An Exploratory Study on Techniques for Quantitative Assessment of Stroke Rehabilitation Exercises

Abstract

Technology-assisted systems to monitor and assess rehabilitation exercises have an opportunity of enhancing rehabilitation practices by automatically collecting patient's quantitative performance data. However, even if a complex algorithm (e.g. Neural Network) is applied, it is still challenging to develop such a system due to patients with various physical conditions. The system with a complex algorithm is limited to be a black-box system that cannot provide explanations on its predictions. To address these challenges, this paper presents a hybrid model that integrates a machine learning (ML) model with a rule-based (RB) model as an explainable artificial intelligence (AI) technique for quantitative assessment of stroke rehabilitation exercises. For evaluation, we collected therapist's knowledge on assessment as 15 rules from interviews with therapists and the dataset of three upper-limb stroke rehabilitation exercises from 15 post-stroke and 11 healthy subjects using a Kinect sensor. Experimental results show that a hybrid model can achieve comparable performance with a ML model using Neural Network, but also provide explanations on a model prediction with a RB model. The results indicate the potential of a hybrid model as an explainable AI technique to support the interpretation of a model and fine-tune a model with user-specific rules for personalization. CCS CONCEPTS • Human-centered computing → Interactive systems and tools; • Applied computing → Health care information systems.

AI-Driven Stroke Rehabilitation Systems and Assessment: A Systematic Review

“…Thus, these systems do not eliminate the need for therapists, but rather assist them and alleviate some of the dependency on them. The consequent research question is directly addressed by the authors of [91], [92], [102] who directly report high agreement levels among therapist and automated assessment.…”

“…The findings indicated a good agreement level with the therapists' assessments. On this basis, Lee et al [92] investigated several such hybrid models using a variety of classifiers, including Neural Networks (NNs), SVMs, and others and discovered that NNs produce an effective result. This was further demonstrated in [93], which combined reinforcement learning with a variety of classifiers.…”

Enabling AI and Robotic Coaches for Physical Rehabilitation Therapy: Iterative Design and Evaluation with Therapists and Post-stroke Survivors

“…Exoskeleton robots have been explored to augment patient's weak body limbs and induce a passive motion for rehabilitation [26]. AI [22] or robotic coaches [11,25,47] can guide patient's rehabilitation through automatically monitoring patient's exercises [23] and providing feedback on whether a patient performs well-being-related or rehabilitation exercises correctly or not [11,17,25,29,41]. As prior work has demonstrated the benefit of physical embodiment to improve the engagement in physical exercises [11], we decided to further explore research on socially assistive robotics.…”

“…how closely a post-stroke sur- vivor achieves the target position), smoothness of a motion, and compensation (i.e. whether a post-stroke survivor utilizes an unnecessary joint to make a motion) [23,40]. When a post-stroke survivor completes an exercise correctly, an AI and robotic coach provides positive encouragement with the gesture of clapping.…”

“…To address this problem, there has been increasing attention on artificial intelligence (AI) and robotic coaches [47]. These systems leverage AI techniques to autonomously monitor patient's exercises [23]. In addition, these systems can assist patient's engagement in well-being-related or rehabilitation exercises through social interaction (e.g.…”