{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:57Z","timestamp":1785545037352,"version":"3.56.0"},"reference-count":35,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Res Protoc"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Spinal cord injury (SCI) causes substantial disability by disrupting spinal pathways, making functional independence a central rehabilitation goal. In 2024, approximately 15.4 million people worldwide were living with SCI. Despite its clinical relevance, traditional prognostic tools, notably the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI), have limitations. Furthermore, access to advanced diagnostics constrains prediction. Existing models often fail to estimate independence, limiting goal setting and resource planning.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop and validate machine learning (ML)\u2013based rules that predict functional independence, as measured by the Spinal Cord Independence Measure, version III (SCIM-III), at 3, 6, and 12 months post injury in individuals with SCI. The model combines clinical admission predictors, readily available to enhance predictive performance: age, sex, time since injury, upper and lower extremity strength, ISNCSCI data (American Spinal Injury Association Impairment Scale grade and neurologic level of injury), rehabilitation type, and the Trunk Control Scale score validated by the research team.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Using retrospective electronic clinical records (2015\u20102026) from Mexico\u2019s Nacional de Rehabilitaci\u00f3n Luis Guillermo Ibarra Ibarra (INR LGII; a tertiary national rehabilitation reference center) for model development and a prospective independent cohort (October 2026-October 2027) for external validation, the study will develop ML models to accurately and generally predict SCIM-III outcomes. Eligible participants are adults (\u226518 years of age) with subacute or chronic SCI. Six architectures are compared: linear regression, classification and regression tree, categorical boosting (gradient boosting algorithm), light gradient boosting machine, multilayer perceptron, and Gaussian process regression, using 10-fold stratified cross-validation for internal validation. Performance is assessed by root-mean-square error, mean absolute error,\n R<\/jats:italic>\n \u00b2, area under the curve, calibration plots, and decision curve analysis. The approach prioritizes reproducibility, interpretability, and clinical applicability, addressing prior models\u2019 limitations (small sample sizes, limited validation, and impractical input requirements). Key steps include data preprocessing, feature selection, model training with appropriate algorithms, and robust evaluation against existing prognostic benchmarks. External validation and ethical considerations are integrated, with commitments to data sharing where feasible.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The study was approved and funded in October 2025. The retrospective development cohort targets 500 registries (from 2025\u20102026) collected between October 2025 and June 2026. A total of 119 records were processed by March 2026. ML development is planned between June 2026 and March 2027. The external prospective validation cohort (n=100) is planned for October 2026-October 2027, and validation for June 2027-March 2028. Results are expected by January 2028.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n A reliable, clinically actionable ML-based prediction tool that estimates SCIM-III trajectories to support goal setting, rehabilitation planning, and resource allocation in SCI care will be developed. Model performance will be benchmarked against published SCI prediction rules, and it will be considered clinically useful if it outperforms the mean-score baseline and existing rules on the prospective validation cohort.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/95236","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T08:45:05Z","timestamp":1778229905000},"page":"e95236-e95236","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning\u2013Based Predictive Model for Functional Independence in Spinal Cord Injury: Protocol for a Predictive Rule Development and Validation Study"],"prefix":"10.2196","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0550-928X","authenticated-orcid":false,"given":"Alberto Isaac","family":"Perez-Sanpablo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3234-4815","authenticated-orcid":false,"given":"Marlene Alejandra","family":"Rodriguez-Barragan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4042-6244","authenticated-orcid":false,"given":"Alicia","family":"Meneses-Pe\u00f1aloza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2780-6878","authenticated-orcid":false,"given":"Jimena","family":"Quinza\u00f1os-Fresnedo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4094-1748","authenticated-orcid":false,"given":"Aida","family":"Barrera-Ortiz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5724-8362","authenticated-orcid":false,"given":"Fabiola Monserrat","family":"Palomino-Ramos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6512-679X","authenticated-orcid":false,"given":"Oscar","family":"Prado-Escobar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6943-7812","authenticated-orcid":false,"given":"Marcela D","family":"Rodr\u00edguez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3979-9465","authenticated-orcid":false,"given":"Irvin Hussein","family":"Lopez-Nava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7326-3440","authenticated-orcid":false,"given":"Jose","family":"Ambrosio-Bastian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"issue":"4","key":"R1","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1177\/0269215509103551","article-title":"Goal setting in rehabilitation: an overview of what, why and how","volume":"23","author":"Wade","journal-title":"Clin Rehabil"},{"issue":"9","key":"R2","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1038\/s41393-020-0485-8","article-title":"Experiences with and perspectives on goal setting in spinal cord injury rehabilitation: a systematic review of qualitative studies","volume":"58","author":"Maribo","journal-title":"Spinal Cord"},{"issue":"9","key":"R3","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1089\/neu.2020.7473","article-title":"Characterizing natural recovery after traumatic spinal cord Injury","volume":"38","author":"Kirshblum","journal-title":"J Neurotrauma"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","first-page":"45","DOI":"10.46292\/sci23-00069","article-title":"Are clinical prediction rules used in spinal cord injury care? A survey of practice","volume":"30","author":"Boyles","journal-title":"Top Spinal Cord Inj Rehabil"},{"issue":"Suppl1","key":"R5","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3171\/2012.4.AOSPINE1245","article-title":"Clinical predictors of neurological outcome, functional status, and survival after traumatic spinal cord injury: a systematic review","volume":"17","author":"Wilson","journal-title":"SPI"},{"issue":"10","key":"R6","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1016\/j.spinee.2017.05.031","article-title":"A simplified clinical prediction rule for prognosticating independent walking after spinal cord injury","volume":"17","author":"Hicks","journal-title":"Spine J"},{"issue":"9770","key":"R7","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1016\/S0140-6736(10)62276-3","article-title":"A clinical prediction rule for ambulation outcomes after traumatic spinal cord injury: a longitudinal cohort study","volume":"377","author":"van Middendorp","journal-title":"Lancet"},{"issue":"2","key":"R8","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.spinee.2021.08.010","article-title":"Development of a clinical prediction rule for patients with cervical spinal cord injury who have difficulty in obtaining independent living","volume":"22","author":"Hori","journal-title":"Spine J"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1093\/jamia\/ocae255","article-title":"Machine learning-based prediction models in medical decision-making in kidney disease: patient, caregiver, and clinician perspectives on trust and appropriate use","volume":"32","author":"Sperling","journal-title":"J Am Med Inform Assoc"},{"issue":"6","key":"R10","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13061782","article-title":"Special issue-spinal cord injuries: advances in rehabilitation","volume":"13","author":"Arora","journal-title":"J Clin Med"},{"issue":"2","key":"R11","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s12028-023-01845-8","article-title":"Guidelines for neuroprognostication in adults with traumatic spinal cord injury","volume":"40","author":"Mahanes","journal-title":"Neurocrit Care"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2014.00141","article-title":"Who is going to walk? A review of the factors influencing walking recovery after spinal cord injury","volume":"8","author":"Scivoletto","journal-title":"Front Hum Neurosci"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1080\/10790268.2018.1518124","article-title":"Prognostic validity of a clinical trunk control test for independence and walking in individuals with spinal cord injury","volume":"43","author":"Quinza\u00f1os-Fresnedo","journal-title":"J Spinal Cord Med"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.expneurol.2024.114913","article-title":"Data-driven prediction of spinal cord injury recovery: an exploration of current status and future perspectives","volume":"380","author":"H\u00e5kansson","journal-title":"Exp Neurol"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2020.05.043","article-title":"Outcome prediction in spinal cord injury: myth or reality","volume":"140","author":"Sharif","journal-title":"World Neurosurg"},{"issue":"24","key":"R16","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.1080\/09638280601055052","article-title":"A multicenter international study on the Spinal Cord Independence Measure, version III (SCIM III)","volume":"29","author":"Catz","journal-title":"Disabil Rehabil"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Rasmussen CE Williams CKI . Gaussian Processes for Machine Learning. MIT Press; 2006. [doi: 10.7551\/mitpress\/3206.001.0001]","DOI":"10.7551\/mitpress\/3206.001.0001"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1080\/10790268.2021.1975083","article-title":"Validation of inertial measurement units for the assessment of trunk control in subjects with spinal cord injury","volume":"46","author":"P\u00e9rez-Sanpablo","journal-title":"J Spinal Cord Med"},{"issue":"3","key":"R19","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1080\/10790268.2016.1238184","article-title":"Predictors of functional outcomes in adults with traumatic spinal cord injury following inpatient rehabilitation: a systematic review","volume":"40","author":"AlHuthaifi","journal-title":"J Spinal Cord Med"},{"key":"R20","unstructured":"Instituto Nacional de Rehabilitaci\u00f3n luis guillermo ibarra ibarra informe de autoevaluaci\u00f3n 2024. Instituto Nacional de Rehabilitaci\u00f3n. 2024. URL: https:\/\/www.inr.gob.mx\/Descargas\/informes\/Informe_Autoevaluacion_2024.pdf [Accessed 03-11-2026]"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2025.111675","article-title":"Larger sample sizes are needed when developing a clinical prediction model using machine learning in oncology: methodological systematic review","volume":"180","author":"Tsegaye","journal-title":"J Clin Epidemiol"},{"issue":"8","key":"R22","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1177\/0962280218784726","article-title":"Sample size for binary logistic prediction models: beyond events per variable criteria","volume":"28","author":"van Smeden","journal-title":"Stat Methods Med Res"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"van der Ploeg","journal-title":"BMC Med Res Methodol"},{"issue":"7","key":"R24","doi-asserted-by":"publisher","first-page":"1262","DOI":"10.1002\/sim.7993","article-title":"Minimum sample size for developing a multivariable prediction model: part I - continuous outcomes","volume":"38","author":"Riley","journal-title":"Stat Med"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines11030685","article-title":"Sample size analysis for machine learning clinical validation studies","volume":"11","author":"Goldenholz","journal-title":"Biomedicines"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241248920","article-title":"Dataset size versus homogeneity: a machine learning study on pooling intervention data in e-mental health dropout predictions","volume":"10","author":"Zantvoort","journal-title":"Digit Health"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1093\/ckj\/sfaa188","article-title":"External validation of prognostic models: what, why, how, when and where?","volume":"14","author":"Ramspek","journal-title":"Clin Kidney J"},{"key":"R28","volume":"30","author":"Lundberg","journal-title":"Adv Neural Inf Process Syst"},{"key":"R29","unstructured":"Norma Oficial Mexicana NOM-012-SSA3-2012, que establece los criterios para la ejecuci\u00f3n de proyectos de investigaci\u00f3n en seres humanos. Secretar\u00eda de salud. Diario Oficial de la Federaci\u00f3n; 2013. URL: https:\/\/www.dof.gob.mx\/nota_detalle.php?codigo=5284149&fecha=04\/01\/2013 [Accessed 03-11-2026]"},{"key":"R30","unstructured":"Estudios Cl\u00ednicos. URL: https:\/\/estudiosclinicos.salud.gob.mx\/ [Accessed 05-06-2026]"},{"issue":"23","key":"R31","doi-asserted-by":"publisher","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","journal-title":"Medicine (Baltimore)"},{"issue":"12","key":"R32","doi-asserted-by":"publisher","first-page":"2027","DOI":"10.1089\/neu.2016.4955","article-title":"Functional outcome prediction after traumatic spinal cord injury based on acute clinical factors","volume":"34","author":"Kaminski","journal-title":"J Neurotrauma"},{"issue":"9","key":"R33","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1089\/neu.2020.7594","article-title":"Use of regression tree analysis for predicting the functional outcome after traumatic spinal cord injury","volume":"38","author":"Facchinello","journal-title":"J Neurotrauma"},{"issue":"1","key":"R34","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","journal-title":"Arch Phys Med Rehabil"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.2196\/66233","article-title":"Predicting spinal cord injury prognosis using machine learning: systematic review and meta-analysis","volume":"4","author":"Zhong","journal-title":"JMIR AI"}],"container-title":["JMIR Research Protocols"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.researchprotocols.org\/2026\/1\/e95236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:23:24Z","timestamp":1785536604000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchprotocols.org\/2026\/1\/e95236"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":35,"URL":"https:\/\/doi.org\/10.2196\/95236","relation":{},"ISSN":["1929-0748"],"issn-type":[{"value":"1929-0748","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]},"article-number":"v15i4e95236"}}