Use of Machine Learning to Identify Determinants of Habitual-Preformed Water Intake

Emma J. Stinson is a Statistician at the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) in Phoenix, Arizona, and is currently pursuing a PhD in Biomedical Informatics and Data Science at Arizona State University. Her research focuses on the development and application of statistical and data-driven methods to study metabolic health, with an emphasis on energy intake and energy expenditure. She is the lead author of a recent Journal of Nutrition publication from the CALERIE study using machine learning to identify determinants of habitual preformed water intake. Her findings showed that data-driven machine learning models can identify novel dietary and physiological factors associated with habitual preformed water intake, relationships that may be missed using traditional statistical approaches, contributing to a deeper understanding of hydration and metabolic health.

The Journal of Nutrition

05/01/2026

Authors: Emma J Stinson, Ethan Collins, Tomas Cabeza De Baca, Marci E Gluck, Manuel Dote-Montero, Susan B Racette, Stavros A Kavouras, Sai Krupa Das, Paolo Piaggi, Susanne Votruba, Ashley Hale, Douglas C Chang