AI can help identify people most at risk for tooth decay

An international research team analyzed data from Brazil's 2023 oral health survey, including 23,726 participants across three age groups, to test whether AI could help identify communities at higher risk for tooth decay. The study, published in Caries Research and led by senior author Fernando Neves Hugo of NYU College of Dentistry, used social, economic, and health information alongside dental findings. Wealth and household crowding emerged as important predictors, with lower wealth and greater crowding linked to higher disease burden; non-White participants also experienced disparities. Untreated decay affected about 36.9% of children, 43.7% of adolescents, and 52.7% of adults. The researchers compared statistical and machine-learning models, including a triage version that relied only on questionnaire data without dental examinations. Predictive performance was modest: the strongest adolescent model explained only about 10% of variation in DMFT scores, with an average error of roughly 2.8 teeth. The authors emphasize that the proposed use is public health planning to target resources and preventive care, not an automated replacement for a dentist's diagnosis. They also caution that the study classified existing dental findings rather than predicting future cavities, that testing in independent populations is needed, and that fairness and algorithmic bias must be evaluated before using scores to influence access to care. The study's contribution is a framework for connecting oral disease with social circumstances at scale, but its value depends on whether transparent, independently tested predictions lead to better access and prevention.

(Source：The Brighter Side of News)