Modelling individual variation in human walking gait across populations and walking conditions via gait recognition

Human walking gait is a personal story written by the body, a tool for understanding biological identity in healthcare and security. Gait analysis methods traditionally diverged between these domains but are now merging their complementary strengths to unlock new possibilities. Using large ground reaction force (GRF) datasets for gait recognition is a way to uncover subtle variations that define individual gait patterns. Previously, this was done by developing and evaluating machine learning models on the same individuals or the same dataset, potentially biasing findings towards population samples or walking conditions. This study introduces a new method for analysing gait variation across individuals, groups and datasets to explore how demographics and walking conditions shape individual gait patterns. Machine learning models were implemented using numerous configurations of four large walking GRF datasets from different countries (740 individuals, 7400 samples) and analysed using explainable artificial intelligence tools. Recognition accuracy ranged from 52 to 100%, with factors like footwear, walking speed and body mass playing interactive roles in defining gait. Models developed with individuals walking in personal footwear at multiple speeds effectively recognized novel individuals across populations and conditions (89-99% accuracy). Integrating force platform hardware and gait recognition software could be invaluable for reading the complex stories of human walking.