Can AI predict walking independence in patients with stroke upon admission to a recovery-phase rehabilitation ward?

Abstract

This study aimed to develop a prediction model for walking independence in patients with stroke in the recovery phase at the time of hospital discharge using Prediction One, an artificial intelligence (AI)-based predictive analysis tool, and to examine its utility. Prediction One was used to develop a prediction model for walking independence for 280 patients with stroke admitted to a rehabilitation ward-based on physical and mental function information at admission. In 134 patients with stroke hospitalized during different periods, accuracy was confirmed by calculating the correct response rate, sensitivity, specificity, and positive and negative predictive values based on the results of AI-based predictions and actual results. The prediction accuracy (area under the curve, AUC) of the proposed model was 91.7%. The correct response rate was 79.9%, sensitivity was 95.7%, specificity was 62.5%, positive predictive value was 73.6%, and negative predictive value was 93.5%. The accuracy of the prediction model developed in this study is not inferior to that of previous studies, and the simplicity of the model makes it highly practical.