EMBC Special Issue: Calibrated Uncertainty for Trustworthy Clinical Gait Analysis Using Probabilistic Multiview Markerless Motion Capture

TL;DR

This study evaluates a probabilistic markerless motion capture system for clinical gait analysis, demonstrating that it produces well-calibrated confidence intervals and reliable uncertainty estimates, enhancing trustworthiness for clinical use.

Contribution

The paper presents a validated probabilistic MMMC method that accurately calibrates confidence intervals and quantifies uncertainty without requiring ground-truth data, advancing clinical gait analysis tools.

Findings

Model showed reliable calibration with ECE < 0.1 for key gait metrics.

Median errors: ~16 mm for step length, ~12 mm for stride length.

Uncertainty estimates correlated strongly with actual errors.

Abstract

Video-based human movement analysis holds potential for movement assessment in clinical practice and research. However, the clinical implementation and trust of multi-view markerless motion capture (MMMC) require that, in addition to being accurate, these systems produce reliable confidence intervals to indicate how accurate they are for any individual. Building on our prior work utilizing variational inference to estimate joint angle posterior distributions, this study evaluates the calibration and reliability of a probabilistic MMMC method. We analyzed data from 68 participants across two institutions, validating the model against an instrumented walkway and standard marker-based motion capture. We measured the calibration of the confidence intervals using the Expected Calibration Error (ECE). The model demonstrated reliable calibration, yielding ECE values generally < 0.1 for both step and stride length and bias-corrected gait kinematics. We observed a median step and stride length error of ~16 mm and ~12 mm respectively, with median bias-corrected kinematic errors ranging from 1.5 to 3.8 degrees across lower extremity joints. Consistent with the calibrated ECE, the magnitude of the model's predicted uncertainty correlated strongly with observed error measures. These findings indicate that, as designed, the probabilistic model reconstruction quantifies epistemic uncertainty, allowing it to identify unreliable outputs without the need for concurrent ground-truth instrumentation.