Interventions currently rely on approvals and decision trees largely based on aggregate, static data that may or may not be relevant to an individual. Objective and subjective measures of health from smartphones and wearable devices could dramatically transform this top-down approach, to a ground-up, individual level approach that enables participants and patients as co-navigators. This talk will focus on the Stress and Recovery Study – a completed feasibility participant centric study that used digital tools to detect and track stress and mental health in frontline healthcare workers working with COVID-19 patients and new work in pregnancy and the mental health of students. New applications of machine learning approaches for the detection of stress events from objective and subjective data will be discussed and future upcoming studies of psychiatric patient populations applying similar methodologies.