Promises and perils of artificial intelligence in dentistry

Abstract

Artificial intelligence (AI) is a subdiscipline of computer science that has made substantial progress in medicine and there is a growing body of AI research in dentistry. Dentists should have an understanding of the foundational concepts and the ability to critically evaluate dental research in AI. Machine learning (ML) is a subfield of AI that most dental AI research is dedicated to. The most prolific area of ML research is automated interpretation of dental imaging. Other areas include providing treatment recommendations, predicting future disease and treatment outcomes. The research impact is limited by small datasets that do not harness the positive correlation between very large datasets and ML performance. There is also a need to standardize research methodologies and utilize performance metrics that are appropriate for the clinical context. In addition to research challenges, this article discusses the ethical, legal and logistical considerations associated with implementation in clinical practice. This includes explainable AI, model bias, data privacy and security. The future implications of AI in dentistry involve a promise for a novel form of practicing dentistry however, the effect of AI on patient outcomes is yet to be determined.

Diagnosis of Tooth Prognosis Using Artificial Intelligence

“…As Model-A includes the datasets trained by a group including experienced prosthodontists, the accuracy turned out to be higher and more predictable in consensus with the gold standard. This result is comparable to the findings that the accuracy of machine learning-generated analytics and predictive modeling is highly dependent on the type and quality of the data from which the machine learning system is learning [ 36 ]. Thus, it is critical to obtain data from experienced clinician educators to build this machine-learning model and the gold standard is applied to the dataset for an accurate and consistent outcome.…”

“…The procedure relies on the recognition of patterns using training data and applies this knowledge to the prediction of outcomes in a different dataset or test data. In dentistry, there are vast quantities of different types of data, including restorative and periodontal charts, the results of diagnostic and laboratory tests, radiographs, and extraoral and intraoral images [ 36 ]. These datasets can be transcribed into machine-learning models to generate outputs such as diagnosis, treatment recommendations, and future disease predictions [ 36 ].…”

“…In dentistry, there are vast quantities of different types of data, including restorative and periodontal charts, the results of diagnostic and laboratory tests, radiographs, and extraoral and intraoral images [ 36 ]. These datasets can be transcribed into machine-learning models to generate outputs such as diagnosis, treatment recommendations, and future disease predictions [ 36 ]. While scientific publications related to AI in healthcare have quadrupled in the past decade [ 37 ], dental literature on the subject of AI has not been as common.…”

Artificial Intelligence: A New Diagnostic Software in Dentistry: A Preliminary Performance Diagnostic Study

“…Most of the artificial intelligence algorithms studied over the years by various authors have been designed to address various clinical situations in various fields of medicine. The future project they are expected to achieve is the creation of an integrated digital workflow system that exploits artificial intelligence for the dental sector [22][23][24].…”

Aged care and artificial intelligence

“…There is no doubt that AI has the potential to make oral health care accessible and effective but there is also the potential for errors to arise if the algorithms developed are not carefully designed and implemented. AI in dentistry is in its infancy but the potential for rapid development is high 1 . It has been said that health care can be made more equitable by tailoring algorithms to specific patient populations (i.e.…”