American Diabetes Association
Revised_PPGR_Supplementary_Figures_and_Tables_Clean.pdf (523.66 kB)

Prediction of Personal Glycemic Responses to Food for Individuals With Type 1 Diabetes Through Integration of Clinical and Microbial Data

Download (523.66 kB)
posted on 2021-10-28, 22:32 authored by Smadar Shilo, Anastasia Godneva, Marianna Rachmiel, Tal Korem, Dmitry Kolobkov, Tal Karady, Noam Bar, Bat Chen Wolf, Yitav Glantz-Gashai, Michal Cohen, Nehama Zuckerman Levin, Naim Shehadeh, Noah Gruber, Neriya Levran, Shlomit Koren, Adina Weinberger, Orit Pinhas-Hamiel, Eran Segal
OBJECTIVE Despite technological advances, results from various clinical trials repeatedly showed that many individuals with type 1 diabetes (T1D) do not achieve their glycemic goals. One of the major challenges in disease management is the administration of an accurate amount of insulin for each meal which will match the expected postprandial glycemic response (PPGR).

RESEARCH DESIGN AND METHODS We recruited individuals with T1D using continuous glucose monitoring (CGM) and continuous subcutaneous insulin infusion (CSII) devices simultaneously to a prospective cohort and profiled them for 2 weeks. Participants were asked to report real-time dietary intake using a designated mobile app. We measured their PPGRs and devised machine-learning algorithms for PPGR prediction, which integrate glucose measurements, insulin dosages, dietary habits, blood parameters, anthropometrics, exercise, and gut microbiota. Data of the PPGR of 1,057 healthy individuals to 47,863 meals were also integrated into the model. The performance of the models was evaluated using 10-fold cross validation.

RESULTS 121 individuals with T1D, 75 adults and 46 children, were included in the study. PPGR to 6,377 meals was measured. Our PPGR prediction model substantially outperforms a baseline model emulating standard of care (correlation of R=0.59 compared to R=0.40 for predicted and observed PPGR respectively, p <10−10). The model was robust across different subpopulations. Feature attribution analysis revealed that glucose levels at meal initiation, glucose trend 30 minutes prior to meal, meal carbohydrate content and meal’s carbohydrate/fat ratio were the most influential features to the model.

CONCLUSIONS Our model enables a more accurate prediction of PPGR and therefore may allow a better adjustment of the required insulin dosage for meals. It can be further implemented in closed-loop systems and may lead to rationally designed nutritional interventions personally tailored for individuals with T1D based on meals with expected low glycemic response.


This work is supported by the The Israel Science Foundation (ISF) (grant no. 3-14762). E.S. is supported by the Crown Human Genome Center; Larson Charitable Foundation New Scientist Fund; Else Kroener Fresenius Foundation; White Rose International Foundation; Ben B. and Joyce E. Eisenberg Foundation; Nissenbaum Family; Marcos Pinheiro de Andrade and Vanessa Buchheim; Lady Michelle Michels; Aliza Moussaieff; and grants funded by the Minerva foundation with funding from the Federal German Ministry for Education and Research and by the European Research Council and the Israel Science Foundation. These funding sources had no role in the design of this study and will not have any role during its execution, analyses, interpretation of the data, or decision to submit results.


Usage metrics

    Diabetes Care


    Ref. manager