Joseph Futoma
Joseph Futoma has 2 papers in the ChatPPG research atlas (2024–2025), linked to 2 models and 11 co-authors in the atlas. Main topics: Apple, AHMS, Mamba-2, behavioral-data, contrastive-learning, ICML.
Papers
- Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions (WBM)2025 · ICML 2025
WBM is an Apple foundation model built on behavioral data from wearables, such as derived activity and health metrics, instead of raw sensor waveforms. It was trained on more than 2.5 billion hours of data from 162K people in the Apple Heart and Movement Study and evaluated on 57 health tasks. It did best on behavior-driven tasks like sleep prediction and improved further when combined with a PPG foundation model.
- Published: ICML 2025 (Apple ML Research)
- Data: 2.5B+ hours, 162K individuals
- Input: behavioral wearable metrics
- Wearable Accelerometer Foundation Models for Health via Knowledge Distillation2024 · arXiv preprint
This Apple paper shows that an accelerometer foundation model can predict many health targets when it learns from a PPG model through knowledge distillation. Training used 20 million minutes of unlabelled data from about 172K people in the Apple Heart and Movement Study. Accelerometer embeddings retrieved the matching PPG embedding with 99.2% top-1 accuracy, and distilled encoders beat accelerometer-only ones by 23% to 49%.
- Published: ArXiv preprint, 2024
- Signals: PPG, Accelerometer
- Result: The authors observe strong cross-modal alignment on unseen data, e.g., 99.2% top-1 accuracy for retrieving PPG embeddings from accelerometry embeddings.