Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions

Eray Erturk, Fahad Kamran, Salar Abbaspourazad, Sean Jewell, Harsh Sharma, Yujie Li, Sinead Williamson, Nicholas J Foti, Joseph Futoma
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15516-15541, 2025.

Abstract

Wearable devices record physiological and behavioral signals that can improve health predictions. While foundation models are increasingly used for such predictions, they have been primarily applied to low-level sensor data, despite behavioral data often being more informative due to their alignment with physiologically relevant timescales and quantities. We develop foundation models of such behavioral signals using over 2.5B hours of wearable data from 162K individuals, systematically optimizing architectures and tokenization strategies for this unique dataset. Evaluated on 57 health-related tasks, our model shows strong performance across diverse real-world applications including individual-level classification and time-varying health state prediction. The model excels in behavior-driven tasks like sleep prediction, and improves further when combined with representations of raw sensor data. These results underscore the importance of tailoring foundation model design to wearables and demonstrate the potential to enable new health applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-erturk25a, title = {Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions}, author = {Erturk, Eray and Kamran, Fahad and Abbaspourazad, Salar and Jewell, Sean and Sharma, Harsh and Li, Yujie and Williamson, Sinead and Foti, Nicholas J and Futoma, Joseph}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {15516--15541}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/erturk25a/erturk25a.pdf}, url = {https://proceedings.mlr.press/v267/erturk25a.html}, abstract = {Wearable devices record physiological and behavioral signals that can improve health predictions. While foundation models are increasingly used for such predictions, they have been primarily applied to low-level sensor data, despite behavioral data often being more informative due to their alignment with physiologically relevant timescales and quantities. We develop foundation models of such behavioral signals using over 2.5B hours of wearable data from 162K individuals, systematically optimizing architectures and tokenization strategies for this unique dataset. Evaluated on 57 health-related tasks, our model shows strong performance across diverse real-world applications including individual-level classification and time-varying health state prediction. The model excels in behavior-driven tasks like sleep prediction, and improves further when combined with representations of raw sensor data. These results underscore the importance of tailoring foundation model design to wearables and demonstrate the potential to enable new health applications.} }
Endnote
%0 Conference Paper %T Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions %A Eray Erturk %A Fahad Kamran %A Salar Abbaspourazad %A Sean Jewell %A Harsh Sharma %A Yujie Li %A Sinead Williamson %A Nicholas J Foti %A Joseph Futoma %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-erturk25a %I PMLR %P 15516--15541 %U https://proceedings.mlr.press/v267/erturk25a.html %V 267 %X Wearable devices record physiological and behavioral signals that can improve health predictions. While foundation models are increasingly used for such predictions, they have been primarily applied to low-level sensor data, despite behavioral data often being more informative due to their alignment with physiologically relevant timescales and quantities. We develop foundation models of such behavioral signals using over 2.5B hours of wearable data from 162K individuals, systematically optimizing architectures and tokenization strategies for this unique dataset. Evaluated on 57 health-related tasks, our model shows strong performance across diverse real-world applications including individual-level classification and time-varying health state prediction. The model excels in behavior-driven tasks like sleep prediction, and improves further when combined with representations of raw sensor data. These results underscore the importance of tailoring foundation model design to wearables and demonstrate the potential to enable new health applications.
APA
Erturk, E., Kamran, F., Abbaspourazad, S., Jewell, S., Sharma, H., Li, Y., Williamson, S., Foti, N.J. & Futoma, J.. (2025). Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:15516-15541 Available from https://proceedings.mlr.press/v267/erturk25a.html.

Related Material