Search

Health coaching is a promising approach to support self-management of chronic conditions like type 2 diabetes; however, there aren’t enough coaching practitioners to support those in need. Advances in Artificial Intelligence (AI) and Machine Learning (ML) have the potential to enable innovative, automated health coaching interventions, but important gaps remain in applying AI and ML to coaching interventions. This thesis aims to identify computational approaches and interactive technologies that enable automated health coaching systems. First, I utilized computational approaches that leverage individuals’ self-tracking and health data and used an expert system to translate ML inferences into personalized nutrition goal recommendations. The system, GlucoGoalie, was evaluated in multiple studies including a 4-week deployment study which demonstrated the feasibility of the approach. Second, I compared human-powered and automated/chatbot approaches to health coaching in a 3-week study which found that t2.coach — a scripted, theoretically-grounded chatbot designed through an iterative, user-centered process — cultivated a coach-like experience that had many similarities to the experience of messaging with actual health coaches, and outlined directions for automated, conversational coaching interventions. Third, I examined multiple AI approaches to enable micro-coaching dialogs — brief coaching conversations related to specific meals, to support achievement of nutrition goals — including a knowledge-based system for natural language understanding, and a data-driven, reinforcement learning approach for dialog management. Together, the results of these studies contribute methods and insights that take steps towards more intelligent conversational coaching systems, with resonance to research in informatics, human-computer interaction, and health coaching.

Type 2 diabetes leads to premature death and reduced quality of life for 8% of Americans. Nutrition management is critical to maintaining glycemic control, yet it is difficult to achieve due to the high individual differences in glycemic response to nutrition. Anticipating glycemic impact of different meals can be challenging not only for individuals with diabetes, but also for expert diabetes educators. Personalized computational models that can accurately forecast an impact of a given meal on an individual’s blood glucose levels can serve as the engine for a new generation of decision support tools for individuals with diabetes. However, to be useful in practice, these computational engines need to generate accurate forecasts based on limited datasets consistent with typical self-monitoring practices of individuals with type 2 diabetes. This paper uses three forecasting machines: (i) data assimilation, a technique borrowed from atmospheric physics and engineering that uses Bayesian modeling to infuse data with human knowledge represented in a mechanistic model, to generate real-time, personalized, adaptable glucose forecasts; (ii) model averaging of data assimilation output; and (iii) dynamical Gaussian process model regression. The proposed data assimilation machine, the primary focus of the paper, uses a modified dual unscented Kalman filter to estimate states and parameters, personalizing the mechanistic models. Model selection is used to make a personalized model selection for the individual and their measurement characteristics. The data assimilation forecasts are empirically evaluated against actual postprandial glucose measurements captured by individuals with type 2 diabetes, and against predictions generated by experienced diabetes educators after reviewing a set of historical nutritional records and glucose measurements for the same individual. The evaluation suggests that the data assimilation forecasts compare well with specific glucose measurements and match or exceed in accuracy expert forecasts. We conclude by examining ways to present predictions as forecast-derived range quantities and evaluate the comparative advantages of these ranges., Author summary Type 2 diabetes is a devastating disease that requires constant patient self-management of glucose, insulin, nutrition and exercise. Nevertheless, glucose and insulin dynamics are complicated, nonstationary, nonlinear, and individual-dependent, making self-management of diabetes a complex task. To help alleviate some of the difficulty for patients, we develop a method for personalized, real-time, glucose forecasting based on nutrition. Specifically, we create and evaluate the computational machinery based on both Gaussian process models and data assimilation that leverages the physiologic knowledge of two mechanistic models to produce a personalized, nutrition-based glucose forecast for individuals with type 2 diabetes in real time that is robust to sparse data and nonstationary patients. Our computational engine was conceived to be of potential use for diabetes self-management.