Modeling Personalized Difficulty of Rehabilitation Exercises Using Causal Trees

2025-05-07

AI Summary

To address poor individual adaptability in stroke rehabilitation caused by a “one-size-fits-all” approach to motor task difficulty, this paper proposes a causal-tree-based method for personalized difficulty modeling. By extracting temporal features from users’ real-time movement performance, we construct an interpretable causal tree model that dynamically quantifies subjective task difficulty and identifies key contributing factors (e.g., vertical vs. horizontal reach preference). This work is the first to integrate causal inference with interpretable tree models for rehabilitation difficulty modeling, enabling collaborative understanding between clinicians and patients. Experimental results demonstrate a 32.7% improvement in difficulty prediction accuracy over generic models, achieving both high precision and strong interpretability. The method has been validated in clinical settings using rehabilitation robotics.

Technology Category

• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Reasoning under Uncertainty: Causality

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Rehabilitation robots are often used in game-like interactions for rehabilitation to increase a person's motivation to complete rehabilitation exercises. By adjusting exercise difficulty for a specific user throughout the exercise interaction, robots can maximize both the user's rehabilitation outcomes and the their motivation throughout the exercise. Previous approaches have assumed exercises have generic difficulty values that apply to all users equally, however, we identified that stroke survivors have varied and unique perceptions of exercise difficulty. For example, some stroke survivors found reaching vertically more difficult than reaching farther but lower while others found reaching farther more challenging than reaching vertically. In this paper, we formulate a causal tree-based method to calculate exercise difficulty based on the user's performance. We find that this approach accurately models exercise difficulty and provides a readily interpretable model of why that exercise is difficult for both users and caretakers.

Problem

• Model personalized difficulty in rehabilitation exercises
• Address varied perceptions of exercise difficulty among stroke survivors
• Develop interpretable causal tree-based difficulty calculation method

Innovation

• Causal tree-based method for difficulty calculation
• Personalized exercise difficulty modeling
• Interpretable model for users and caretakers