Calibrated Uncertainty for Trustworthy Clinical Gait Analysis Using Probabilistic Multiview Markerless Motion Capture

OBJECTIVE: This study evaluates the calibration and accuracy of a probabilistic MMMC method. 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 estimate biomechanical variables against clinical gold-standards. METHODS: 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). RESULTS: 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^ across lower extremity joints. Consistent with the calibrated ECE, the magnitude of the model's predicted uncertainty correlated strongly with observed error measures. CONCLUSION: These findings indicate that, as designed, the probabilistic model reconstruction quantifies epistemic uncertainty, shown by low absolute error and calibrated uncertainty. SIGNIFICANCE: These findings highlight the potential to identify unreliable outputs without the need for concurrent ground-truth instrumentation through the use of this probabilistic model.