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

1. 1Collect 3D skeletal motion data from a large population using depth cameras
2. 2Develop a gait foundation model to learn embeddings from the motion data
3. 3Evaluate the model's performance in predicting health phenotypes such as age, BMI, and visceral adipose tissue area
4. 4Compare the performance of learned embeddings with engineered features

Data scientists and AI engineers on a healthcare team can benefit from this research to develop predictive models for health phenotypes, while product managers can explore applications in healthcare and wellness

💡 Learned embeddings from 3D skeletal motion can outperform engineered features in predicting health phenotypes

🚀 Gait foundation model predicts health phenotypes from 3D skeletal motion!