In this project, we will develop and evaluate a novel approach to tailoring behavioral interventions for problem-solving in diabetes self-management to individuals' behavioral and glycemic profiles discovered using computational learning and self-monitoring data. Growing evidence suggests significant differences in individuals' physiology and glycemic function, and their cultural, social, and economical circumstances that impact diabetes self-management. These discoveries highlight the benefits of tailoring of both medical treatment and behavioral interventions to individuals' pathophysiology, psycho-social characteristics, and daily behaviors. Yet such tailoring typically relies on expert identification of tailoring variables and decision rules, and on standard surveys for assessment of tailoring variables. Data collected with self- monitoring can more accurately reflect an individual's behaviors and glycemic patterns, thus highlighting their ?behavioral phenotypes?, yet such data are rarely utilized in tailoring. The ongoing focus of this research is on facilitating problem-solving in diabetes self-management. Previous research suggested problem identification and generation of alternatives as critical steps in problem-solving in diabetes. In our previous work, we developed an informatics intervention that relied on expert-generated knowledge for providing assistance on these steps of problem-solving. In the proposed research we will investigate an alternative solution that relies on computational pattern analysis of data collected with self monitoring technologies to tailor the problem-solving assistance to individuals' unique behavioral phenotypes. Our new intervention, GlucoType uses computational methods to identify systematic patterns in individuals' diet, physical activity, and sleep, captured with custom-built and commercial self- monitoring technologies, and correlate these patterns with fluctuations in individuals' blood glucose levels. GlucoType then uses this information to 1) reinforce behaviors with positive glycemic impact from an individual's own experience (for example, exercising before breakfast, or including lean protein for dinner), and 2) suggest new combinations of activities by comparing patterns across individuals. We will evaluate the effectiveness of GlucoType in a Cluster-Randomized Controlled Trial (cRCT) with individuals recruited from Federally Qualified Community Health Centers in NYC.
The proposed HIT solution will be designed to help individuals with diabetes improve their problem-solving abilities, develop better self-case behaviors and improve their health. As such, this project has a high potential public health impact.
