The faster a child takes bites during a meal or snack, the greater risk they have for developing obesity, according to researchers in the Penn State Department of Nutritional Sciences. But research into this association is often limited to small studies in laboratory environments, largely because counting a child’s bite rate is difficult; it requires someone to watch videos of a child eating and manually record each bite.
To make bite rate counting possible for larger studies and in different environments, researchers from the Penn State Departments of Nutritional Sciences and of Human Development and Family Studies collaborated to develop an artificial intelligence (AI) model that measures bite rate.
A pilot study — recently published in Frontiers in Nutrition — demonstrated that the system is currently about 70% as successful as human bite counters. While it requires more development, the researchers said the AI model shows promise to help researchers — and eventually parents and health professionals — identify when children need to slow or otherwise adjust the ways they eat.
Eating too quickly and obesity risk
“When we eat quickly, we don’t give our digestive track time to sense the calories,” said Kathleen Keller, Social Science Research Institute cofunded faculty member and Helen A. Guthrie Chair of nutritional sciences at Penn State and co-author of this 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 behavior repeats, faster eaters are at greater risk for developing obesity.”
Faster bite rate, especially when combined with larger bite size, is associated with higher obesity rates among children, according to previous research from Keller’s laboratory group. Other studies have demonstrated that larger bite size may also be a risk factor for choking.
“Bite rate is often the target behavior for interventions aimed at slowing eating rate,” said Alaina Pearce, research data management librarian at Penn State and co-author of this research. “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."
Measuring bite rate is tedious, labor-intensive work, meaning it is expensive, which often limits the amount of data considered in bite rate studies, according to Keller, a Penn State Social Science Research Institute co-funded faculty member.
Leveraging technology to keep children healthy
To address that problem, Yashaswini Bhat, doctoral candidate in nutritional sciences and lead author on the study, wanted to develop the first AI bite counter for use in studies of children’s eating behaviors.
“I have an interest in AI and data science, but I had never developed a system like this one,” Bhat said.
She collaborated with Timothy Brick, associate professor of human development and family studies at Penn State and study co-author, to build a system that could identify children’s faces in a video with multiple people and then detect individual bites when a child was eating.
“An experienced and knowledgeable collaborator like Dr. Brick was invaluable to this project,” Bhat said.
The researchers used 1,440 minutes of videos from Keller’s Food and Brain Study, a National Institute of Diabetes and Digestive and Kidney Diseases-funded study of the neural mechanisms that may influence overeating in children. The video footage included 94 seven- to nine-year-old children consuming four meals on separate occasions with varying amounts of identical foods.
The researchers identified bites in 242 of the videos by watching the videos and noting each bite. They then used that information to train the AI model. Once the model was able to identify events that appeared to be bites, the researchers had it evaluate 51 other videos from the same data set. The researchers then compared the bites identified by the model to see if they matched the bites coded by research assistants.
A successful first step
“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.”
The system, however, is not yet ready for widespread use, according to Bhat. Results demonstrated that the model was roughly 97% as successful as a human at identifying a child’s face in the video but was about 70% as successful as a human at identifying every bite.
“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. “As one might imagine, this type of behavior is much more common among children than it is with adults. Chewing on a utensil sometimes appeared to be a bite, and this complicated the task for the AI model.”
While more work is needed, the researchers said that this study represents a successful pilot test. With more training, they said the system — called ByteTrack — will more accurately identify bites and learn to ignore other actions, like sipping a beverage.
“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 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 funded this research.