Artificial Intelligence is getting better and better at facial recognition and can even “deep fake” smiles. But what about what goes on inside the mouth?
A new study tested an AI model’s ability to recognize gingivitis, or gum inflammation, and found that the model identified various symptoms, such as redness and swelling, with 90% accuracy.
The research could be expanded to look at how the AI could be used to increase access to dental care within elderly communities, researchers said.
More than two-thirds of Americans over the age of 65 have some form of dental disease, according to the Centers for Disease Control and Prevention. The CDC cites a variety of factors, including a history of smoking or being homebound.
In addition, patients with chronic diseases such as diabetes or arthritis are also likely to develop gum disease.
Good oral care also has been linked to staving off cognitive decline.
“Our study shows that AI can be a valuable screening tool in detecting and diagnosing gum disease, allowing earlier intervention and better health outcomes for the population,” said Dr. Walter Yu-Hang Lam, one of the study’s lead researchers, in the Mobi Health report. Lam warned that barring regular checkups, many patients risk losing teeth to disease or paying for expensive rehab or surgery.
The study, which is the first to analyze AI’s ability to spot gingivitis, used over 500 images of gums in various conditions. In the United States, startups such as VideaHealth and Overjet are also developing AI-assisted dental care.
The research was a collaboration between several Asian Universities, including the Faculty of Dentistry at the University of Hong Kong and the Department of Computer Science at Hong Kong Chu Hai College.
The study noted that “further investigation and training are required” to improve the AI and move it towards clinical applications.
