IMPORTANCE Emerging evidence suggests that postprandial glycemic responses (PPGRs) to food may be influenced by and predicted according to characteristics unique to each individual, including anthropometric and microbiome variables. Interindividual diversity in PPGRs to food requires a personalized approach for the maintenance of healthy glycemic levels. OBJECTIVES To describe and predict the glycemic responses of individuals to a diverse array of foods using a model that considers the physiology and microbiome of the individual in addition to the characteristics of the foods consumed. DESIGN, SETTING, AND PARTICIPANTS This cohort study using a personalized predictive model enrolled 327 individuals without diabetes from October 11, 2016, to December 13, 2017, in Minnesota and Florida to be part of a study lasting 6 days. The study measured anthropometric variables, described the gut microbial composition, and assessed blood glucose levels every 5 minutes using a continuous glucose monitor. Participants logged their food and activity information for the duration of the study. A predictive model of individualized PPGRs to a diverse array of foods was trained and applied. MAIN OUTCOMES AND MEASURES Glycemic responses to food consumed over 6 days for each participant. The predictive model of personalized PPGRs considered individual features, including the microbiome, in addition to the features of the foods consumed. RESULTS Postprandial response to the same foods varied across 327 individuals (mean [SD] age, 45 [12] years; 78.0% female). A model predicting each individual's responses to food that considers several individual factors in addition to food features had better overall performance (R = 0.62) than current standard-of-care approaches using nutritional content alone (R = 0.34 for calories and R = 0.40 for carbohydrates) to control postprandial glycemic levels. CONCLUSIONS AND RELEVANCE Across the cohort of adults without diabetes who were examined, a personalized predictive model that considers unique features of the individual, such as clinical characteristics, physiological variables, and the microbiome, in addition to nutrient content was more predictive than current dietary approaches that focus only on the calorie or carbohydrate content of foods. Providing individuals with tools to manage their glycemic responses to food based on personalized predictions of their PPGRs may allow them to maintain their blood glucose levels within limits associated with good health.

Background Controlled glycemic concentrations are associated with a lower risk of conditions such as cardiovascular disease and diabetes. Models commonly used to guide interventions to control the glycemic response to food have low efficacy, with recent clinical guidelines arguing for the use of personalized approaches. Objective We tested the efficacy of a predictive model of personalized postprandial glycemic response to foods that was developed with an Israeli cohort and that takes into consideration food components and specific features, including the microbiome, when applied to individuals from the Midwestern US. Design We recruited 327 individuals for this study. Participants provided information regarding lifestyle, dietary habits, and health, as well as a stool sample for characterization of their gut microbiome. Participants were connected to continuous glucose monitors for 6 d, and the glycemic response to meals logged during this time was computed. The ability of a model trained using meals logged by the Israeli cohort to correctly predict glycemic responses in the Midwestern cohort was assessed and compared with that of a model trained using meals logged by both cohorts. Results When trained on the Israeli cohort meals only, model performance for predicting responses of individuals in the Midwestern cohort was better (R = 0.596) than that observed for models taking into consideration the carbohydrate (R = 0.395) or calorie content of the meals alone (R = 0.336). Performance increased (R = 0.618) when the model was trained on meals from both cohorts, likely because of the observed differences in age distribution, diet, and microbiome. Conclusions We show that the modeling framework described in Zeevi et al. for an Israeli cohort is applicable to a Midwestern population, and outperforms commonly used approaches for the control of blood glucose responses. The adaptation of the model to the Midwestern cohort further enhances performance and is a promising means for designing effective nutritional interventions to control glycemic responses to foods. This trial was registered at clinicaltrials.gov as NCT02945514.

No abstract

HbA1c% is the most commonly used metric for assessing glycemic status, but only represents an averaged, indirect measure. Continuous Glucose Monitors (CGM) provides additional, elaborated assessment metrics. A recent study, [Zeevi et al., 2015, Cell ] showed that glycemic responses to foods vary across individuals and can be predicted using a machine learning framework. Moreover, it showed that personally tailored diets based on this framework improves Postprandial Glycemic Response (PPGR) in one-week interventions. Here, we tested the ability of such framework to improve longer term measures of glycemic control. A cohort of 28 diabetic individuals, not using short term insulin, were tracked. Each participant was tested for initial HbA1c, and connected to a CGM for a period of 14 days. Then, participant's anthropometrics, lifestyle, clinical parameters, and gut microbiome composition, were fed into a machine learning algorithm built into a personalized mobile application. Using the application, participants could define meals by combining foods, and obtain instant scores indicating the predicted PPGR for each meal. Participants were instructed to limit consumption to highly scoring meals. After 4-20 months of using the application, participants were re-connected to CGM, and HbA1c% levels were measured again. Results: Significant improvements in multiple endpoints: Average HbA1c% dropped from 7.2% to 6.5% (p-value: 1.2e-8). Average %time-in-range [70,140] mg/dl increased from 69.1% to 79.6% (p-value: 0.005). Average %time-in-range [70,180] mg/dl increased from 89.6% to 94.2% (p-value: 0.002). Mean glucose levels decreased from 125.6 mg/dl to 114.6 mg/dl (p-value: 0.0002). These observations, coupled with the short-term benefits shown in recent work, imply that drugless, personalized, nutrition-based interventions, may be key to achieving significant improvements in glycemic control of type 2 diabetic patients. Disclosure Y. Ben Shlomo: Employee; Self; DayTwo. S. Azulay: Employee; Self; DayTwo. T. Raveh-Sadka: Employee; Self; DayTwo. Y. Cohen: Employee; Self; DayTwo. A. Hanemann: Employee; Self; DayTwo.