A Dual-Use Framework for Clinical Gait Analysis: Attention-Based Sensor Optimization and Automated Dataset Auditing

TL;DR

This paper introduces an attention-based deep learning framework that optimizes sensors and audits datasets in clinical gait analysis, revealing biases and suggesting new sensor combinations for improved diagnostics.

Contribution

It presents a novel interpretable framework that automatically detects dataset biases and proposes optimized sensor configurations for gait analysis.

Findings

Discovered severe laterality bias in public gait datasets.

Identified new sensor combinations for specific clinical tasks.

Demonstrated the framework's ability to audit dataset integrity.

Abstract

Objective gait analysis using wearable sensors and AI is critical for managing neurological and orthopedic conditions. However, models are vulnerable to hidden dataset biases, and task-specific sensor optimization remains a challenge. We propose a multi-stream attention-based deep learning framework that functions as both a sensor optimizer and an automated data auditor. Applied to the Voisard et al. (2025) multi-cohort gait dataset on four clinical tasks (PD, OA, CVA screening; PD vs CVA differential), the model's attention mechanism quantitatively discovered a severe dataset confound. For OA and CVA screening, tasks where bilateral assessment is clinically essential, the model assigned more than 70 percent attention to the Right Foot while statistically ignoring the Left Foot (less than 0.1 percent attention, 95 percent CI [0.0-0.1]). This was not a clinical finding but a direct reflection of a severe laterality bias (for example, 15 of 15 right-sided OA) in the public dataset. The primary contribution of this work is methodological, demonstrating that an interpretable framework can automatically audit dataset integrity. As a secondary finding, the model proposes novel, data-driven sensor synergies (for example, Head plus Foot for PD screening) as hypotheses for future optimized protocols.