Artificial Intelligence in Dentistry

Standards provide a roadmap for evaluating and integrating AI systems into dental practice by establishing criteria for safety, efficacy, transparency and fairness.

Bluish AI rendition of lower teeth xray

First U.S. Standard on AI In Dentistry Approved by the American National Standards Institute

ANSI/ADA Standard No. 1110-1:2025, Dentistry — Validation Dataset Guidance for Image Analysis Systems Using Artificial Intelligence, Part 1: Image Annotation and Data Collection

The purpose of this standard is to provide standardized criteria for annotating and collecting data from 2D radiographs to classify the images and use them in clinical decision-making. It covers image analysis associated with machine learning and deep learning and identifies the necessary annotations and data content for 2D radiographic images to be queried, exchanged and communicated among providers at all treatment locations for diagnosis, treatment, administrative tasks, research and development efforts.

 

Additional National Standards Documents on AI

ADA White Paper No. 1106:2022, Dentistry — Overview of Augmented and Artificial Intelligence Uses in Dentistry

This white paper introduces the use of artificial and augmented intelligence in many clinical disciplines, including prevention, caries and periodontal disease, implants, oral and maxillofacial surgery, endodontics, prosthetics, and digital imaging. The paper addresses nonclinical areas as well, focusing on payer topics such as claims processing, payment integrity and quality assurance. The document also provides information on the current regulatory environment.

 

ADA Technical Report No. 1109:2025, Dentistry—Evaluation of Dental Image Analysis Systems Using Augmented/Artificial Intelligence

This technical report highlights the need for an independent dataset to validate AI algorithms used to analyze 2D dental images. The dataset, which would be based on known diagnoses from validated sources and kept by a third party that is not an AI manufacturer, would allow all users, developers and approval agencies to compare each proposed AI algorithm for accuracy and specificity. The report proposes methods for establishing the dataset and describes the general principles of AI, including the need for data and methods to be private and secure to avoid bias.

 

If you would like to join get started at the ADA Standards Program and contribute your expertise in the development of future standards.