Optimizing the setting of medical interactive rehabilitation assistant platform to improve the performance of the patients: A case study

作者：

Highlights：

• This study aims to develop a method for optimizing patients' profile setting according to the estimated optimal results.

• The proposed method is developed by unsupervised and supervised learning techniques. In particular, we used the Self-Organizing Map (SOM) to cluster patients' records into several distinct clusters. Moreover, the K-fold Cross Validation was applied to construct the prediction models.

• Meanwhile, the Classification And Regression Tree (CART) was utilized to predict the patient's optimal input setting for playing the Medical Interactive Rehabilitation Assistant (MIRA) games.

摘要

•Performing Tele-rehabilitation is an alternative for the conventional rehabilitation service which helps patients in rural areas to access a service that is practical in terms of logistics and cost in a controlled environment.•This study aims to develop a method for optimizing patients' profile setting according to the estimated optimal results.•The proposed method is developed by unsupervised and supervised learning techniques. In particular, we used the Self-Organizing Map (SOM) to cluster patients' records into several distinct clusters. Moreover, the K-fold Cross Validation was applied to construct the prediction models.•Meanwhile, the Classification And Regression Tree (CART) was utilized to predict the patient's optimal input setting for playing the Medical Interactive Rehabilitation Assistant (MIRA) games.

论文关键词：Rehabilitation,Machine learning,MIRA,SOM,CART.

论文评审过程：Received 23 December 2020, Revised 19 July 2021, Accepted 16 August 2021, Available online 20 August 2021, Version of Record 16 September 2021.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102151