How quickly a child eats could influence their long-term health, but studying that behavior has always been slow work. Researchers at Penn State are now using artificial intelligence (AI) to help.
A new pilot study published in Frontiers in Nutrition shows that AI can accurately detect when a child takes a bite during a meal, an important step toward identifying early eating habits that may raise the risk of obesity.
“When we eat quickly, we don’t give our digestive tract time to sense the calories,” said Kathleen Keller, professor and Helen A. Guthrie Chair of Nutritional Sciences at Penn State and co-author of the study. “The faster you eat, the faster food moves through your stomach, and the body cannot release hormones in time to let you know you are full.”
Previous research has shown that children who take larger or faster bites tend to eat more overall and may be more likely to develop obesity. But tracking bite rate requires hours of manual video review, limiting how much data researchers can collect.
To solve that problem, doctoral candidate Yashaswini Bhat led the development of an AI system called ByteTrack, which automatically counts bites using video footage. Working with colleagues in nutrition and human development, Bhat trained the AI model on 1,440 minutes of video from 94 children participating in an ongoing study of eating behaviors and brain activity.
“The system we developed was very successful at identifying the children’s faces,” Bhat said. “It also did an excellent job identifying bites when it had a clear, unobstructed view of a child’s face.”
In its first test, ByteTrack correctly identified children’s faces 97% of the time and recognized bites with about 70% accuracy, similar to how a human observer would perform. The researchers plan to refine the model so it can handle real-world conditions such as group meals or when a child moves out of frame.
The ultimate goal, Keller said, is to create a tool that can help scientists, and possibly families, better understand how children eat and when they may need to slow down.
“Bite rate is a stable characteristic of children’s eating style that can be targeted to reduce their eating rate, intake and ultimately risk for obesity,” said Alaina Pearce, a research data management librarian and co-author of the study.
With further development, the researchers hope ByteTrack could one day power smartphone apps that provide gentle feedback to help children form healthy eating habits.
This research was supported by the National Institute of Diabetes and Digestive and Kidney Diseases, the National Institute of General Medical Sciences, the Penn State Institute for Computational and Data Sciences, and the Penn State Clinical and Translational Science Institute.