Mood disorders are among the leading causes of morbidity and mortality worldwide, and have a profound impact on quality of life and productivity for millions of people. A longstanding barrier to progress, both in the context of clinical setting and drug trials has been the fundamental difficulty of accurately measuring mood states, behaviors, and social functioning of individuals affected by mood disorders. Mobile phones have become an integral part of modern life, and our prior work has shown that they can be used to collect behavioral and social network data at very large scales. Using existing open-source software as a foundation, we will develop a smartphone application that functions as a digital self-report instrument and simultaneously, in an unobtrusive manner, collects passive data on both the behavior and communication patterns of subjects. Two cohorts, a group of psychiatric outpatients and a non-psychiatric control group, will install the application on their own phones, which enables us to collect four longitudinal streams of data over a two-year period. First, we will collect active data consisting of subjects'responses to questions, presented by the smartphone application, about their mood and well-being. Second, we will utilize built-in accelerometer and GPS devices to collect passive mobility and location data. Third, we will track how subjects use other applications on their smartphones. Fourth, we will employ anonymized call and text messaging logs to learn about the structure and dynamics of the phone-mediated social network of subjects. The main objective of this proposal is to develop new analytical tools and technology capable of integrating these four streams of data in order to create a set of novel behavioral metrics. These metrics, validated for the outpatient cohort using quarterly clinical evaluations, will provide low- cost, highly scalable tools for monitoring social functioning and behavioral patterns of participants. Such tools could profoundly improve clinical management of psychiatric illnesses, and expedite the development of new efficacious treatments. The project is innovative in the way it combines longitudinal active and passive data streams, collected unobtrusively on the smartphone, to study behavioral changes caused by mood disorders. The resulting smartphone software platform and the requisite data analytic tools will be openly shared with the scientific community, and subsequent studies will be able to leverage this platform at no cost. The PI has a strong track record of innovative, high impact multidisciplinary work and has published scientific articles in journals such as Science, PNAS, and JAMA;his work has been covered in Nature, Science, BBC News, and the New York Times, among others.

National Institute of Health (NIH)
National Institute of Mental Health (NIMH)
NIH Director’s New Innovator Awards (DP2)
Project #
Application #
Study Section
Special Emphasis Panel (ZRG1-MOSS-C (56))
Program Officer
Chambers, David A
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
Harvard University
Biostatistics & Other Math Sci
Schools of Public Health
United States
Zip Code
Onnela, Jukka-Pekka; Rauch, Scott L (2016) Harnessing Smartphone-Based Digital Phenotyping to Enhance Behavioral and Mental Health. Neuropsychopharmacology 41:1691-6
Torous, John; Kiang, Mathew V; Lorme, Jeanette et al. (2016) New Tools for New Research in Psychiatry: A Scalable and Customizable Platform to Empower Data Driven Smartphone Research. JMIR Ment Health 3:e16
Torous, John; Staples, Patrick; Onnela, Jukka-Pekka (2015) Realizing the potential of mobile mental health: new methods for new data in psychiatry. Curr Psychiatry Rep 17:602
Torous, John; Staples, Patrick; Shanahan, Meghan et al. (2015) Utilizing a Personal Smartphone Custom App to Assess the Patient Health Questionnaire-9 (PHQ-9) Depressive Symptoms in Patients With Major Depressive Disorder. JMIR Ment Health 2:e8
Onnela, Jukka-Pekka; Waber, Benjamin N; Pentland, Alex et al. (2014) ERRATUM: Using sociometers to quantify social interaction patterns. Sci Rep 4:6278