Photo by Ketut Subiyanto from Pexels

BEIJING, China – Love taking selfies? You’re in luck! According to a new study in the European Heart Journal, selfies can do more than just show off your face. In fact, they might actually help your doctor diagnose heart disease. Scientists using a computer algorithm can detect coronary artery disease (CAD) using four pictures of a person’s face.

“To our knowledge, this is the first work demonstrating that artificial intelligence can be used to analyze faces to detect heart disease,” says lead researcher Zhe Zheng in a media release. “It is a step towards the development of a deep learning-based tool that could be used to assess the risk of heart disease, either in outpatient clinics or by means of patients taking ‘selfies’ to perform their own screening.”

Zheng is vice director of the National Center for Cardiovascular Diseases and vice president of Fuwai Hospital, Chinese Academy of Medical Sciences, and Peking Union Medical College in China.

Are the signs of heart disease on your face?

Certain facial features have been previously linked to higher risks for heart disease, including thinning or gray hair, wrinkles, or creases in the ear lobes. Other signs include xanthelasmata (bumpy yellow patches on the inside corners of the eyelids), and arcus cornea (gray or blue rings around the cornea). Despite these warning signals, the study finds it’s difficult for doctors to successfully diagnose heart disease by these features alone.

To develop their computer algorithm, researchers recruited 5,796 patients across eight Chinese hospitals between 2017 and 2019. All of the patients underwent angiograms, a blood vessel imaging procedure.

Researchers then take four photos (from the front, the sides, and overhead) before interviewing each patient about their medical histories. Radiologists also look at each patient’s angiogram to determine the extent of blood vessel narrowing. Blood vessel narrowing is an indicator of heart disease severity.

A successful test, but not perfect

Once the algorithm was created, study authors tested it on 1,013 patients across nine Chinese hospitals. They find their algorithm correctly identifies those with heart disease 80 percent of the time. Still, researchers caution their invention also has a very high false-positive rate of around 50 percent.

“The algorithm had a moderate performance, and additional clinical information did not improve its performance, which means it could be used easily to predict potential heart disease based on facial photos alone,” researcher Xiang-Yang Ji explains. “The cheek, forehead and nose contributed more information to the algorithm than other facial areas. However, we need to improve the specificity as a false positive rate of as much as 46% may cause anxiety and inconvenience to patients, as well as potentially overloading clinics with patients requiring unnecessary tests.”

Privacy concerns

While their findings are promising, the researchers note that ethical implications are a factor in developing and disseminating their technology. When it comes to a patient’s likeness and their personal photos, privacy is a major issue to address.

“Ethical issues in developing and applying these novel technologies is of key importance. We believe that future research on clinical tools should pay attention to the privacy, insurance and other social implications to ensure that the tool is used only for medical purposes,” Zheng concludes.

[fb_follow /]

About Brianna Sleezer

Our Editorial Process

StudyFinds publishes digestible, agenda-free, transparent research summaries that are intended to inform the reader as well as stir civil, educated debate. We do not agree nor disagree with any of the studies we post, rather, we encourage our readers to debate the veracity of the findings themselves. All articles published on StudyFinds are vetted by our editors prior to publication and include links back to the source or corresponding journal article, if possible.

Our Editorial Team

Steve Fink


Chris Melore


Sophia Naughton

Associate Editor