Researchers at the University of Pennsylvania School of Dentistry have developed an artificial intelligence-powered process to identify risk factors associated with tooth decay.
The team used machine learning to analyze public data from the National Health and Nutrition Examination Survey. Michelle Khoo, professor of orthodontics, and Jason Moore, professor of biostatistics and epidemiology, led the December 2025 study, which was published in the Journal of Dental Research.
“This type of machine learning pipeline can turn complex national health data into clearer hypotheses and better predictive models, starting with oral health and potentially extending to other medical fields,” Koo, co-founder director of the Center for Innovation & Precision Dentistry, said in a press release from the School of Dentistry.
Koo and Moore’s research was supported by researchers at the School of Dentistry, the Pennsylvania Institute for Biomedical Informatics, the School of Nursing, and Cedars-Sinai Medical Center.
The study, titled “Unraveling caries heterogeneity in NHANES using machine learning,” allowed the team to detect previously unrecognized patterns linking dental health to systemic, nutritional, and environmental factors.
The NHANES survey is conducted by the Centers for Disease Control and Prevention and includes data on the determinants of health for Americans. These datasets can be “somewhat messy” due to various “heterogeneity” aspects within the study.
The researchers organized the data into several subsets, including by age. They found that most signs of tooth decay occurred in children under 5 years of age (a pattern of iron and vitamin D deficiency was also observed) and adults over 65 years of age.
“Our results demonstrate the importance of age-targeted prevention and prediction, especially for young children and older adults, based on real-world dietary patterns, laboratory signals, environmental risk conditions, and potentially other signals,” Koo wrote.
Tooth decay is associated with exposure to lead, among other metals and chemicals. The researchers noted that tooth decay “may be more than just a local disease,” but may serve as a “surveillance marker for underlying systemic health problems.”
The study found that “sugar-rich foods” such as apple juice, energy drinks, flavored milk and ice cream were linked to tooth decay.
The researchers also found that sleep may be linked to tooth decay, but said “further research is needed.”
In February 2025, researchers from the School of Dentistry, School of Engineering and Applied Sciences, and Perelman School of Medicine worked We work together to create treatment options for apical periodontitis, a chronic dental infection that causes tooth loss and affects more than half of the world’s population.
