Motion2Meaning: A Clinician-Centered Framework for Contestable LLM in Parkinson's Disease Gait Interpretation

TL;DR

Motion2Meaning introduces a clinician-centered, contestable AI framework for Parkinson's gait analysis using wearable sensors, combining interpretability, oversight, and advanced explanation safeguards to improve transparency and clinical validation.

Contribution

This work presents a novel integrated system with a contestable LLM and XAI safeguards for PD gait interpretation, enhancing transparency and clinician control over AI decisions.

Findings

Achieved 89.0% F1-score on PhysioNet dataset.

XMED detects unreliability with a five-fold increase in explanation discrepancies.

Clinicians can validate and contest AI predictions effectively.

Abstract

AI-assisted gait analysis holds promise for improving Parkinson's Disease (PD) care, but current clinical dashboards lack transparency and offer no meaningful way for clinicians to interrogate or contest AI decisions. To address this issue, we present Motion2Meaning, a clinician-centered framework that advances Contestable AI through a tightly integrated interface designed for interpretability, oversight, and procedural recourse. Our approach leverages vertical Ground Reaction Force (vGRF) time-series data from wearable sensors as an objective biomarker of PD motor states. The system comprises three key components: a Gait Data Visualization Interface (GDVI), a one-dimensional Convolutional Neural Network (1D-CNN) that predicts Hoehn & Yahr severity stages, and a Contestable Interpretation Interface (CII) that combines our novel Cross-Modal Explanation Discrepancy (XMED) safeguard with a contestable Large Language Model (LLM). Our 1D-CNN achieves 89.0% F1-score on the public PhysioNet gait dataset. XMED successfully identifies model unreliability by detecting a five-fold increase in explanation discrepancies in incorrect predictions (7.45%) compared to correct ones (1.56%), while our LLM-powered interface enables clinicians to validate correct predictions and successfully contest a portion of the model's errors. A human-centered evaluation of this contestable interface reveals a crucial trade-off between the LLM's factual grounding and its readability and responsiveness to clinical feedback. This work demonstrates the feasibility of combining wearable sensor analysis with Explainable AI (XAI) and contestable LLMs to create a transparent, auditable system for PD gait interpretation that maintains clinical oversight while leveraging advanced AI capabilities. Our implementation is publicly available at: https://github.com/hungdothanh/motion2meaning.