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

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Yankai Zheng, Yuhe Liu, Yuxin Ma, Tianci Xue, Jiayuan Tian, Yu Fu, Yuxuan Hu, Jianing Wang, Zichun Xiao, Junya Mu, Shaohui Ma
• Venue: arXiv: cs.LG
• Published: 2026-07-22
• Collected: 2026-07-23
• URL: http://arxiv.org/abs/2607.20237v1
• PDF: https://arxiv.org/pdf/2607.20237v1
• DOI: UNKNOWN

Plain-Language Brief

The study introduces PhaseAware, a framework designed for continuous evaluation of rehabilitation quality during physical therapy sessions. It combines temporal data with phase-specific and body part descriptors to improve the accuracy of assessment. The model was tested on two different squatting protocols and showed significant improvement over the accepted baseline on one of them. Additionally, it generates structured review cues for clinicians to better understand the assessments and monitor boundary cases, but it's not intended for autonomous decision-making.

What the Document Says

• The study presents PhaseAware, a framework for continuous rehabilitation quality assessment that combines temporal data with phase-specific and body part descriptors.
• It 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, which is an 88.9% reduction relative to the accepted baseline.
• It maintained favorable performance on KIMORE, suggesting that the phase-aware design transfers across related squatting protocols.
• The architecture employs a backbone-conditioned gated residual mechanism to stabilize feature representation.
• PhaseAware generates structured review cues based on phase- and body-level sensitivity.
• 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.

Key Concepts Mentioned

• rehabilitation scoring systems
• PhaseAware
• temporal backbone
• phase- and body-group descriptors
• backbone-conditioned gated residual pathway
• RMSE
• UI-PRMD
• KIMORE

Claims Made by the Document

• PhaseAware offers a significant improvement over the accepted baseline in rehabilitation scoring.
• The phase-aware design of PhaseAware transfers across related squatting protocols.

Evidence Used

• An RMSE of 0.0230 was achieved on UI-PRMD, which is an 88.9% reduction relative to the accepted baseline.
• Favorable performance on KIMORE.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.