Developmental Prediction of Poststroke Patients in Activities of Daily Living by Using Tree-Structured Parzen Estimator-Optimized Stacking Ensemble Approaches

• Published in: IEEE journal of biomedical and health informatics Vol. 28; no. 5; pp. 2745 - 2758
• Main Authors: Lin, Pei-Hua, Kuo, Ping-Huan, Chen, Kuan-Lin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-05-2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Activities of Daily Living; Activities of daily living prediction; Adult; Aged; Aged, 80 and over; Algorithms; Barthel index post-stroke patients; Daily; Female; Hospitals; Humans; Injury prevention; Learning algorithms; Machine Learning; Machine learning algorithms; Male; Middle Aged; Multilayer perceptrons; occupational therapy; Optimization; Patients; Prediction algorithms; Predictive models; Stroke; Stroke (medical condition); Stroke - physiopathology; Stroke Rehabilitation - methods; Training
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2024.3372649

Poststroke injuries limit the daily activities of patients and cause considerable inconvenience. Therefore, predicting the activities of daily living (ADL) results of patients with stroke before hospital discharge can assist clinical workers in formulating more personalized and effective strategies for therapeutic intervention, and prepare hospital discharge plans that suit the patients needs. This study used the leave-one-out cross-validation procedure to evaluate the performance of the machine learning models. In addition, testing methods were used to identify the optimal weak learners, which were then combined to form a stacking model. Subsequently, a hyperparameter optimization algorithm was used to optimize the model hyperparameters. Finally, optimization algorithms were used to analyze each feature, and features of high importance were identified by limiting the number of features to be included in the machine learning models. After various features were fed into the learning models to predict the Barthel index (BI) at discharge, the results indicated that random forest (RF), adaptive boosting (AdaBoost), and multilayer perceptron (MLP) produced suitable results. The most critical prediction factor of this study was the BI at admission. Machine learning models can be used to assist clinical workers in predicting the ADL of patients with stroke at hospital discharge.