Clinical trial / 2015
A machine-learning algorithm predicted personalized postprandial glycemic responses to meals.
Researchers monitored continuous glucose across 46,898 meals in an 800-person cohort and observed high variability in responses to identical foods. A machine-learning model integrating clinical parameters, diet, anthropometrics, physical activity, and gut microbiota predicted personalized glycemic responses, which was validated in 100 participants. A blinded randomized dietary intervention guided by the algorithm significantly reduced postprandial glycemic responses and altered gut microbiota composition.
- Study type
- Prospective cohort and randomized controlled trial
- Who was studied
- 800 adults, with 100-person validation cohort
- What was measured
- Postprandial glycemic response and gut microbiota configuration
THE PAPER
Personalized Nutrition by Prediction of Glycemic Responses.
Zeevi D, Korem T, Zmora N, Israeli D, Rothschild D, Weinberger A, Ben-Yacov O, Lador D, Avnit-Sagi T, Lotan-Pompan M, Suez J, Mahdi JA, Matot E, Malka G, Kosower N, Rein M, Zilberman-Schapira G, Dohnalová L, Pevsner-Fischer M, Bikovsky R, Halpern Z, Elinav E, Segal E. Cell, 2015.
This note is written from the study's published abstract. It summarizes what the authors reported; it is not medical advice and does not replace reading the full paper.