Algorithms could play role in predicting risk of tooth loss

20 July 2021

A study conducted by researchers at the Harvard School of Dental Medicine has developed machine-learning algorithms that consider factors such as socioeconomic status in determining teeth at risk. 

The study, detailed in a report on the Dental Tribune, sought to expand on how much influence socioeconomic factors have on dental health beyond the usually allowed for variable of age and dental care. 

As is well known, regular dental checkups by a dentist are a key factor in catching oral health issues before they develop into a serious problem, allowing for early intervention and treatment. 

But for many people in lower socioeconomic circumstances, particularly in the U.S. where the Dental Tribune notes “adult dental coverage is not an essential health benefit in most public health insurance programs”, many people don’t see a dentist until dental disease is well advanced at which point “extraction becomes the most affordable option”. 

While machine-learning methods are currently employed to assist in making clinical decisions, they are not a routine part of determining oral health outcomes, something this study hopes it will help to rectify. 

The development and testing of five algorithms led to important findings, says lead author Dr. Hawazin Elani, assistant professor of oral health policy and epidemiology at HSDM. 

“Our analysis showed that while all machine-learning models can be useful predictors of risk, those that incorporate socioeconomic variables can be especially powerful screening tools to identify those at heightened risk for tooth loss." 

“This work highlights the importance of social determinants of health. Knowing the patient’s education level, employment status, and income is just as relevant for predicting tooth loss as assessing their clinical dental status,” she added. 

For more on this study, read “Machine-learning algorithms may help in predicting tooth loss”