New research uses artificial intelligence to analyse facial photos.
Selfies are a great way to capture the incidental moments of your life, but now they might be able to play a role in saving your life.
A new study has found that sending a selfie to your doctor could be a cheap and simple way of detecting heart disease in the not too distant future.
Using artificial intelligence, according to the study, it was possible to show that a computer algorithm was able to analyse four different photographs of a person’s face and detect the presence of coronary artery disease.
The researchers said the tool had the potential to be used as a screening device that could identify possible heart disease in people in the general population, or in high-risk groups, who could then be referred for further clinical investigation.
The algorithm still needs to be developed further and tested in larger groups of people from different ethnic backgrounds, though, according to the researchers.
"To our knowledge, this is the first work demonstrating that artificial intelligence can be used to analyse faces to detect heart disease,” said lead researcher Professor Zhe Zheng.
“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. This could guide further diagnostic testing or a clinical visit.
"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. This could be a cheap, simple and effective (way) of identifying patients who need further investigation."
It is already known that certain facial features are associated with an increased risk of heart disease. These include:
- thinning or grey hair
- creases in the ear lobes,
- small yellow deposits of cholesterol deposits underneath the skin, usually around the eyelids
- fat and cholesterol deposits that appear as a hazy white, grey or blue opaque ring in the outer edges of the cornea.
However, these facial features are difficult for humans to use successfully to predict and quantify heart disease risk.
The study analysed 5796 patients from eight hospitals in China between July 2017 and March 2019 and trained research nurses took four facial photos, one frontal, two profiles and one view of the top of the head.
Radiologists reviewed the patients’ angiograms and assessed the degree of heart disease and information that was used train and validate the deep learning algorithm.
The researchers then tested the algorithm on a further 1013 patients from nine hospitals in China, enrolled between April 2019 and July 2019.
They found that the algorithm out-performed existing methods of predicting heart disease risk, correctly detecting heart disease in 80 per cent of cases.
Would you ever send selfies to your doctor? Would you trust a computer to assess your health risk? Are you worried about the insurance and privacy implications of this technology?
If you enjoy our content, don’t keep it to yourself. Share our free eNews with your friends and encourage them to sign up.
Join YOURLifeChoices, it’s free
- Receive our daily enewsletter
- Enter competitions
- Comment on articles