Leveraging AI in dental caries prediction, prevention
Researchers have explored whether artificial intelligence can help clinicians tackle the high rate of dental decay.
In a study published in Caries Research, researchers developed a machine-learning model designed to support risk stratification and public health planning around population-level dental caries using data from the national 2023 Brazilian Oral Health Survey — which involved nearly 25,000 participants between the ages of 12 and 44 years. They then divided the study participants into three groups on the basis of age (12 years, 15 to 19 years and 35 to 44 years) and used a set of predictors covering socioeconomic, psychosocial, behavioral and clinical factors to predict the presence and severity of dental caries.
The researchers noted that older participant groups were more likely to have dental caries and that a nonclinical model demonstrated accuracy in identifying participants who may be at higher risk of experiencing dental decay without requiring oral examinations in a clinical setting. Further, the Zero-Inflated Negative Binomial model was effective in predicting the severity of dental caries, indicating that predictors of structural inequity may play a large role, especially among those aged 15 to 19 years. Additional analysis suggested that wealth scores and household density may contribute extensively to the risk of developing dental caries, nonwhite participants had the greatest risk of dental caries among all three age groups, and 12-year-old participants without access to water sanitation provided by piped water were more likely to develop dental decay compared with those who did have access.
According to a news article from Medical Xpress reporting on the findings, the researchers underscored that artificial intelligence may help bolster public health surveillance efforts and preventive treatment strategies to better address the high burden of dental caries in middle-income countries beyond Brazil. The researchers are preparing to run a similar analysis using data from the U.S. National Health and Nutrition Examination Survey. However, because the causes of tooth decay can be multifactorial, dental caries is currently one of the most common health conditions in the world.
The results of the study highlighted the potential benefit of incorporating an AI-based triage framework to screen for high-risk populations rather than individual patients. The researchers hope to use country-specific factors to apply their new machine-learning method to dental caries risk stratification and prevention across the world.
Read more: Medical Xpress
The article presented here is intended to inform you about the broader media perspective on dentistry, regardless of its alignment with the ADA's stance. It is important to note that publication of an article does not imply the ADA's endorsement, agreement, or promotion of its content.