor impairment recovery, 0.958 for gross manual dexterity recovery, and 0.888 for functional strength recovery. Baseline motor severity and corticospinal tract integrity were the dominant biological determinants of recovery. Earlier rehabilitation initiation and greater upper-limb robot-assisted therapy exposure were also associated with improved outcomes; however, these findings should be interpreted as observational associations subject to treatment-selection bias rather than evidence of causal effects. Conclusions: Probabilistic ML prediction integrating neural reserve and rehabilitation-related exposure variables can support individualized precision rehabilitation planning and improve functional outcome stratification in early subacute stroke.<\/jats:p>","DOI":"10.3390\/jcm15103851","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T12:36:40Z","timestamp":1779107800000},"page":"3851","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Machine Learning-Based Prediction of Transition to Functional Upper Limb Recovery After Intensive Inpatient Rehabilitation in Early Subacute Stroke"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4272-7489","authenticated-orcid":false,"given":"Jong-Mi","family":"Park","sequence":"first","affiliation":[{"name":"Department and Research Institute of Rehabilitation Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6241-7392","authenticated-orcid":false,"given":"Sang-Chul","family":"Lee","sequence":"additional","affiliation":[{"name":"Department and Research Institute of Rehabilitation Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5234-2454","authenticated-orcid":false,"given":"Yong-Wook","family":"Kim","sequence":"additional","affiliation":[{"name":"Department and Research Institute of Rehabilitation Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea"},{"name":"Yonsei Institute for Digital Health, Yonsei University, Seoul 03722, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seo-Yeon","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department and Research Institute of Rehabilitation Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea"},{"name":"Yonsei Institute for Digital Health, Yonsei University, Seoul 03722, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1002\/ana.24510","article-title":"Corticospinal tract lesion load: An imaging biomarker for stroke motor outcomes","volume":"78","author":"Feng","year":"2015","journal-title":"Ann. Neurol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1111\/ene.14494","article-title":"Differential early predictive factors for upper and lower extremity motor recovery after ischaemic stroke","volume":"28","author":"Lee","year":"2021","journal-title":"Eur. J. Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1177\/154596802401105171","article-title":"The fugl-meyer assessment of motor recovery after stroke: A critical review of its measurement properties","volume":"16","author":"Gladstone","year":"2002","journal-title":"Neurorehabil. Neural Repair."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.1016\/j.apmr.2015.06.009","article-title":"How do fugl-meyer arm motor scores relate to dexterity according to the action research arm test at 6 months poststroke?","volume":"96","author":"Hoonhorst","year":"2015","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1177\/1545968314523678","article-title":"Two common tests of dexterity can stratify upper limb motor function after stroke","volume":"28","author":"Lin","year":"2014","journal-title":"Neurorehabil. Neural Repair."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2527","DOI":"10.1093\/brain\/aws146","article-title":"The prep algorithm predicts potential for upper limb recovery after stroke","volume":"135","author":"Stinear","year":"2012","journal-title":"Brain"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1002\/acn3.488","article-title":"Prep2: A biomarker-based algorithm for predicting upper limb function after stroke","volume":"4","author":"Stinear","year":"2017","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1161\/01.STR.0000087172.16305.CD","article-title":"Probability of regaining dexterity in the flaccid upper limb: Impact of severity of paresis and time since onset in acute stroke","volume":"34","author":"Kwakkel","year":"2003","journal-title":"Stroke"},{"key":"ref_9","first-page":"1805","article-title":"Moving beyond regression techniques in cardiovascular risk prediction: Applying machine learning to address analytic challenges","volume":"38","author":"Goldstein","year":"2017","journal-title":"Eur. Heart J."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Miyazaki, Y., Kawakami, M., Kondo, K., Tsujikawa, M., Honaga, K., Suzuki, K., and Tsuji, T. (2023). Improvement of predictive accuracies of functional outcomes after subacute stroke inpatient rehabilitation by machine learning models. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0286269"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Park, D., Jeong, E., Kim, H., Pyun, H.W., Kim, H., Choi, Y.J., Kim, Y., Jin, S., Hong, D., and Lee, D.W. (2021). Machine learning-based three-month outcome prediction in acute ischemic stroke: A single cerebrovascular-specialty hospital study in south korea. Diagnostics, 11.","DOI":"10.3390\/diagnostics11101909"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1682\/JRRD.2004.02.0215","article-title":"Identification of key pinch forces required to complete functional tasks","volume":"41","author":"Smaby","year":"2004","journal-title":"J. Rehabil. Res. Dev."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1093\/brain\/120.1.141","article-title":"Localization of the motor hand area to a knob on the precentral gyrus. A new landmark","volume":"120","author":"Yousry","year":"1997","journal-title":"Brain"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1212\/WNL.0b013e3181ccc6d9","article-title":"Structural integrity of corticospinal motor fibers predicts motor impairment in chronic stroke","volume":"74","author":"Lindenberg","year":"2010","journal-title":"Neurology"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2116","DOI":"10.3174\/ajnr.A2660","article-title":"Anatomic location and somatotopic arrangement of the corticospinal tract at the cerebral peduncle in the human brain","volume":"32","author":"Kwon","year":"2011","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1016\/j.clinph.2012.01.010","article-title":"A practical guide to diagnostic transcranial magnetic stimulation: Report of an ifcn committee","volume":"123","author":"Groppa","year":"2012","journal-title":"Clin. Neurophysiol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1016\/j.clinph.2015.02.001","article-title":"Non-invasive electrical and magnetic stimulation of the brain, spinal cord, roots and peripheral nerves: Basic principles and procedures for routine clinical and research application. An updated report from an i.F.C.N. Committee","volume":"126","author":"Rossini","year":"2015","journal-title":"Clin. Neurophysiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1146\/annurev.neuro.31.060407.125547","article-title":"Descending pathways in motor control","volume":"31","author":"Lemon","year":"2008","journal-title":"Annu. Rev. Neurosci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s00234-017-1816-0","article-title":"Diffusion tensor imaging as a prognostic biomarker for motor recovery and rehabilitation after stroke","volume":"59","author":"Puig","year":"2017","journal-title":"Neuroradiology"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1177\/1545968308317578","article-title":"Predicting hand motor recovery in severe stroke: The role of motor evoked potentials in relation to early clinical assessment","volume":"23","author":"Pasman","year":"2009","journal-title":"Neurorehabil. Neural Repair."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1924","DOI":"10.1212\/WNL.0000000000002675","article-title":"Predicting motor improvement after stroke with clinical assessment and diffusion tensor imaging","volume":"86","author":"Buch","year":"2016","journal-title":"Neurology"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"S225","DOI":"10.1044\/1092-4388(2008\/018)","article-title":"Principles of experience-dependent neural plasticity: Implications for rehabilitation after brain damage","volume":"51","author":"Kleim","year":"2008","journal-title":"J. Speech Lang. Hear. Res."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Nudo, R.J. (2013). Recovery after brain injury: Mechanisms and principles. Front. Hum. Neurosci., 7.","DOI":"10.3389\/fnhum.2013.00887"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5603","DOI":"10.1113\/jphysiol.2011.215160","article-title":"The primate reticulospinal tract, hand function and functional recovery","volume":"589","author":"Baker","year":"2011","journal-title":"J. Physiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1002\/ana.10848","article-title":"Influence of interhemispheric interactions on motor function in chronic stroke","volume":"55","author":"Murase","year":"2004","journal-title":"Ann. Neurol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1038\/nrneurol.2014.162","article-title":"Modulation of brain plasticity in stroke: A novel model for neurorehabilitation","volume":"10","author":"Pellegrino","year":"2014","journal-title":"Nat. Rev. Neurol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/j.clinph.2019.11.002","article-title":"Evidence-based guidelines on the therapeutic use of repetitive transcranial magnetic stimulation (rtms): An update (2014\u20132018)","volume":"131","author":"Lefaucheur","year":"2020","journal-title":"Clin. Neurophysiol."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/10\/3851\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T04:29:06Z","timestamp":1779164946000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/10\/3851"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,16]]},"references-count":27,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["jcm15103851"],"URL":"https:\/\/doi.org\/10.3390\/jcm15103851","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,16]]}}}