While some question the effectiveness of telemedicine, many more critique the selfie as frivolous.

But selfies may play a key role in understanding our health and add to the effectiveness of telemedicine.

According to the authors of a new study recently published in the European Heart Journal, sending a “selfie” to your doctor could be a cheap and simple way of detecting heart disease.

Their research suggests that a computer algorithm can detect coronary artery disease by analyzing photographs of a person’s face. The technology can identify specific facial features that are already known to be associated with an increased risk of heart disease. These include thinning or grey hair, wrinkles, ear lobe creases, as well as small yellow deposits of cholesterol underneath the skin, usually around the eyelids, known as xanthelasmata; and fat and cholesterol deposits that appear as a hazy white, grey or blue opaque ring in the outer edges of the cornea (known as arcus corneae). Though these features are often visible to the naked eye, they are difficult for humans to use successfully to predict and quantify heart disease risk.

More than 6,800 people took part in the research, providing nurses with selfie photos, which were then analyzed with the algorithm. The computer analysis correctly predicted 80 percent of cases, which makes it just as accurate as standard tests.

Professor Zhe Zheng who led the research team from China’s National Centre for Cardiovascular Diseases, said the selfie screening tool could be a “cheap, simple and effective” way of identifying patients who need further treatment or tests. “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 through patients taking ‘selfies’ to perform their own screening,” he explained. “Our ultimate goal is to develop a self-reported application for high-risk communities to assess heart disease risk in advance of visiting a clinic.”

Co-researcher Professor Xiang-Yang Ji added: “The algorithm had 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.”

The researchers highlight three critical limitations.

First, they note the low specificity of the test, “we need to improve the specificity as a false positive rate of as much as 46 percent may cause anxiety and inconvenience to patients, as well as potentially overloading clinics with patients requiring unnecessary tests.”

Also, the test algorithm needs to be improved and validated in larger populations. It requires further refinement and external validation in other populations and ethnicities before it can be used as a screening tool to identify possible heart disease in people in the general population or in high-risk groups, which could be referred for further clinical investigations.

And lastly, there are key ethical issues in developing and applying these facial recognition technologies. The methodology raises ethical questions about the possible misuse of information. Unwanted dissemination of sensitive health record data that can easily be extracted from a facial photo can make the technology a significant threat to personal data protection. The authors of the research paper agree on this point. Prof. Zheng said: “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.”

It is said that everyone’s face tells a story. Perhaps one of the most important ones has to do with our health.

Dr. Tara Well is a psychology professor at Barnard College in New York City where she developed a mirror-based meditation called “a revelation” in the New York Times. She has taught hundreds of people how to use the mirror to awaken self-compassion, manage emotions, and improve face-to-face communication. Find out more at www.MirrorMeditation.com




Image courtesy of cottonbro.