Markerless Motion Capture in Routine Clinical Upper Limb Assessments: Validity and Insights Beyond Ordinal Scoring

2026-07-26

AI Summary

Traditional upper-limb functional assessments, such as the Action Research Arm Test (ARAT), rely on subjective ordinal scoring and exhibit limited sensitivity and specificity. This study introduces, for the first time in real-world clinical settings, an artificial intelligence–driven, markerless motion capture system combined with biomechanical reconstruction and kinematic feature extraction to objectively quantify ARAT performance. Applied across 47 clinical evaluations, the approach achieved high-fidelity movement reconstruction, yielding metrics with strong discriminant validity. Notably, it uncovered individualized recovery patterns among patients who received identical ARAT scores and detected continued functional improvement beyond the point of score saturation, thereby substantially enhancing both the sensitivity and specificity of post-stroke upper-limb assessment.

Abstract

The Action Research Arm Test (ARAT) is a widely-used upper limb outcome measure in neurorehabilitation, but its ordinal scoring is subjective and suffers from limited sensitivity and specificity. We evaluated whether artificial-intelligence (AI)-based markerless motion capture (MMC), embedded into ARAT assessments during clinical routine, accurately reconstructs upper limb movement and yields valid, objective kinematic metrics carrying clinically meaningful information beyond the ordinal score. Across 47 sessions from 20 mixed-neurological patients (1,174 ARAT tasks), biomechanical reconstruction was accurate and robust across impairment levels, and kinematic metrics showed the discrimination pattern expected of a construct-valid measure. In longitudinal case studies, the metrics added the specificity and sensitivity the ordinal score lacks: a domain decomposition exposed patient-specific recovery profiles underlying equal ARAT gains (specificity), and kinematic improvement continued to be detected after the ARAT had saturated (sensitivity). MMC in clinical routine can thus provide valid, objective, sensitive, and specific kinematic measurement complementing ordinal scoring.

Problem

• markerless motion capture
• Action Research Arm Test
• kinematic metrics
• ordinal scoring
• neurorehabilitation

Innovation

• markerless motion capture
• AI-based kinematic analysis
• Action Research Arm Test
• objective clinical assessment
• neurorehabilitation