AI can discover tooth decay more precisely than human dentists

Dental

New research suggests that artificial intelligence systems can discover tooth decay more precisely than human dentists. Pearl's analysis contrasts the diagnostic capacities of three human dentists to that of a diagnostic device for artificial intelligence.

After reviewing more than eight thousand and seven hundred bitewing and periapical radiographs, the study looked at the relationship between AI diagnostics and the human. There was a lack of diagnostic consensus among the three human dentists, the research unveiled.

“New research suggests that artificial intelligence systems can discover tooth decay more precisely than human dentists.“

They showed a unanimous consensus of seventy-nine per cent when it came to the absence of decay; but, when it came to the prevalence of decay, this fell to four-point-two per cent. Furthermore, in a fifth of instances, when two dentists discovered decay in an X-ray, the remaining three did not.

Pearl’s CEO Ophir Tanz, stated: “Our intention in producing this study was simply to demonstrate the efficacy of computer vision machine learning diagnostics in dental radiology. Diagnostic inconsistency may be a natural by-product of human professionals making case by case judgements. But a scale inconsistency in the standard of care could result in suboptimal patient treatment. With broader implications for population health at large. Fortunately, the study’s findings also point to a solution; the machine’s diagnostic performance shows that AI is capable of infusing consistency into the bedrock of dental care.”

Chair and associate professor in oral and maxillofacial radiology - the division of diagnostic and surgical sciences, UCLA School of Dentistry, Dr Sanjay Mallya, stated: “More studies like this are in order. It would be useful for instance, to drill deeper to see if the discrepancy evident in this study persists for caries across varying degrees of severity.”

See all the latest jobs in Dental
Return to news