AI‐Driven Dentistry and Public Health Surveillance: Opportunities and Challenges
Source: PubMed Central Open Access, NCBI / U.S. National Library of Medicine
ABSTRACT The integration of artificial intelligence (AI) into dentistry is reshaping clinical workflows, opening new possibilities for population‐level public health monitoring. Machine learning approaches, such as convolutional neural networks and other deep learning architectures, are becoming more and more capable to exhibit diagnostic performances, which are close to those of expert human readers. Beyond single‐clinic decision support, aggregated outputs that have been collected from AI diagnostic systems could be used as real‐time signals for population surveillance: When combined with geospatial and socioeconomic datasets, they may help reveal structural barriers to care. This review presents opportunities and constraints at the intersection of diagnostic AI and dental public health surveillance and outlines a five‐stage framework (data ingestion, spatiotemporal aggregation, socioeconomic enrichment, predictive modeling, and dashboard deployment) for turning de‐identified AI outputs into actionable, equity‐focused public health intelligence. This article also examines methodological, privacy, and governance challenges—including bias, interpretability, and accountability—as well as ethical issues and proposes safeguards to support equitable deployment. Artificial intelligence (AI) in dentistry is presented as a population‐level surveillance tool by transforming anonymized diagnostic outputs into actionable public health intelligence. A five‐stage framework integrating AI
Abstract
ABSTRACT The integration of artificial intelligence (AI) into dentistry is reshaping clinical workflows, opening new possibilities for population‐level public health monitoring. Machine learning approaches, such as convolutional neural networks and other deep learning architectures, are becoming more and more capable to exhibit diagnostic performances, which are close to those of expert human readers. Beyond single‐clinic decision support, aggregated outputs that have been collected from AI diagnostic systems could be used as real‐time signals for population surveillance: When combined with geospatial and socioeconomic datasets, they may help reveal structural barriers to care. This review presents opportunities and constraints at the intersection of diagnostic AI and dental public health surveillance and outlines a five‐stage framework (data ingestion, spatiotemporal aggregation, socioeconomic enrichment, predictive modeling, and dashboard deployment) for turning de‐identified AI outputs into actionable, equity‐focused public health intelligence. This article also examines methodological, privacy, and governance challenges—including bias, interpretability, and accountability—as well as ethical issues and proposes safeguards to support equitable deployment. Artificial intelligence (AI) in dentistry is presented as a population‐level surveillance tool by transforming anonymized diagnostic outputs into actionable public health intelligence. A five‐stage framework integrating AI diagnostics with geospatial and socioeconomic data enables prediction of oral health disparities, supports targeted interventions, and promotes equitable resource allocation while emphasizing privacy, transparency, and ethical governance. puh270278-abs-0001 graphical