{
  "id": 19178107,
  "title": "AI can predict who’s at high risk for cavities",
  "url": "https://urgent.news/2026/11/09/ai-can-predict-whos-at-high-risk-for-cavities",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-09T16:34:44.000Z",
  "source": {
    "name": "Futurity",
    "slug": "futurity",
    "url": "https://www.futurity.org/artificial-intelligence-cavities-3352372/"
  },
  "original_language": "en",
  "account": "Researchers are using artificial intelligence to predict who is at high risk for cavities. Published in the journal Caries Research, these findings could identify population clusters most at risk for tooth decay based on larger social determinants of health instead of relying on clinical diagnostics at the individual level. Fernando Neves Hugo, chair of the epidemiology and health promotion department at NYU College of Dentistry and the study's senior author, emphasizes the transformative potential of AI for public health surveillance and risk stratification, particularly in addressing the global burden of cavities. Dental cavities, the most common health condition globally, affect billions across all age groups and are influenced by factors that often manifest at the population level, including access to dental care, diet, sugar consumption, and water sources. By employing AI algorithms to analyze extensive datasets, researchers can uncover patterns that might otherwise be challenging to detect. Hugo and his team applied AI models to data from the Brazilian Oral Health Survey, which included 23,726 participants, including children, adolescents, and adults. The survey collected demographic information and social determinants of health linked to oral health, such as socioeconomic factors (wealth, household density, private dental insurance, water source) and behaviors (time since last dental visit). Participants also underwent clinical exams to assess the prevalence and severity of tooth decay. Traditional analyses revealed that wealth and household density were the strongest predictors of cavity risk, while non-white populations had a higher risk across all age groups. Private dental insurance and recent dental visits were protective against cavities. Water source also played a significant role, with 62.5% of 12-year-olds lacking access to fluoridated water having cavities, compared to 35.5% in those with fluoridated water systems. The researchers applied several machine learning algorithms to the dataset and discovered that the AI models could accurately predict cavity risk and severity by age group, accounting for the complex interactions between various factors. Hugo explains that incorporating machine learning into this framework goes beyond mere cavity risk prediction; it addresses the multidimensional complexity of social determinants that traditional measures often overlook. The AI approach functions as a high-resolution sensor, identifying individuals whose profiles indicate a heightened risk that might otherwise remain hidden within community averages. While the findings may apply to other middle-income countries, local factors like access to dental care and benefits would alter the variables explaining cavity risk in different regions. The researchers aim to replicate this AI-enabled approach using data from other countries to develop tailored prevention strategies. Hugo and his colleagues are planning to conduct a similar analysis using US data from the National Health and Nutrition Examination Survey. Hugo concludes that public health and preventive interventions require accountability and optimal resource utilization. A more targeted approach helps optimize resources, maximizing impact.",
  "summary": "Machine learning can identify groups who would most benefit from dental care, enabling targeted public health programs.",
  "key_points": [
    "AI predicts high-risk individuals for cavities using social determinants of health",
    "Study in Caries Research analyzes Brazilian Oral Health Survey data of 23,726 participants",
    "AI models accurately predict cavity risk and severity by age group"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}