PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring

2026-07-22

AI Summary

This study addresses the limited clinical interpretability and poor workflow integration of existing rehabilitation scoring systems, which hinder physician review and monitoring of borderline cases. To overcome these limitations, the authors propose PhaseAware, a novel framework that integrates temporal backbone networks with phase- and body-part descriptors, augmented by a backbone-conditioned gated residual mechanism. This approach uniquely enables simultaneous high-accuracy scoring and generation of phase- and body-sensitive interpretability cues in rehabilitation movement assessment. The system supports structured review prompts to facilitate human–AI collaboration rather than autonomous decision-making. Evaluated on the UI-PRMD squat dataset, PhaseAware achieves an RMSE of 0.0230, reducing baseline error by 88.9%, and demonstrates strong generalization performance on the KIMORE dataset.

Abstract

Rehabilitation scoring systems are most useful when their outputs can be reviewed and interpreted within clinical workflows. This study presents PhaseAware, a compact framework for continuous rehabilitation quality assessment that combines a temporal backbone with phase- and body-group descriptors through a backbone-conditioned gated residual pathway. The model was evaluated on the UI-PRMD deep-squat protocol and further tested on the KIMORE squatting subset. On UI-PRMD, PhaseAware achieved an RMSE of 0.0230, corresponding to an 88.9% reduction relative to the accepted baseline. It also maintained favorable performance on KIMORE, suggesting that the phase-aware design transfers across related squatting protocols. In addition to score prediction, PhaseAware generates structured review cues based on phase- and body-level sensitivity, highlighting the movement stages and body regions most relevant to each prediction. The architecture employs a backbone-conditioned gated residual mechanism to stabilize feature representation, supporting use in resource-constrained settings. These cues are intended to support clinician review, boundary-case monitoring, and human-in-the-loop triage rather than autonomous decision-making. Overall, PhaseAware offers a practical and interpretable approach to rehabilitation scoring that may help integrate automated assessment into information systems while preserving clinician oversight.

Problem

• rehabilitation scoring
• interpretability
• human-in-the-loop
• clinical workflow
• boundary monitoring

Innovation

• Phase-aware modeling
• Interpretable AI
• Human-in-the-loop
• Gated residual network
• Rehabilitation scoring