# A Gait Foundation Model Predicts Multi-System Health Phenotypes from 3D Skeletal Motion

arXiv: https://arxiv.org/abs/2603.25283 · HTML: https://mlsanity.com/paper/2603.25283/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 59 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 10 of 10)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition](https://mlsanity.com/paper/2209.02399/) (2022)
- [GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation](https://mlsanity.com/paper/2207.00106/) (2022)
- [Self-Supervised Learning of Gait-Based Biomarkers](https://mlsanity.com/paper/2307.16321/) (2023)

## Built on by (most cited first, 1 of 1)

- [Learning Human Health and Diseases from 24-hour Wrist Movement](https://mlsanity.com/paper/2608.29494/) (2026)

## Abstract (arXiv)

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 phenotypic targets; after adjustment for age, BMI, VAT, and height, gait provided independent gains in all 18 body systems in males and 17 of 18 in females, and improved prediction of clinical diagnoses and medication use. Anatomical ablation revealed that legs dominated metabolic and frailty predictions while torso encoded sleep and lifestyle phenotypes. These findings establish gait as an independent multi-system biosignal, motivating translation to consumer-grade video and its integration as a scalable, passive vital sign.