A study suggests that it is possible for a deep learning computer algorithm to detect coronary artery disease (CAD) by analysing four photographs of a person’s face.
More than 6,800 people in China were selected to take part in the research, providing nurses with facial images – one frontal, two profiles and one view of the top of the head – as well as data on their socio-economic status, lifestyle and medical history.
This information was used to create, train and validate the deep learning algorithm, checking for indications of coronary artery disease, such as grey hair, ear lobe crease and xanthelasmata, which are small, yellow deposits of cholesterol underneath the skin, usually seen around the eyelids.
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
But scientists behind the project say the system still requires further development and needs to be tested in larger groups of people from different ethnic backgrounds.
Research lead Professor Zhe Zheng, from China’s National Centre for Cardiovascular Diseases, said such a screening tool could be a “cheap, simple and effective” way of identifying patients who need further investigation.
“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,” 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.
“However, the algorithm requires further refinement and external validation in other populations and ethnicities.”
Co-researcher Professor Xiang-Yang Ji, added: “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.
“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.”
As well as the need for further testing, scientists note ethical issues around data privacy is a “key importance”.
The paper was published in the European Heart Journal.
