The purpose of this proposal is develop, and bring to fruition, methods for using data to optimize mobile interventions aimed at preventing, treating and supporting the recovery from alcohol use disorders. Social and personal costs of alcohol use disorders in the US are very high, yet relatively few Americans with alcohol use disorders receive treatment. Interventions delivered via mobile devices, such as smartphones, can increase the availability and decrease the cost of both preventing, treating and providing support for individuals in recovery. At this time data has seen little use in optimizing the timing and selection of behavioral interventions that can be delivered via mobile devices. The goal of this project is (1) to develop and evaluate data analysis methods and optimization algorithms that can reside on the mobile device and that, as an individual experiences the mobile intervention and provides responses, will optimize the timing and selection of the behavioral intervention to the individual; (2) to develop data analysis methods and optimization algorithms that can be used following a clinical study involving the mobile intervention to further optimize the intervention; and (3) to disseminate and illustrate the developed methods and algorithms to the clinical science community so as to maximize clinical impact. We propose to conduct the technical development of the data analysis methods/algorithms and to test and refine the developments in a virtual environment using simulators that mimic the data from three different clinical studies involving prevention, treatment and recovery from alcohol use disorders. We will collaborate with clinical scientists on tutorials for these methods as well as disseminate the data analysis methods by conducting symposia and workshops. We will develop initial versions of the data analysis/algorithm software and make the software freely accessible.

Public Health Relevance

The proposed research involves the development and evaluation of data analysis methods that can be used to optimize the selection of interventions as well as the timing of the delivery of the interventions via mobile devices such as smartphones. The goal of these methods is to facilitate improvements in the ability of individuals to combat their problematic excessive drinking and to recover from such drinking behavior. The research team, from the University of Michigan and North Carolina State University, includes experts in statistical methods for using data to optimize treatment sequences (Susan Murphy, Ph.D. and Eric Laber, Ph.D.), experts in computer science methods for using real time data to optimize treatment sequences (Ambuj Tewari, Ph.D.) and in coping, health behavior change and alcohol use (Inbal Nahum-Shani, Ph.D.).

Agency
National Institute of Health (NIH)
Institute
National Institute on Alcohol Abuse and Alcoholism (NIAAA)
Type
Research Project (R01)
Project #
7R01AA023187-03
Application #
9515100
Study Section
National Institute on Alcohol Abuse and Alcoholism Initial Review Group (AA)
Program Officer
Hagman, Brett Thomas
Project Start
2015-09-01
Project End
2020-08-31
Budget Start
2017-09-01
Budget End
2018-08-31
Support Year
3
Fiscal Year
2017
Total Cost
Indirect Cost
Name
Harvard University
Department
Biostatistics & Other Math Sci
Type
Schools of Arts and Sciences
DUNS #
082359691
City
Cambridge
State
MA
Country
United States
Zip Code
02138
Greenewald, Kristjan; Tewari, Ambuj; Klasnja, Predrag et al. (2017) Action Centered Contextual Bandits. Adv Neural Inf Process Syst 30:5973-5981
Bekiroglu, Korkut; Lagoa, Constantino; Murphy, Suzan A et al. (2017) Control Engineering Methods for the Design of Robust Behavioral Treatments. IEEE Trans Control Syst Technol 25:979-990
Guan, Qian; Laber, Eric B; Reich, Brian J (2016) Comment. J Am Stat Assoc 111:936-942
Lizotte, Daniel J; Laber, Eric B (2016) Multi-Objective Markov Decision Processes for Data-Driven Decision Support. J Mach Learn Res 17:
Laber, Eric B; Zhao, Ying-Qi; Regh, Todd et al. (2016) Using pilot data to size a two-arm randomized trial to find a nearly optimal personalized treatment strategy. Stat Med 35:1245-56
Liao, Peng; Klasnja, Predrag; Tewari, Ambuj et al. (2016) Sample size calculations for micro-randomized trials in mHealth. Stat Med 35:1944-71
Pelham Jr, William E; Fabiano, Gregory A; Waxmonsky, James G et al. (2016) Treatment Sequencing for Childhood ADHD: A Multiple-Randomization Study of Adaptive Medication and Behavioral Interventions. J Clin Child Adolesc Psychol 45:396-415
Lu, Xi; Nahum-Shani, Inbal; Kasari, Connie et al. (2016) Comparing dynamic treatment regimes using repeated-measures outcomes: modeling considerations in SMART studies. Stat Med 35:1595-615
Almirall, Daniel; DiStefano, Charlotte; Chang, Ya-Chih et al. (2016) Longitudinal Effects of Adaptive Interventions With a Speech-Generating Device in Minimally Verbal Children With ASD. J Clin Child Adolesc Psychol 45:442-56
Nahum-Shani, Inbal; Smith, Shawna N; Spring, Bonnie J et al. (2016) Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support. Ann Behav Med :

Showing the most recent 10 out of 17 publications