AI Model Could One Day Help Prevent Childhood Obesity by Counting Bites

Key Takeaways:

• Researchers at Penn State have developed an artificial intelligence (AI) system capable of counting how many bites a child takes during a meal, achieving around 70% accuracy compared to human observers.
  
• Eating too quickly increases the risk of obesity in children because the body has less time to register fullness, leading to overeating.
  
• The AI system, named ByteTrack, may in future help parents, clinicians, and researchers monitor and guide children’s eating habits in real-world environments.
  
  
  

AI and eating behaviours: A new frontier in obesity prevention

The faster a child eats, the greater their risk of developing obesity, according to researchers from the Penn State Department of Nutritional Sciences. However, accurately measuring bite rate—the number of bites taken during a meal—has long posed a challenge. Traditionally, this requires a researcher to watch and manually record each bite from hours of video footage, limiting most studies to small, controlled laboratory environments.

In a collaborative effort between Penn State’s Departments of Nutritional Sciences and Human Development and Family Studies, researchers have created an AI model designed to automate this process. Their pilot study, published in Frontiers in Nutrition, shows that the system is currently around 70% as effective as a human observer in counting bites. Although still under development, the researchers believe the technology could eventually help identify when a child needs to slow their eating rate or adjust their eating behaviour.

The link between eating speed and obesity

“When we eat quickly, we do not give our digestive tract time to sense the calories,” explained Professor Kathleen Keller, the Helen A. Guthrie Chair of Nutritional Sciences at Penn State and co-author of the study. “The faster you eat, the faster it goes through your stomach, and the body cannot release hormones in time to let you know you are full. Later, you may feel like you have overeaten, but when this behaviour repeats, faster eaters are at greater risk for developing obesity.”

Keller’s research group has previously demonstrated that a faster bite rate, especially when combined with larger bite size, correlates with a higher likelihood of obesity in children. Other studies have also linked larger bite size to an increased risk of choking.

“Bite rate is often the target behaviour for interventions aimed at slowing eating rate,” noted Dr Alaina Pearce, research data management librarian at Penn State and co-author of the study. “This is because 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.”

Manually recording bite rate, however, is both labour-intensive and costly. As Keller pointed out, “Measuring bite rate is tedious, labour-intensive work, meaning it is expensive, which often limits the amount of data considered in bite rate studies.”

Using AI to support healthier habits

To overcome these limitations, Yashaswini Bhat, a doctoral candidate in nutritional sciences and lead author of the study, set out to develop the first AI-powered bite counter designed specifically for studying children’s eating behaviours.

“I have an interest in AI and data science, but I had never developed a system like this one,” Bhat explained.

She partnered with Associate Professor Timothy Brick, from Penn State’s Department of Human Development and Family Studies, to create a system capable of detecting children’s faces within videos and identifying when a child takes a bite.

“An experienced and knowledgeable collaborator like Dr Brick was invaluable to this project,” Bhat added.

The team trained the system using 1,440 minutes of video footage from Keller’s Food and Brain Study, funded by the National Institute of Diabetes and Digestive and Kidney Diseases. The footage featured 94 children aged seven to nine, each consuming four meals with identical foods on different occasions.

Researchers manually identified bites in 242 videos to train the AI. Once the system had been trained to recognise what a bite looks like, it was tested on an additional 51 videos. The AI’s results were then compared to those of human researchers.

Promising early results

“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.”

While the AI was 97% as effective as a human observer at recognising faces, it achieved about 70% accuracy in counting bites. Bhat noted that challenges arose when children were partially obscured, turned away from the camera, or engaged in behaviours such as chewing on their spoons or playing with their food—actions common among younger participants.

“The system was less accurate when a child’s face was not in full view of the camera or when a child chewed on their spoon or played with their food, as often happens toward the end of a meal,” Bhat said. “Chewing on a utensil sometimes appeared to be a bite, and this complicated the task for the AI model.”

Next steps for the ByteTrack system

Although still in its early stages, the researchers view the pilot as an important step toward automating bite rate analysis. The system, called ByteTrack, will continue to be refined so it can distinguish between bites and similar movements such as sipping a drink.

“The eventual goal is to develop a robust system that can function in the real world,” Bhat said. “One day, we might be able to offer a smartphone app that warns children when they need to slow their eating so they can develop healthy habits that last a lifetime.”

The 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.