An artificial intelligence (AI) dental algorithm has demonstrated 96.4% accuracy in helping orthodontists determine the best treatment approach for patients missing permanent second premolars — a common but complex clinical scenario, the University at Buffalo reported.
While most children see their permanent second premolars erupt around age 11, between two and 11 per cent of the population are born without them, a condition known as tooth agenesis. In such cases, orthodontists must decide whether to retain the primary molars, extract them and close the space orthodontically, or extract them and preserve the space for future restorative options such as implants or bridges.
“Tooth agenesis … is among the most common and clinically challenging dental anomalies encountered today,” said Thikriat Al-Jewair, DDS, L.B. Badgero Endowed Chair and associate professor in the Department of Orthodontics at the University at Buffalo School of Dental Medicine.
Al-Jewair recently led an exploratory study, published in the January 2026 issue of Orthodontics and Craniofacial Research, examining whether AI could support that decision-making process.
Four machine-learning models
The research team developed four machine-learning models using dental models, radiographs, clinical photographs, and medical and dental histories from 100 adolescent patients treated between 2010 and 2024. All participants retained their primary second molars at the start of treatment.
Among the models tested, a Random Forest classifier achieved the highest predictive accuracy at 96.4%. Key factors influencing treatment decisions included patient preference for future restoration, degree of mandibular crowding, and presence of ankylosis — a condition in which a tooth becomes fused to the bone and begins to submerge.
“Enhancing diagnostic accuracy and improving treatment predictability are critical, and this is where AI may provide meaningful support,” Al-Jewair said.
Related: Artificial intelligence and algorithms: Friend or foe as the great predictors?
AI supports — not replaces — clinical judgment
Researchers emphasized that the AI system is designed to support — not replace — the clinical decisions of licensed orthodontists, particularly when managing complex cases.
“Less experienced orthodontists, such as new graduates, struggle with this type of malocclusion, and AI could be a helpful tool,” Al-Jewair said. “If we can integrate these AI algorithms into the technology we already use in clinical practice, I think they have the potential to enhance the accuracy of our clinical decisions and improve treatment outcomes.”
The study represents a collaboration between the University at Buffalo’s Department of Orthodontics and the Department of Biostatistics in the School of Public Health and Health Professions, underscoring the growing role of data science in clinical dentistry. A faculty member in the Department of Orthodontics at the University of Illinois Chicago College of Dentistry, who specializes in AI, also contributed to the research.
You can also listen to our podcast on AI trends to watch for in 2026: