top of page


The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial

Lauffenburger JC, Yom-Tov E, Keller PA, McDonnell ME, Crum KL, Bhatkhande G, Sears ES, Hanken K, Bessette LG, Fontanet CP, Haff N, Vine S, Choudhry NK

NPJ Digit Med

2024 February 19

Preferences for mHealth Technology and Text Messaging Communication in Patients With Type 2 Diabetes: Qualitative Interview Study

Lauffenburger JC, Barlev RA, Sears ES, Keller PA, McDonnel ME, Yom-Tov E, Fontanet CP, Hanken K, Haff N, Choudhry NK​

J Med Internet Res

2021 June

REinforcement learning to improve non-adherence for diabetes treatments by Optimising Response and Customising Engagement (REINFORCE): study protocol of a pragmatic randomised trial

Lauffenburger LC, Yum-Tov E, Keller PA, McDonnell ME, Bessette LG, Fontanet CP, Sears ES, Kim E, Hanken K, Buckley JJ, Barlev RA, Haff N, Choudhry NK

BMJ Open

2021 December 3

Text messaging has beneficial effects for promoting health behaviors like adherence to medication but has had modest impact, in part because message content has rarely been personalized. Reinforcement learning has been used in consumer technology to personalize content but has had limited application in health care. The REINFORCE trial was a preliminary efficacy trial conducted at Brigham and Women’s Hospital that sought to evaluate the impact of a reinforcement learning text messaging program that personalized text based upon an individual’s level of responsiveness. The intervention resulted in a non-significant improvement in adherence but had large and significant effects for individuals who, at baseline, were non-adherent or had moderately poor disease control. We anticipate that results will be published in the winter of 2024. NCT04473326

Co-Principal Investigators: Julie Lauffenburger, PharmD, PhD and Niteesh Choudhry, MD, PhD

bottom of page