{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T17:12:14Z","timestamp":1788369134806,"version":"build-2803163510"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Rehabil. Sci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Spinal cord injury (SCI) presents a significant burden to patients, families, and the healthcare system. The ability to accurately predict functional outcomes for SCI patients is essential for optimizing rehabilitation strategies, guiding patient and family decision making, and improving patient care.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We conducted a retrospective analysis of 589 SCI patients admitted to a single acute rehabilitation facility and used the dataset to train advanced machine learning algorithms to predict patients' rehabilitation outcomes. The primary outcome was the Functional Independence Measure (FIM) score at discharge, reflecting the level of independence achieved by patients after comprehensive inpatient rehabilitation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Tree-based algorithms, particularly Random Forest (RF) and XGBoost, significantly outperformed traditional statistical models and Generalized Linear Models (GLMs) in predicting discharge FIM scores. The RF model exhibited the highest predictive accuracy, with an R-squared value of 0.90 and a Mean Squared Error (MSE) of 0.29 on the training dataset, while achieving 0.52 R-squared and 1.37 MSE on the test dataset. The XGBoost model also demonstrated strong performance, with an R-squared value of 0.74 and an MSE of 0.75 on the training dataset, and 0.51 R-squared with 1.39 MSE on the test dataset. Our analysis identified key predictors of rehabilitation outcomes, including the initial FIM scores and specific demographic factors such as level of injury and prehospital living settings. The study also highlighted the superior ability of tree-based models to capture the complex, non-linear relationships between variables that impact recovery in SCI patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>This research underscores the potential of machine learning models to enhance the accuracy of outcome predictions in SCI rehabilitation. The findings support the integration of these advanced predictive tools in clinical settings to better guide decision making for patients and families, tailor rehabilitation plans, allocate resources efficiently, and ultimately improve patient outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fresc.2025.1594753","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T05:26:49Z","timestamp":1756099609000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Machine learning predicts improvement of functional outcomes in spinal cord injury patients after inpatient rehabilitation"],"prefix":"10.3389","volume":"6","author":[{"given":"Mohammad","family":"Rasoolinejad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irene","family":"Say","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter B.","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinran","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily R.","family":"Rosario","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel C.","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2236","DOI":"10.1001\/jama.2015.6250","article-title":"Traumatic spinal cord injury in the United States, 1993\u20132012","volume":"313","author":"Jain","year":"2015","journal-title":"JAMA"},{"key":"B2","doi-asserted-by":"publisher","first-page":"9","DOI":"10.20517\/2347-8659.2019.15","article-title":"Economic impact of traumatic spinal cord injuries in the United States","volume":"6","author":"Merritt","year":"2019","journal-title":"Neuroimmunol Neuroinflamm"},{"key":"B3","doi-asserted-by":"publisher","first-page":"463","DOI":"10.4102\/ajod.v8i0.463","article-title":"Associations between health behaviour, secondary health conditions and quality of life in people with spinal cord injury","volume":"8","author":"Mashola","year":"2019","journal-title":"Afr J Disabil"},{"key":"B4","doi-asserted-by":"publisher","first-page":"17018","DOI":"10.1038\/nrdp.2017.18","article-title":"Traumatic spinal cord injury","volume":"3","author":"Ahuja","year":"2017","journal-title":"Nat Rev Dis Primers"},{"key":"B5","doi-asserted-by":"publisher","first-page":"6938718","DOI":"10.1155\/2017\/6938718","article-title":"Pre- and postintervention factor structure of functional independence measure in patients with spinal cord injury","volume":"2017","author":"Saltychev","year":"2017","journal-title":"Rehabil Res Pract"},{"key":"B6","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1038\/sc.2013.179","article-title":"The experience of using the scale of functional independence measure in individuals undergoing spinal cord injury rehabilitation in Brazil","volume":"52","author":"Barbetta","year":"2014","journal-title":"Spinal Cord"},{"key":"B7","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1080\/10790268.2018.1504427","article-title":"Functional independence of persons with long-standing motor complete spinal cord injury in The Netherlands","volume":"43","author":"Osterthun","year":"2020","journal-title":"J Spinal Cord Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e38286","DOI":"10.1097\/MD.0000000000038286","article-title":"Prediction of gait recovery using machine learning algorithms in patients with spinal cord injury","volume":"103","author":"Yoo","year":"2024","journal-title":"Medicine (Baltimore)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.jocn.2022.11.003","article-title":"Efficacy of a machine learning-based approach in predicting neurological prognosis of cervical spinal cord injury patients following urgent surgery within 24\u2005h after injury","volume":"107","author":"Shimizu","year":"2023","journal-title":"J Clin Neurosci"},{"key":"B10","doi-asserted-by":"publisher","first-page":"737","DOI":"10.3174\/ajnr.A6020","article-title":"Convolutional neural network-based automated segmentation of the spinal cord and contusion injury: deep learning biomarker correlates of motor impairment in acute spinal cord injury","volume":"40","author":"McCoy","year":"2019","journal-title":"AJNR Am J Neuroradiol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1038\/s41393-023-00924-z","article-title":"Machine learning to develop a predictive model of pressure injury in persons with spinal cord injury","volume":"61","author":"Luther","year":"2023","journal-title":"Spinal Cord"},{"key":"B12","doi-asserted-by":"publisher","first-page":"ENEURO.0149-22.2022","DOI":"10.1523\/ENEURO.0149-22.2022","article-title":"Spinal cord injury AIS predictions using machine learning","volume":"10","author":"Kapoor","year":"2023","journal-title":"eNeuro"},{"key":"B13","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.wneu.2024.05.103","article-title":"Predicting the outcome and survival of patients with spinal cord injury using machine learning algorithms: a systematic review","volume":"188","author":"Habibi","year":"2024","journal-title":"World Neurosurg"},{"key":"B14","doi-asserted-by":"publisher","first-page":"E390","DOI":"10.1097\/BRS.0000000000004267","article-title":"Machine learning-based prediction of prolonged intensive care unit stay for critical patients with spinal cord injury","volume":"47","author":"Fan","year":"2022","journal-title":"Spine (Phila Pa 1976)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.spinee.2021.08.003","article-title":"Development of a machine learning algorithm for predicting in-hospital and 1-year mortality after traumatic spinal cord injury","volume":"22","author":"Fallah","year":"2022","journal-title":"Spine J"},{"key":"B16","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1038\/s41393-024-01008-2","article-title":"Predictive modeling of ambulatory outcomes after spinal cord injury using machine learning","volume":"62","author":"Draganich","year":"2024","journal-title":"Spinal Cord"},{"key":"B17","doi-asserted-by":"publisher","first-page":"102046","DOI":"10.1016\/j.jcot.2022.102046","article-title":"Machine learning in clinical diagnosis, prognostication, and management of acute traumatic spinal cord injury (SCI): a systematic review","volume":"35","author":"Dietz","year":"2022","journal-title":"J Clin Orthop Trauma"},{"key":"B18","doi-asserted-by":"publisher","first-page":"7691","DOI":"10.1038\/s41598-024-56711-0","article-title":"Prediction model for spinal cord injury in spinal tuberculosis patients using multiple machine learning algorithms: a multicentric study","volume":"14","author":"Feng","year":"2024","journal-title":"Sci Rep"},{"key":"B19","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.apmr.2023.08.011","article-title":"Functional outcome prediction after spinal cord injury using ensemble machine learning","volume":"105","author":"Kato","year":"2024","journal-title":"Arch Phys Med Rehabil"},{"key":"B20","doi-asserted-by":"publisher","first-page":"678","DOI":"10.14245\/ns.1938390.195","article-title":"Predictive modeling of outcomes after traumatic and nontraumatic spinal cord injury using machine learning: review of current progress and future directions","volume":"16","author":"Khan","year":"2019","journal-title":"Neurospine"},{"key":"B21","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.spinee.2019.09.007","article-title":"Development of an unsupervised machine learning algorithm for the prognostication of walking ability in spinal cord injury patients","volume":"20","author":"DeVries","year":"2020","journal-title":"Spine J"},{"key":"B22","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.jocn.2021.11.037","article-title":"Determining the short-term neurological prognosis for acute cervical spinal cord injury using machine learning","volume":"96","author":"Okimatsu","year":"2022","journal-title":"J Clin Neurosci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1089\/neur.2020.0009","article-title":"XGBoost, a machine learning method, predicts neurological recovery in patients with cervical spinal cord injury","volume":"1","author":"Inoue","year":"2020","journal-title":"Neurotrauma Rep"},{"key":"B24","doi-asserted-by":"publisher","first-page":"e41819","DOI":"10.2196\/41819","article-title":"A machine learning-based approach to predict prognosis and length of hospital stay in adults and children with traumatic brain injury: retrospective cohort study","volume":"24","author":"Fang","year":"2022","journal-title":"J Med Internet Res"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1005168","DOI":"10.3389\/fresc.2022.1005168","article-title":"Machine learning predicts improvement of functional outcomes in traumatic brain injury patients after inpatient rehabilitation","volume":"3","author":"Say","year":"2022","journal-title":"Front Rehabil Sci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1385013","DOI":"10.3389\/fneur.2024.1385013","article-title":"Explainable machine learning for predicting neurological outcome in hemorrhagic and ischemic stroke patients in critical care","volume":"15","author":"Wei","year":"2024","journal-title":"Front Neurol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s00586-025-08873-2","article-title":"A multimodal machine learning model integrating clinical and MRI data for predicting neurological outcomes following surgical treatment for cervical spinal cord injury","author":"Shimizu","year":"2025","journal-title":"Eur Spine J"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1089\/neu.2022.0383","article-title":"Machine learning web application for predicting functional outcomes in patients with traumatic spinal cord injury following inpatient rehabilitation","volume":"41","author":"Maki","year":"2024","journal-title":"J Neurotrauma"},{"key":"B29","doi-asserted-by":"publisher","first-page":"235","DOI":"10.4102\/sajp.v71i1.235","article-title":"Factors that influence functional ability in individuals with spinal cord injury: a cross-sectional, observational study","volume":"71","author":"Hastings","year":"2015","journal-title":"S Afr J Physiother"},{"key":"B30","first-page":"4768","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"B31","first-page":"340","article-title":"From explanations to feature selection: assessing SHAP values as feature selection mechanism","author":"Marc\u00edlio","year":"2020"},{"key":"B32","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1038\/sc.2011.31","article-title":"Recovery following ischemic myelopathies and traumatic spinal cord lesions","volume":"49","author":"Scivoletto","year":"2011","journal-title":"Spinal Cord"},{"key":"B33","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1589\/jpts.26.67","article-title":"Analysis of the factors influencing functional outcomes in patients with spinal cord injury","volume":"26","author":"Milicevic","year":"2014","journal-title":"J Phys Ther Sci"},{"key":"B34","doi-asserted-by":"publisher","first-page":"175S","DOI":"10.1177\/2192568217703084","article-title":"Type and timing of rehabilitation following acute and subacute spinal cord injury: a systematic review","volume":"7","author":"Burns","year":"2017","journal-title":"Global Spine J"},{"key":"B35","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1179\/2045772312Y.0000000058","article-title":"Relationship of physical therapy inpatient rehabilitation interventions and patient characteristics to outcomes following spinal cord injury: the SCIRehab project","volume":"35","author":"Teeter","year":"2012","journal-title":"J Spinal Cord Med"},{"key":"B36","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1179\/2045772312Y.0000000057","article-title":"Relationship of patient characteristics and rehabilitation services to outcomes following spinal cord injury: the SCIRehab project","volume":"35","author":"Whiteneck","year":"2012","journal-title":"J Spinal Cord Med"},{"key":"B37","author":"Morley","year":"2019","journal-title":"Analyses to Inform the Potential Use of Standardized Patient Assessment Data Elements in the Inpatient Rehabilitation Facility Prospective Payment System"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1471","DOI":"10.1016\/S0003-9993(99)90260-5","article-title":"Characteristics of the functional independence measure in traumatic spinal cord injury","volume":"80","author":"Hall","year":"1999","journal-title":"Arch Phys Med Rehabil"},{"key":"B39","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/0003-9993(93)90119-U","article-title":"A validation of the functional independence measurement and its performance among rehabilitation inpatients","volume":"74","author":"Dodds","year":"1993","journal-title":"Arch Phys Med Rehabil"},{"key":"B40","doi-asserted-by":"publisher","first-page":"838","DOI":"10.3906\/sag-1809-7","article-title":"Early term effects of robotic assisted gait training on ambulation and functional capacity in patients with spinal cord injury","volume":"49","author":"Yildirim","year":"2019","journal-title":"Turk J Med Sci"},{"key":"B41","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41393-023-00892-4","article-title":"Efficacy of aquatic therapy in people with spinal cord injury: a systematic review and meta-analysis","volume":"61","author":"Palladino","year":"2023","journal-title":"Spinal Cord"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.1016\/j.jamda.2022.02.003","article-title":"Characterizing standardized functional data at inpatient rehabilitation facilities","volume":"23","author":"Li","year":"2022","journal-title":"J Am Med Dir Assoc"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.1016\/j.apmr.2023.07.009","article-title":"Concurrent validation of the inpatient rehabilitation facility patient assessment instrument version 1.4; sections GG, B, and C","volume":"104","author":"Harmon","year":"2023","journal-title":"Arch Phys Med Rehabil"}],"container-title":["Frontiers in Rehabilitation Sciences"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fresc.2025.1594753\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T05:26:50Z","timestamp":1756099610000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fresc.2025.1594753\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":43,"alternative-id":["10.3389\/fresc.2025.1594753"],"URL":"https:\/\/doi.org\/10.3389\/fresc.2025.1594753","relation":{},"ISSN":["2673-6861"],"issn-type":[{"value":"2673-6861","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,25]]},"article-number":"1594753"}}