Identifying Real-Time Data Predictors of Stress and Depression Using Mobile Technology

Research Overview

One robust finding in depression research is that life stress is the single most important trigger of depressive episodes. Understanding how life stress leads to depression has the potential to transform our ability to prevent and treat depression. Unfortunately, the capacity to capture the effects of stress accurately and in real-time has been limited because assessments of psychiatric phenotypes has traditionally relied on patients’ self-report of symptoms. Mobile electronic technology holds great promise in overcoming these limitations by capturing continuous, real-time, passive measures likely to be related to the progression from stress to depression. Dr. Sen’s research has demonstrated that the onset of stress and depression can be prospectively predicted in a large group of individuals: medical interns. Medical internship, the first year of professional medical training, is characterized by long work hours, emotionally difficult situations and inconsistent and insufficient sleep. Internship is a rare situation whereby the onset of a major, uniform stressor and a dramatic increase in depressive symptoms can be accurately predicted.

In this project, the research team will determine the dynamic relationships between mood, sleep, and circadian rhythms, and develop a micro-randomized intervention trial for depression under stress using an app platform that integrates mobile phones signals and wearable data. The team will build personalized models of sleep, circadian rhythms, physical activity, and mood, and assess and optimize the efficacy of objective mobile sensor to detect depression onset.  The researchers believe that when real-time data on an individual is fit to the right mathematical model, simple and insightful information can be easily communicated back to the end user as well as their caregiver and/or domain expert.  The clinical aim, therefore, is to allow individuals at risk to be identified early and provided the right treatment at the right time, and empower the individuals to manage health and remain engaged with the mobile health technology.

The impact of this project goes beyond depression.  Advanced tools and models with large-scale computing power and data integration capacity are critical in studying physiology, psychosocial behavior and environment in real-time, and their role in defining risk for mental illness.  The research team’s multi-disciplinary approach in analyzing real-time, multi-modal mobile data can be generalized to the prediction of onset and preventive treatment of many other diseases.

Research Impact

Research Team

Srijan Sen, Principal Investigator, Associate Professor, Department of Psychiatry and Molecular and Behavioral Neuroscience Institute
Margit Burmeister, Professor, Departments of Computational Medicine and Bioinformatics, Human Genetics, Psychiatry and Molecular and Behavioral Neuroscience Institute
Olivia Walch, postdoctoral fellow, Department of Neurology
Daniel Forger, Professor, Departments of Mathematics and Computational Medicine and Bioinformatics
Ambuj Tewari, Associate Professor, Department of Statistics, and Department of Electrical Engineering and Computer Science
Zhenke Wu, Assistant Professor, Department of Biostatistics and Michigan Institute for Data Science