DIAMANTE

DIAMANTE

Enhancing diabetes and depression self­-management via adaptive mobile messaging

The main aim of “Diabetes and Mental Health Adaptive Notification Tracking and Evaluation” (DIAMANTE) was to test a smartphone intervention that generates adaptive messaging, learning from daily patient data to personalize the timing and type of text-messages. We compared the adaptive content to 1. a uniform random messaging intervention, in which the messaging content and timing will be delivered with equal probabilities (i.e. not adapted by a learning algorithm), and 2. a control condition that only delivers a weekly mood message. 

By targeting both diabetes and depression, our research will lead to services that are responsive to the realities of these comorbid disorders and will likely have greater impact than interventions that focus only on one disease or the other.

We used user-centered design (UCD) methods to iteratively develop the DIAMANTE content and text messaging system through three iterative phases of UCD with ten patients each (total n=30). The first phase consisted of 1.5-hour individual semi-structured interviews. Findings from phase 1 were used to inform content and information delivery decisions of the final intervention, including selecting the thematic message categories and the design. In the second phase, patients tested out an early prototype of the mobile application through usability testing. Patients tested the final DIAMANTE intervention including thematic message content and the application in the third, final UCD phase, in order to address any user-related issues prior to launching the randomized control trial.

In the DIAMANTE Randomized Controlled Trial, we aimed to examine the effect of a smartphone app that uses reinforcement learning to predict the most effective messages for increasing physical activity. We recruited 276 low-income minority patients with depression and diabetes within the San Francisco Health Network, and compared this intervention to static messages with health management content, and a control group that only receives a weekly mood message.

Team

Principal Investigators

• Adrian Aguilera, Ph.D.
  • Associate Professor
    • University of California, Berkeley
    • University of California, San Francisco, Psychiatry
• Courtney Lyles, Ph.D.
  • Director, Center for Healthcare Research and Policy, University of California, Davis
  • Associate Professor, University of California, San Francisco

Post-Doctoral Scholars

• Marvyn Arévalo Avalos, Ph.D.
  • University of California, Berkeley

Graduate Students

• Laura Elizabeth Pathak, MSW

Staff

• Faviola Garcia, B.A.
• Karina Rosales, B.A.
• Rosa Hernandez Ramos, B.A.
• Jose Miramontes, B.A.
• Anu Cemballi, B.A.

Research Assistants

• Vivian Yip, B.A.
• Suchitra Sudarshan, B.A.
• Alexander Chavarria, B.A.
• Cindy Tenorio, B.A.
• Jiayin Lin

Special thanks to:

• Chris Karr
  • Owner, Audatious Software