Forecasting the Walking Assistance Rehabilitation Level of Stroke Patients Using Artificial Intelligence
Kanghyeon Seo,
Bokjin Chung,
Hamsa Priya Panchaseelan,
Taewoo Kim,
Hyejung Park,
Byungmo Oh,
Minho Chun,
Sunjae Won,
Donkyu Kim,
Jaewon Beom,
Doyoung Jeon,
Jihoon Yang
Affiliations
Kanghyeon Seo
Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea
Bokjin Chung
Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea
Hamsa Priya Panchaseelan
Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea
Taewoo Kim
Department of Rehabilitation Medicine, National Traffic Injury Rehabilitation Hospital, 260 Jungang-ro, Yangpyeong-gun, Gyunggi-do 12564, Korea
Hyejung Park
Department of Rehabilitation Medicine, National Traffic Injury Rehabilitation Hospital, 260 Jungang-ro, Yangpyeong-gun, Gyunggi-do 12564, Korea
Byungmo Oh
Department of Rehabilitation Medicine, National Traffic Injury Rehabilitation Hospital, 260 Jungang-ro, Yangpyeong-gun, Gyunggi-do 12564, Korea
Minho Chun
Asan Medical Center, Department of Rehabilitation Medicine, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Korea
Sunjae Won
Department of Rehabiliation Medicine, Yeouido St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 10 63-ro, Yeongdeungpo-gu, Seoul 07345, Korea
Donkyu Kim
Department of Physical Medicine and Rehabilitation, Chung-Ang University Hospital, Chung-Ang University College of Medicine, 102 Heukseok-ro, Dongjak-gu, Seoul 06973, Korea
Jaewon Beom
Department of Rehabilitation Medicine, Seoul National University College of Medicine, Seoul National University Bundang Hospital, 82 Gumi-ro, 173beon-gil, Bundang-gu, Seongnam-si 13620, Gyeonggi-do, Korea
Doyoung Jeon
Department of Mechanical Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea
Jihoon Yang
Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea
Cerebrovascular accidents (CVA) cause a range of impairments in coordination, such as a spectrum of walking impairments ranging from mild gait imbalance to complete loss of mobility. Patients with CVA need personalized approaches tailored to their degree of walking impairment for effective rehabilitation. This paper aims to evaluate the validity of using various machine learning (ML) and deep learning (DL) classification models (support vector machine, Decision Tree, Perceptron, Light Gradient Boosting Machine, AutoGluon, SuperTML, and TabNet) for automated classification of walking assistant devices for CVA patients. We reviewed a total of 383 CVA patients’ (1623 observations) prescription data for eight different walking assistant devices from five hospitals. Among the classification models, the advanced tree-based classification models (LightGBM and tree models in AutoGluon) achieved classification results of over 90% accuracy, recall, precision, and F1-score. In particular, AutoGluon not only presented the highest predictive performance (almost 92% in accuracy, recall, precision, and F1-score, and 86.8% in balanced accuracy) but also demonstrated that the classification performances of the tree-based models were higher than that of the other models on its leaderboard. Therefore, we believe that tree-based classification models have potential as practical diagnosis tools for medical rehabilitation.
