A new algorithm has been developed that capable to correctly detect coronary artery disease with an 80% success rate by analyzing the facial features of participants in a study.
Signs that are showing that a person could be suffering from poor cardiovascular health are like alopecia, (hair loss), xanthelasmata (yellow eyelids), and arcus cornea (an opaque ring around the eye’s cornea).
Researchers in China have invented a “deep learning” algorithm that can determine an individual’s risk of heart disease by being shown just four photos of them.
Expert says the algorithm needs more refinement before it can be rolled out as a useful tool to diagnose a heart attack and it has the potential to “revolutionize medicine”.
It is also was trained to analyze the four images and assess each person’s risk of heart risk heart disease. 1,000 patients were also studied to validate the findings.
The algorithm has correctly detected heart disease in 80% of the group and the result has been published in the European Heart Journal. it was also capable of correctly detecting patients without coronary artery disease 61% of the time.
Xiang-Yang Ji, one of the researchers working on the study said, “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,”.
Source: Daily Star
