By John Salak –
Selfies don’t exactly have a great reputation. They are kind of an exercise in look at me self-obsession. This, of course, doesn’t stop them from being popular with everyone from kings to presidents, celebrities and, of course, the self-absorbed. Well, the image of selfies may have just gotten a boost—no pun intended.
A hot-off-the-presses study published in European Heart Journal reports that the common selfie may be a cheap and effective way to detect heart disease. A two-year study of more than 6,000 patients from nine Chinese cities discovered that using a deep learning computer algorithm can help detect coronary artery disease (CAD) by analyzing four photographs 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. 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,” said Professor Zhe Zheng, who led the research and is vice director of the National Center for Cardiovascular in Beijing.
Zheng acknowledged that more research is needed. But he noted that program’s ultimate goal is to develop a self-reporting application for high risk communities to assess heart disease risk before individuals go to a medical facility.
The facial recognition effort builds off existing research that shows certain facial features are associated with an increased risk of heart disease. These features include thinning or grey hair, wrinkles, ear lobe crease, xanthelasmata (small, yellow deposits of cholesterol underneath the skin, usually around the eyelids) and arcus corneae (fat and cholesterol deposits that appear as a hazy white, grey or blue opaque ring in the outer edges of the cornea).
Despite this information, it is difficult for individuals with any of these characteristics to predict and quantify their heart disease risk. The facial recognition algorithm is designed to take away the guess work by analyzing four images of an individual, one frontal, two profiles and one view from the top of a head. The Chinese study found the algorithm approach was able to correctly identify heart disease in 80 percent of the individuals studied. It also correctly cleared individuals of disease risk over 60 percent of the time.
“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. However, 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,” said Prof. Zheng, Professor Xiang-Yang Ji, director of the Brain and Cognition Institute at Beijing’s Tsinghua University.
Want more proof selfies have some real value? Getting real is the key. An earlier study out of the University of California, Irvine, found that selfies can have a positive impact on a person’s mood provided they are not faking their smiles and feel-good looks.
The study focused on, not surprisingly, college students who were assigned to take three different types of photos each day: smiling selfies, photos of things that made them happy and snaps of the things that they believed would make others happy. They were then asked to record their moods immediately afterwards.
The three-week study revealed that students only reported positive emotional side effects when they didn’t feel like they were faking or forcing a smile. Students also reported that “natural smiles” came more easily as the study progressed.
The Chinese and U.S. research doesn’t, of course, cast selfies in an entirely new light. But it probably buffs their image a bit—pun intended.
