Interpretable and Personalized Health Prediction System

Published:

Overview

Duration: 2023 – 2025

Developed an end-to-end health prediction system using smartwatch data. Proposed an Adaptive Spatial-Temporal Interpretable framework for accurate stress and sleep prediction despite data sparsity. Adapts to diverse user profiles (age, gender, behavior) to mitigate domain shift, while revealing key contributing factors for personalized health recommendations.

  • Personalized Sleep Prediction – A two-stage adaptive spatial-temporal model for interpretable and personalized sleep quality prediction from sparse wearable data.
    Wang, X., Claudine J. C. Lamoth, & Wilhelm, E. (2025). Personalized and interpretable sleep prediction via two stage adaptive spatial-temporal model. arXiv:2509.06974, under review.
  • Adaptive Stress Prediction – An online adaptive learning framework for interpretable and personalized stress prediction using multivariate and sparse physiological signals.
    Wang, X., Claudine J. C. Lamoth, & Wilhelm, E. (2026). AdaptStress: Online Adaptive Learning for Interpretable and Personalized Stress Prediction Using Multivariate and Sparse Physiological Signals. Under review.
  • Deep Adaptive Spatiotemporal Modeling – Personalized sleep prediction via deep adaptive spatiotemporal modeling from sparse wearable sensor data.
    Wang, X., Lamoth, C. J. C., & Wilhelm, E. (2025). Personalized sleep prediction via deep adaptive spatiotemporal modeling and sparse data. 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2025.
  • Multivariate Stress Forecast – Stress forecasting from sparse data collected during lifestyle interventions using multivariate wearable signals.
    Wang, X., Bellink, C., Lamoth, C., & Wilhelm, E. (2024). Multivariate stress forecast from sparse data during lifestyle interventions. IEEE International Conference on E-health Networking, Application & Services (HealthCom).
  • Personalized Stress Forecasting – Personalized stress forecasting utilizing multivariate sparse data from wearable devices.
    Wang, X., Lamoth, C. J. C., & Wilhelm, E. (2025). Personalized stress forecasting utilizing multivariate sparse data. 10th Dutch Bio-Medical Engineering Conference.

  1. Wang, X., Claudine J. C. Lamoth, & Wilhelm, E. (2026). AdaptStress: Online Adaptive Learning for Interpretable and Personalized Stress Prediction Using Multivariate and Sparse Physiological Signals. Under review.

  2. Wang, X., Claudine J. C. Lamoth, & Wilhelm, E. (2025). Personalized and interpretable sleep prediction via two stage adaptive spatial-temporal model. arXiv:2509.06974, under review.

  3. Wang, X., Lamoth, C. J. C., & Wilhelm, E. (2025). Personalized sleep prediction via deep adaptive spatiotemporal modeling and sparse data. 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2025.

  4. Wang, X., Lamoth, C. J. C., & Wilhelm, E. (2025). Personalized stress forecasting utilizing multivariate sparse data. 10th Dutch Bio-Medical Engineering Conference.

  5. Wang, X., Bellink, C., Lamoth, C., & Wilhelm, E. (2024). Multivariate stress forecast from sparse data during lifestyle interventions. IEEE International Conference on E-health Networking, Application & Services (HealthCom).