Trustworthy Gait Analysis for Computer-Aided Diagnosis in Parkinson’s Disease and Knee Osteoarthritis: A Targeted Narrative Review of Algorithms and Clinical Validation

Abstract

Gait analysis is increasingly used as a dynamic functional biomarker for computer-aided diagnosis (CADx), although strong internal performance alone does not establish clinical utility. This targeted narrative review examines Parkinson’s disease (PD) and knee osteoarthritis (KOA) as its primary clinical contexts while treating fall risk and other mobility disorders as contextual extensions. A structured literature search and source-verification process covered studies available through 31 July 2026. The review corpus comprised 118 sources spanning clinical evidence, measurement validation, datasets, algorithmic architectures, and methodological guidance. This review critically compares sensing modalities, public and proprietary datasets, feature-based models, CNN/RNN architectures, graph neural networks, Transformers, state-space models, and trust-supporting approaches, including explainable artificial intelligence, automated machine learning, federated learning, and multimodal fusion. Using an explicit coverage rule, a common validation audit was applied to 15 empirical or measurement-validation studies. The audited evidence did not demonstrate mature independent multisite validation for disease-focused gait CADx. Formal probability calibration and quantitative testing of explanation stability were also absent, while publicly available KOA-specific multimodal benchmarks remained scarce. Based on these findings, this review proposes a six-level validation-readiness ladder in which independent external evidence at Level 3 represents the minimum threshold for initiating a supervised clinical pilot. The framework prioritizes subject-level separation, leakage control, calibration, clinically meaningful reference standards, and prospective workflow evaluation.