OGA-AID: Clinician-in-the-loop AI Report Drafting Assistant for Multimodal Observational Gait Analysis in Post-Stroke Rehabilitation

TL;DR

OGA-AID is a multi-agent AI system that assists clinicians in drafting structured gait analysis reports from multimodal data, improving accuracy and efficiency in post-stroke rehabilitation.

Contribution

This work introduces a novel multi-agent large language model system that integrates multimodal gait data for clinical report drafting, demonstrating improved performance over baselines.

Findings

OGA-AID outperforms single-pass baselines with low error.

Expert preliminary notes further reduce assessment error.

Multimodal agentic systems are feasible for clinical gait assessment.

Abstract

Gait analysis is essential in post-stroke rehabilitation but remains time-intensive and cognitively demanding, especially when clinicians must integrate gait videos and motion-capture data into structured reports. We present OGA-AID, a clinician-in-the-loop multi-agent large language model system for multimodal report drafting. The system coordinates 3 specialized agents to synthesize patient movement recordings, kinematic trajectories, and clinical profiles into structured assessments. Evaluated with expert physiotherapists on real patient data, OGA-AID consistently outperforms single-pass multimodal baselines with low error. In clinician-in-the-loop settings, brief expert preliminary notes further reduce error compared to reference assessments. Our findings demonstrate the feasibility of multimodal agentic systems for structured clinical gait assessment and highlight the complementary relationship between AI-assisted analysis and human clinical judgment in rehabilitation workflows.