Interpretable Machine Learning for Stroke Recovery: Predicting Discharge and 3-Month Functional Outcomes.
Introduction: Stroke is a leading cause of disability worldwide. This study uses Machine Learning models to investigate factors influencing modified Rankin Scale scores at discharge and three months post-discharge. Methods: Data from 116 stroke patients were analyzed using four predictive models: Lo...
| Publicado en: | NeuroRehabilitation Vol. 58; no. 3; pp. 453 - 463 |
|---|---|
| Autores principales: | , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Sage Publications Inc.
May2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=193319990&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 193319990 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 10538135 3RE jtl: NeuroRehabilitation issn: 10538135 maglogo: N pubinfo: dt: May2026 vid: 58 iid: 3 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 193319990 191675144 193319990 193319990 10.1177/10538135261420819 193319990 ppf: 453 ppct: 10 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Interpretable Machine Learning for Stroke Recovery: Predicting Discharge and 3-Month Functional Outcomes. aug: au: Augusto, Inês Carvalho Martins Antonio, Nuno Marreiros, Ana Ramalhete, Sara Ventura Nzwalo, Hipólito affil: NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Lisbon, Portugal sug: subj: Stroke Rehabilitation Machine Learning Utilization Prediction Models Utilization Recovery Patient Discharge Treatment Outcomes Human Male Female Adult Middle Age Aged Aged, 80 and Over Funding Source Portugal Stroke Patients Inpatients Retrospective Design Record Review Logistic Regression Support Vector Machine Random Forest Boosting Machine Learning Algorithms Kruskal-Wallis Test Post Hoc Analysis ROC Curve Correlational Studies Sociodemographic Factors Comorbidity Head Injuries Cerebrovascular Disorders Rehabilitation, Driver Data Analysis Software Descriptive Statistics Scales Adult: 19-44 years Middle Aged: 45-64 years Aged: 65+ years Aged, 80 & over Male Female ab: Introduction: Stroke is a leading cause of disability worldwide. This study uses Machine Learning models to investigate factors influencing modified Rankin Scale scores at discharge and three months post-discharge. Methods: Data from 116 stroke patients were analyzed using four predictive models: Logistic Regression, Support Vector Machine, Random Forest, and Extreme Gradient Boosting (XGB). Shapley Additive Explanations (SHAP) were also employed to interpret factor significance. Results and discussion: The XGB model achieved an Area Under the Curve of 79% at discharge and 87% three months post-discharge. SHAP analysis revealed changing factor significance over time. The National Institutes of Health Stroke Scale was most critical at discharge, while post-discharge destination became more significant at three months. Age, time metrics, thrombolysis therapy, and management of long-term health issues also proved influential. Conclusions: Findings highlight the complex, evolving nature of stroke recovery. The shift in factor importance from clinical interventions to broader health management issues emphasizes the need for time-sensitive, multifaceted approaches to stroke care. This study contributes to understanding stroke recovery by identifying key influencing factors and demonstrating the value of SHAP for model interpretation. The insights gained have practical implications for rehabilitation practices. By identifying evolving predictors of recovery, the proposed framework may support early stratification of rehabilitation needs, assist clinicians in tailoring rehabilitation intensity and modality, and inform discharge destination decisions. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|