Improving Outcomes Through Personalized Recommendations in a Remote Diabetes Monitoring Program: Observational Study.

BACKGROUND: Diabetes management is complex, and program personalization has been identified to enhance engagement and clinical outcomes in diabetes management programs. However, 50% of individuals living with diabetes are unable to achieve glycemic control, presenting a gap in the delivery of self-management education and behavior change. Machine learning and recommender systems, which have been used within the health care setting, could be a feasible application for diabetes management programs to provide a personalized user experience and improve user engagement and outcomes. OBJECTIVE: This study aims to evaluate machine learning models using member-level engagements to predict improvement in estimated A1c and develop personalized action recommendations within a remote diabetes monitoring program to improve clinical outcomes. METHODS: A retrospective study of Livongo for Diabetes member engagement data was analyzed within five action categories (interacting with a coach, reading education content, self-monitoring blood glucose level, tracking physical activity, and monitoring nutrition) to build a member-level model to predict if a specific type and level of engagement could lead to improved estimated A1c for members with type 2 diabetes. Engagement and improvement in estimated A1c can be correlated; therefore, the doubly robust learning method was used to model the heterogeneous treatment effect of action engagement on improvements in estimated A1c. RESULTS: The treatment effect was successfully computed within the five action categories on estimated A1c reduction for each member. Results show interaction with coaches and self-monitoring blood glucose levels were the actions that resulted in the highest average decrease in estimated A1c (1.7% and 1.4%, respectively) and were the most recommended actions for 54% of the population. However, these were found to not be the optimal interventions for all members; 46% of members were predicted to have better outcomes with one of the other three interventions. Members who engaged with their recommended actions had on average a 0.8% larger reduction in estimated A1c than those who did not engage in recommended actions within the first 3 months of the program. CONCLUSIONS: Personalized action recommendations using heterogeneous treatment effects to compute the impact of member actions can reduce estimated A1c and be a valuable tool for diabetes management programs in encouraging members toward actions to improve clinical outcomes.

Association of physical activity on blood glucose in individuals with type 2 diabetes.

Regular physical activity (PA) has been shown to improve glycemic control in persons with type 2 diabetes. This study aimed to investigate the impact of PA on blood glucose after controlling for medication use, demographics, and week of activation using a real-world population of individuals with type 2 diabetes. A longitudinal, retrospective study was performed evaluating weekly PA of Livongo members (N = 9,509), which analyzed fasting blood glucose (FBG), step counts, and daily active minutes. Linear mixed-effect modeling technique was used to investigate within member and between member effects of input variables on average weekly FBG. Of members enrolled, 6,336 (32%) had self-reported body mass index, qualified week with diabetes medications, and FBG measures. Members' baseline average age was 49.4 (SD 10.1) years old, 43% female, and 45,496 member weeks with an average of 7.2 qualified weeks (PA observable in ≥4 days) per member. Average weekly FBG was 140.5 mg/dL (SD 39.8), and average daily step counts were 4,833 (SD 3,266). Moving from sedentary (<5,000 steps per day) to active (≥5,000 steps per day) resulted in mean weekly FBG reduction of 13 mg/dL (95% CI: -22.6 to -3.14). One additional day of ≥8,000 steps reduced mean weekly FBG by 0.47 mg/dL (95% CI: -0.77 to -0.16). Members who completed 30 min of moderate to vigorous PA above the population average reduced mean weekly FBG by 7.7 mg/dL (95% CI: -13.4 to -2.0). PA is associated with a mean weekly FBG reduction of 13 mg/dL when changing from a sedentary to active lifestyle while participating in a remote diabetes monitoring program.

Change in BMI accurately predicted by social exposure to acquaintances.

Research has mostly focused on obesity and not on processes of BMI change more generally, although these may be key factors that lead to obesity. Studies have suggested that obesity is affected by social ties. However these studies used survey based data collection techniques that may be biased toward select only close friends and relatives. In this study, mobile phone sensing techniques were used to routinely capture social interaction data in an undergraduate dorm. By automating the capture of social interaction data, the limitations of self-reported social exposure data are avoided. This study attempts to understand and develop a model that best describes the change in BMI using social interaction data. We evaluated a cohort of 42 college students in a co-located university dorm, automatically captured via mobile phones and survey based health-related information. We determined the most predictive variables for change in BMI using the least absolute shrinkage and selection operator (LASSO) method. The selected variables, with gender, healthy diet category, and ability to manage stress, were used to build multiple linear regression models that estimate the effect of exposure and individual factors on change in BMI. We identified the best model using Akaike Information Criterion (AIC) and R(2). This study found a model that explains 68% (p<0.0001) of the variation in change in BMI. The model combined social interaction data, especially from acquaintances, and personal health-related information to explain change in BMI. This is the first study taking into account both interactions with different levels of social interaction and personal health-related information. Social interactions with acquaintances accounted for more than half the variation in change in BMI. This suggests the importance of not only individual health information but also the significance of social interactions with people we are exposed to, even people we may not consider as close friends.

Time-critical social mobilization.

The World Wide Web is commonly seen as a platform that can harness the collective abilities of large numbers of people to accomplish tasks with unprecedented speed, accuracy, and scale. To explore the Web's ability for social mobilization, the Defense Advanced Research Projects Agency (DARPA) held the DARPA Network Challenge, in which competing teams were asked to locate 10 red weather balloons placed at locations around the continental United States. Using a recursive incentive mechanism that both spread information about the task and incentivized individuals to act, our team was able to find all 10 balloons in less than 9 hours, thus winning the Challenge. We analyzed the theoretical and practical properties of this mechanism and compared it with other approaches.