Center of Pressure- and Machine Learning-based Gait Score and Clinical Risk Factors for Predicting Functional Outcome in Acute Ischemic Stroke

Abstract

ObjectivesTo investigate whether machine learning (ML)-based center of pressure (COP) analysis for gait assessment, when used in conjunction with clinical information, offers additive benefits in predicting functional outcomes in patients with acute ischemic stroke. Study DesignA prospective, single-center cohort study. SettingA tertiary hospital setting. ParticipantsA total of 185 patients with acute ischemic stroke, capable of walking 10 meters with or without a gait aid by day 7 post-admission. From these patients, 10,804 pairs of consecutive footfalls were included for analysis. InterventionsNot applicable. Main Outcome MeasuresThe dependent variable was a three-month poor functional outcome, defined as modified Rankin scale scores ≥ 2. For independent variables, 65 clinical variables including demographics, anthropometrics, comorbidities, laboratory data, questionnaires, and drug history were included. Gait function was evaluated using a pressure-sensitive mat. Time-series COP data were parameterized into spatial and temporal variables and analyzed with logistic regression and two ML models (LightGBM, and multilayer perceptron [MLP]). We derived output GAIT scores from the best-performing model analyzed COP data, and constructed multivariable logistic regression models using clinical variables and the GAIT scores. ResultsAmong the included patients, 70 (37.8%) experienced unfavorable outcomes. The MLP model demonstrated the highest predictive performance with an area under the receiver operating characteristic curve (AUROC) of 0.799. Multivariable logistic regression identified age, initial National Institute of Health Stroke Scale, and initial Fall Efficacy Scale-International as associated factors with unfavorable outcomes. The combined multivariable logistic regression incorporating COP-derived output scores improved the AUROC to 0.812. ConclusionsGait function, assessed through COP analysis, serves as a significant predictor of functional outcome in acute ischemic stroke patients. Machine learning-based COP analysis, when combined with clinical data, enhances the prediction of poor functional outcomes.