Enabling Eating Detection in a Free-living Environment: Integrative Engineering and Machine Learning Study

• Published in: Journal of medical Internet research Vol. 24; no. 3; p. e27934
• Main Authors: Zhang, Bo, Deng, Kaiwen, Shen, Jie, Cai, Lingrui, Ratitch, Bohdana, Fu, Haoda, Guan, Yuanfang
• Format: Journal Article
• Language: English
• Published: Canada Journal of Medical Internet Research 01-03-2022; Gunther Eysenbach MD MPH, Associate Professor; JMIR Publications
• Subjects: Algorithms; Analysis; Area Under Curve; Artificial intelligence; Cardiovascular diseases; Care and treatment; Data collection; Data entry; Deep learning; Dementia; Deployment; Diabetes; Diabetes therapy; Eating behavior; Eating disorders; Engineering; Feeding Behavior; Food; Food habits; Humans; Laboratories; Machine Learning; Meals; Original Paper; Patient satisfaction; Prospective Studies; Robustness; Sensors; Tracking; Type 2 diabetes; Wearable computers; Wrist; Taiwan; United States > US; eating; deep learning; digital watch
• ISSN: 1438-8871; 1439-4456; 1438-8871
• DOI: 10.2196/27934

Monitoring eating is central to the care of many conditions such as diabetes, eating disorders, heart diseases, and dementia. However, automatic tracking of eating in a free-living environment remains a challenge because of the lack of a mature system and large-scale, reliable training set.
This study aims to fill in this gap by an integrative engineering and machine learning effort and conducting a large-scale study in terms of monitoring hours on wearable-based eating detection.
This prospective, longitudinal, passively collected study, covering 3828 hours of records, was made possible by programming a digital system that streams diary, accelerometer, and gyroscope data from Apple Watches to iPhones and then transfers the data to the cloud.
On the basis of this data collection, we developed deep learning models leveraging spatial and time augmentation and inferring eating at an area under the curve (AUC) of 0.825 within 5 minutes in the general population. In addition, the longitudinal follow-up of the study design encouraged us to develop personalized models that detect eating behavior at an AUC of 0.872. When aggregated to individual meals, the AUC is 0.951. We then prospectively collected an independent validation cohort in a different season of the year and validated the robustness of the models (0.941 for meal-level aggregation).
The accuracy of this model and the data streaming platform promises immediate deployment for monitoring eating in applications such as diabetic integrative care.