Real-time, personalized medicine through wearable sensors and dynamic predictive modeling: a new paradigm for clinical medicine.

Accurately predicting the onset and course of a disease in an individual is a major unmet challenge in medicine due to the complex and dynamic nature of disease progression. Continuous data from wearable technologies and biomarker data with a fine time resolution provide a unique opportunity to learn more about disease evolution and to usher in a new era of personalized and real-time medicine. Herein, we propose the potential of real-time, continuously measured physiological data as a noninvasive biomarker approach for detecting disease transitions, using allogeneic hematopoietic stem cell transplant (HCT) patient care as an example. Additionally, we review a recent computational technique, the landscape dynamic network biomarker method, that uses biomarker data to identify transition states in disease progression and explore how to use it with both biomarker and physiological data for earlier detection of graft-versus-host disease specifically. Throughout, we argue that increased collaboration across multiple fields is essential to realizing the full potential of wearable and biomarker data in a new paradigm of personalized and real-time medicine.