Chronic mental illnesses such as major depression and schizophrenia impose a heavy burden both on the individual and society. High quality clinical care can reduce the burden but such care demands sequential clinical decision making concerning treatment. The long term goal of this project is to improve sequential clinical decision making.
The specific aims concern methodological approaches for helping clinicians address questions such as: How long should one wait to decide that a patient is not deriving sufficient benefit from treatment? If it is established that a patient is not sufficiently benefiting from treatment then which treatment should be provided next? Should the sequence of treatments vary according to patient characteristics and outcomes such as disease features, response, side effect burden, and adherence? In this project methods taken from computer science, engineering and statistics are generalized and adapted for use with clinical trial data so as to address these kinds of questions. The methods will be developed and validated using data from two large NIMH funded trials. This project will be conducted by a collaborative team involving a computer scientist, two psychiatrists and a statistician.

National Institute of Health (NIH)
National Institute of Mental Health (NIMH)
Research Project (R01)
Project #
Application #
Study Section
Mental Health Services in MH Specialty Settings (SRSP)
Program Officer
Rupp, Agnes
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
University of Michigan Ann Arbor
Biostatistics & Other Math Sci
Schools of Arts and Sciences
Ann Arbor
United States
Zip Code
Almirall, Daniel; Griffin, Beth Ann; McCaffrey, Daniel F et al. (2014) Time-varying effect moderation using the structural nested mean model: estimation using inverse-weighted regression with residuals. Stat Med 33:3466-87
Shortreed, Susan M; Laber, Eric; Scott Stroup, T et al. (2014) A multiple imputation strategy for sequential multiple assignment randomized trials. Stat Med 33:4202-14
Laber, Eric B; Lizotte, Daniel J; Qian, Min et al. (2014) Dynamic treatment regimes: technical challenges and applications. Electron J Stat 8:1225-1272
McKeague, Ian W; Qian, Min (2014) Estimation of treatment policies based on functional predictors. Stat Sin 24:1461-1485
Almirall, Daniel; McCaffrey, Daniel F; Ramchand, Rajeev et al. (2013) Subgroups analysis when treatment and moderators are time-varying. Prev Sci 14:169-78
Fonteneau, Raphael; Murphy, Susan A; Wehenkel, Louis et al. (2013) Batch Mode Reinforcement Learning based on the Synthesis of Artificial Trajectories. Ann Oper Res 208:383-416
Little, Roderick J; D'Agostino, Ralph; Cohen, Michael L et al. (2012) The prevention and treatment of missing data in clinical trials. N Engl J Med 367:1355-60
Almirall, Daniel; Lizotte, Daniel J; Murphy, Susan A (2012) SMART Design Issues and the Consideration of Opposing Outcomes: Discussion of ""Evaluation of Viable Dynamic Treatment Regimes in a Sequentially Randomized Trial of Advanced Prostate Cancer"" by by Wang, Rotnitzky, Lin, Millikan, and Thall. J Am Stat Assoc 107:509-512
Almirall, Daniel; Compton, Scott N; Rynn, Moira A et al. (2012) SMARTer discontinuation trial designs for developing an adaptive treatment strategy. J Child Adolesc Psychopharmacol 22:364-74
Nahum-Shani, Inbal; Qian, Min; Almirall, Daniel et al. (2012) Q-learning: a data analysis method for constructing adaptive interventions. Psychol Methods 17:478-94

Showing the most recent 10 out of 40 publications