The latest technology trends: A selfie reveals the risk of death from cancer

Listen to the article. The audio text is automated, generated by an automated system

Specialized scientists have been able to invent a new tool based on artificial intelligence techniques. This tool can predict the probability of death for cancer patients, using a “selfie” photo that the patient takes of his own face, which is considered the easiest and simplest possible medical examination in this field.

A report published by the British newspaper Daily Mail, and viewed by Al Arabiya.net, said that scientists have developed a tool based on artificial intelligence capable of identifying patients most at risk of death, simply by looking at their faces. A simple selfie may soon help doctors predict whether a cancer patient will survive his disease.

Scientists have created an artificial intelligence tool that can detect patients most at risk of death, by analyzing an image of the patient's face.

In the tests conducted, more than half of the people classified as “highest risk” died within 90 days. In contrast, the death rate in the group classified as “least risk” did not exceed 2% during the same time period.

Experts believe that this technology may help doctors identify patients who are fit enough to undergo intensive cancer treatments, and those who may need a more moderate treatment approach.

This innovation came at the hands of American researchers at the Mass General Brigham Foundation, and they called the innovative tool (FaceSurvival). The tool is based on previous research indicating that cancer patients who appear older than their actual age are more likely to die.

But instead of estimating a patient's biological age, the new AI technology looks for subtle indicators in facial features that might reveal chances of survival.

In standard medical practice, doctors often make quick judgments about a patient's health just by looking at him or her; This is known as “visual assessment” which helps them estimate how weak or frail the patient is.

“Doctors already intuitively evaluate a patient's health based on their appearance,” says study co-author Dr. Grace Lee, an expert in colorectal surgery.

“Our tool provides a way to standardize and accurately measure this intuitive practice, which may contribute to improving the accuracy of medical predictions and supporting clinical decision-making,” she adds.

To develop this technology, researchers trained an artificial intelligence system using more than 40 million publicly available facial images. They then trained the FaceSurvival system to predict death rates using images of more than 34,000 cancer patients.

These results were published in the journal "The Lancet Digital Health", and could radically change the way doctors evaluate the condition of patients before starting treatment.