Synergy between human clinical expertise and artificial intelligence for better oral health care.
The Feher Lab at Harvard University works at the intersection of applied machine learning and dental medicine, advancing our understanding of oral diseases and contributing to personalized treatment approaches.
Continuing Education Course “Artificial Intelligence in Dental Medicine” by the Harvard School of Dental Medicine
Registration for Cohort 3 starting early 2027 is opening soon.
Contact Harvard School of Dental Medicine Continuing Education here to join the waitlist and secure your spot.
The first intercontinentally tested machine learning model that predicts individual responses to periodontal treatment.
Periodontal treatment is largely standardized, but individual outcomes can vary. Some patients experience disease progression despite adherence to treatment protocols. We developed a machine learning model to predict individual outcomes one year post-treatment using only baseline parameters. Our model was trained on South American patient data and tested on North American and European patient data.
A computer vision architecture that estimates periodontal stability at the tooth and patient level.
This work uses a combined object detection and image classification architecture on intraoral radiographs to estimate periodontal stability, which traditionally requires both clinical and radiographic examination, from radiographic signal alone. The model uses single tooth-level results to estimate periodontal stability at the patient level.
“Artificial intelligence holds enormous potential for improving the health of millions of people around the world”
WHO Director-General Tedros Adhanom Ghebreyesus