A foundation model for gait transforms 3D skeletal motion into a systemic biosignal for multi-system health monitoring.
March 27, 2026
Original Paper
A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion
arXiv · 2603.25283
The Takeaway
The model successfully predicts age, BMI, and clinical phenotypes across 18 body systems from passive depth-camera data. It establishes gait as a high-dimensional diagnostic tool rather than just a symptom of specific pathologies.
From the abstract
Gait is increasingly recognized as a vital sign, yet current approaches treat it as a symptom of specific pathologies rather than a systemic biomarker. We developed a gait foundation model for 3D skeletal motion from 3,414 deeply phenotyped adults, recorded via a depth camera during five motor tasks. Learned embeddings outperformed engineered features, predicting age (Pearson r = 0.69), BMI (r = 0.90), and visceral adipose tissue area (r = 0.82). Embeddings significantly predicted 1,980 of 3,210