Human-Computer Interaction Institute Thesis Defense
- Remote Access - Zoom
- Virtual Presentation - ET
- JULIAN RAMOS
- Ph.D. Student
- Human-Computer Interaction Institute
- Carnegie Mellon University
Exploring AI-based personalization of a mobile health intervention and its effects on behavior change, motivation, and adherence
Medical treatments are traditionally personalized in a manual process by healthcare practitioners. Personalization starts with a one-size-fits-all treatment, then is adjusted for each patient in a lengthy trial and error process. This process can result in unnecessary treatment, exposure to side effects, and patient loss of interest due to treatment ineffectiveness. Mobile health (mHealth) researchers have investigated ways to decrease ineffective treatment exposure by personalizing health interventions using Artificial Intelligence (AI). AI methods like contextual-bandits have been used for personalizing content with promising results. However, content personalization approaches alone are under-powered by lacking personalization of time of treatment: an active component that delivers health advice in the form of alerts or reminders at appropriate times (e.g., time, location, and activity). State of the art work has shown that reminders alone can increase adherence to treatment but have not resulted in behavior change yet.
In this thesis, I developed and tested a method for personalizing mobile health interventions' content and timing of treatment. I tested this approach in a real-world deployment (n=30, spring 2019) of a behavioral sleep intervention. I found that this personalization approach improved sleep duration, motivation to improve sleep-related behaviors, and adherence to sleep advice. I discovered that contextual factors and participant intrinsic characteristics have a significant effect on adherence to treatment. Building on these results, I implemented a machine learning classifier that predicts next-day adherence to treatment with promising performance.
Following up on these promising results, I deployed a larger (n=80) sleep intervention only days before the beginning of the 2020 pandemic to further investigate the marginal effects of personalization of content and treatment timing. This intervention did not result in behavior change. After further investigation, I found that decreased motivation towards sleep improvement, change in the way participants interacted with their phones, among other pandemic induced effects, led to a null result. In this part of my thesis, I investigate this 2020 deployment and the specific causes of the null intervention results. I compare the behaviors of the participants in the 2020 and 2019 studies using behavioral logs, phone usage and sensor streams and surveys. I found that a lack of motivation caused by anxiety and stress induced by the pandemic, and a drastic change in phone use and daily routines were the most likely reasons for the null intervention results.
In summary, this thesis contributes 1) A method for the simultaneous personalization of content and timing of treatment using AI, sensors, and human feedback and its evaluation in a real-world deployment, 2) A deployment and test of the system using the aforementioned methods, 3) Findings on contributing factors that change adherence to treatment in the context of a behavioral intervention, 4) A machine learning classifier for the prediction of next-day adherence and 5) An investigation of the contributing factors that lead to null results in a second deployment during a pandemic.
Anind Dey (Chair, University of Washington)
Mayank Goel (Co-chair, Carnegie Mellon University)
Carissa Low (University of Pittsburgh)
Tanzeem Choudhur (Cornell University)
Robert Kraut (Carnegie Mellon University)
Zoom Participation. See announcement.