Rapid advances in technology, are leading to field-deployable mobile sensing devices that can now be used to quantify the complex dynamics across time of key physical, biological, behavioral, social, and environmental factors that contribute to health and disease risk. These data will enable us to break through to the next level of biomedical understanding of causation in complex disorders. While ongoing efforts have made significant strides in the analysis of big data in the areas of genomics, imaging, and EHR, significant new investment is needed to develop and disseminate data analytics tools specific to the unique features of mobile sensor data (e.g., high volume, velocity, variety, variability, and versatility) to convert this wealth of data into information, knowledge, and action. Investment in a strong, open, scientific, and computational infrastructure for mobile big data at this early stage promises outsize returns to advance science and improve health. The Data Science Research (DSR) Core of the Center of Excellence for Mobile Sensor Data to Knowledge (MD2K) will generate generalizable theory, methods, tools, and software, to address major barriers to processing complex mobile sensor data (e.g., transition from early lab feasibility to robust field utility) so as to enable the use of mobile sensor data by the broader community for biomedical knowledge discovery and just-in-time care delivery, laying the foundation for P5 Medicine. The DSR Core will demonstrate the feasibility, utility, and generalizability of the MD2K approach by implementing the entire MD2K data analytics system in the context of two biomedical applications - reducing relapse among abstinent daily smokers and reducing readmission among congestive heart failure (CHF) patients. All the tools and software developed by MD2K will be freely available as open-source projects to engage data science researchers in advancing the science of MD2K. Biomedical researchers will be able to install the MD2K software on mobile devices to collect mobile sensor data and the MD2K analytics software on their servers to analyze these data for biomedical discovery.

Public Health Relevance

By enabling the use of mobile sensor data to detect and predict person-specific disease risk factors ahead of the onset of adverse clinical events, this project will make it possible to intervene anytime, anywhere, to anticipate and prevent disease complications at the earliest timepoint, ultimately supporting wellness. These tools, made freely available, will reduce the burden of complex chronic disorders on health and healthcare.

National Institute of Health (NIH)
National Institute of Biomedical Imaging and Bioengineering (NIBIB)
Specialized Center--Cooperative Agreements (U54)
Project #
Application #
Study Section
Special Emphasis Panel (ZRG1)
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
University of Memphis
United States
Zip Code
Nahum-Shani, Inbal; Smith, Shawna N; Spring, Bonnie J et al. (2018) Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support. Ann Behav Med 52:446-462
Walton, Ashley; Nahum-Shani, Inbal; Crosby, Lori et al. (2018) Optimizing Digital Integrated Care via Micro-Randomized Trials. Clin Pharmacol Ther 104:53-58
Bari, Rummana; Adams, Roy J; Rahman, Mahbubur et al. (2018) rConverse: Moment by Moment Conversation Detection Using a Mobile Respiration Sensor. Proc ACM Interact Mob Wearable Ubiquitous Technol 2:
Almirall, Daniel; Kasari, Connie; McCaffrey, Daniel F et al. (2018) Developing Optimized Adaptive Interventions in Education. J Res Educ Eff 11:27-34
Polack Jr, Peter J; Chen, Shang-Tse; Kahng, Minsuk et al. (2018) Chronodes: Interactive Multifocus Exploration of Event Sequences. ACM Trans Interact Intell Syst 8:
Boruvka, Audrey; Almirall, Daniel; Witkiewitz, Katie et al. (2018) Assessing Time-Varying Causal Effect Moderation in Mobile Health. J Am Stat Assoc 113:1112-1121
Crane, Harry; Dempsey, Walter (2018) EDGE EXCHANGEABLE MODELS FOR INTERACTION NETWORKS. J Am Stat Assoc 113:1311-1326
Rabbi, Mashfiqui; Philyaw Kotov, Meredith; Cunningham, Rebecca et al. (2018) Toward Increasing Engagement in Substance Use Data Collection: Development of the Substance Abuse Research Assistant App and Protocol for a Microrandomized Trial Using Adolescents and Emerging Adults. JMIR Res Protoc 7:e166
Klasnja, Predrag; Smith, Shawna; Seewald, Nicholas J et al. (2018) Efficacy of Contextually Tailored Suggestions for Physical Activity: A Micro-randomized Optimization Trial of HeartSteps. Ann Behav Med :
Dempsey, Walter; McCullagh, Peter (2018) Survival models and health sequences. Lifetime Data Anal 24:550-584

Showing the most recent 10 out of 108 publications