{
  "id": 19254873,
  "title": "AI used to predict cavities",
  "url": "https://urgent.news/2026/11/10/ai-used-to-predict-cavities",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-10T00:30:01.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-11-ai-cavities.html"
  },
  "original_language": "en",
  "account": "An international group of scientists is utilizing artificial intelligence to predict individuals who are at an elevated risk for dental cavities. Their research, published in the academic journal Caries Research, aims to identify population clusters most vulnerable to tooth decay by examining broader social determinants of health, rather than relying solely on individual clinical diagnoses. Fernando Neves Hugo, chair of the Department of Epidemiology and Health Promotion at NYU College of Dentistry and the study's senior author, emphasized that AI presents a groundbreaking opportunity for public health surveillance and risk stratification, particularly in tackling the global cavity burden. He noted that these advanced tools could effectively target resources and deliver preventive care to the groups most likely to benefit. Dental cavities represent the most prevalent global health issue, affecting billions across all age groups. Factors contributing to cavities often manifest at the population level, such as access to dental care, dietary habits, water quality, and other societal influences. To analyze these complex relationships, the researchers applied various AI models to data from the Brazilian Oral Health Survey, which included 23,726 participants aged 12 and older from the 2023 study. The survey collected demographic data (age, sex, race), social determinants of health (socioeconomic factors, household characteristics, dental insurance status, water sources), and behavioral information (frequency of dental visits). Clinical exams assessed the degree and extent of tooth decay. Traditional analyses indicated that wealth and household density were the most influential predictors of cavity risk. Non-white populations showed a higher likelihood of cavities across all age groups, while private dental insurance and regular dental visits were protective factors. Water source also played a significant role: 12-year-olds without access to fluoridated water had a cavity rate nearly twice that of those with fluoridated water systems (62.5% vs. 35.5%). The AI models demonstrated the ability to accurately predict cavity risk and severity by age group, considering the complex interplay of various factors. According to Hugo, integrating machine learning into public health frameworks goes beyond mere risk prediction; it addresses the intricate, multidimensional interactions between social determinants that conventional methods often overlook. This approach acts as a high-resolution sensor, identifying individuals with profiles indicating heightened risk that might otherwise go unnoticed within broader community averages. While the findings may apply to other middle-income countries, the researchers acknowledged that local factors, including access to dental care and benefits, would likely modify the variables influencing cavity risk in different regions. Hugo and his team plan to conduct similar AI-enabled analyses using data from the National Health and Nutrition Examination Survey in the United States. By tailoring prevention strategies specific to each country, Hugo and his colleagues aim to optimize resource allocation, ensuring maximum impact for public health interventions.",
  "summary": "An international team of researchers is leveraging artificial intelligence to predict who is at high risk for cavities. The findings, published in the journal Caries Research, could help identify population clusters most at risk for tooth decay based on larger social determinants of health rather than on clinical diagnostics at the individual level.",
  "key_points": [],
  "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."
}