AI Models Predict High-Risk Populations for Dental Cavities Using Social Determinants of Health

AI Transforms Cavity Prevention Through Population-Level Risk Assessment

Researchers have developed AI models to predict high-risk populations for dental cavities by analyzing social determinants of health rather than individual clinical diagnostics. Published in Caries Research, the study demonstrates how machine learning algorithms can identify population clusters most vulnerable to tooth decay, enabling more targeted public health interventions1

1

2

Fernando Neves Hugo, chair of the epidemiology and health promotion department at NYU College of Dentistry and senior author, explains that AI offers a transformative opportunity for addressing the global burden of cavities. "These are powerful tools that could be helpful for targeting resources and delivering preventive care to specific groups that will benefit the most," Hugo states1

1

Analyzing 23,726 Patients to Predict Cavity Risk

The research team applied machine learning algorithms to data from the Brazilian Oral Health Survey, a national epidemiological study coordinated by the Brazilian Ministry of Health. The analysis included 23,726 people who participated in the 2023 survey, spanning children, adolescents, and adults2

2

The dataset captured demographic information including age, sex, and race, alongside social determinants of health linked to oral health outcomes. Researchers examined socioeconomic factors such as wealth, household density, private dental insurance status, and water source, as well as behavioral factors like time since last dental visit. Participants underwent clinical exams to measure tooth decay prevalence and severity1

1

Source: Futurity

Wealth and Water Access Emerge as Critical Predictors

Traditional analyses revealed that oral health reflects a complex interplay of socioeconomic, structural, and behavioral factors. Wealth and household density emerged as the strongest predictors of cavity risk across all age groups. Non-white populations showed higher cavity risk, while private dental insurance and recent dental visits provided protective effects2

2

Water source played a particularly critical role in cavity development. Among 12-year-olds, 62.5% without access to fluoridated water had dental cavities—nearly double the 35.5% observed in those with fluoridated water systems. This stark difference underscores how infrastructure decisions directly impact oral health outcomes at the population level1

1

Related Stories

AI Model Predicts Future Health Risks for Over 1,000 Diseases

AI Model Unlocks Hidden Health Risks in Routine Sleep Studies, Doubles Mortality Prediction Accuracy

AI-Enhanced ECG and CT Scans Revolutionize Cardiovascular Risk Prediction

AI Model Predicts Disease Onset Up to 20 Years in Advance

Machine Learning Reveals Hidden Risk Patterns

When researchers applied several machine learning algorithms to the dataset, the AI models accurately predicted cavity risk and severity by age group through evaluating relative contributions of different factors. Hugo emphasizes that integrating machine learning goes beyond merely predicting cavity risk: "Our machine learning approach acts as a high-resolution sensor that identifies individuals whose profiles signal a heightened risk that would otherwise be invisible within community averages"2

2

Source: Medical Xpress

This AI-enabled approach addresses the complexity and multidimensional interactions between social determinants that traditional measures often mask, providing public health officials with actionable insights for resource allocation1

1

Expanding to US Data for Tailored Prevention Strategies

The researchers note their findings may translate to other middle-income countries, though local factors including access to dental care would likely shift the variables explaining cavity risk in different contexts. Hugo and colleagues are preparing to replicate this analysis using US data from the National Health and Nutrition Examination Survey to develop tailored prevention strategies2

2

"When we think about public health and preventive interventions, we need to be accountable to society and make the best use of the resources we have. A more targeted approach helps us optimize resources—essentially, getting more bang for our buck," Hugo explains. This AI-driven methodology could reshape how preventive healthcare resources are allocated globally, ensuring dental cavities—the most common health condition affecting billions worldwide—receive more effective intervention1

1