His birth date does not necessarily reveal the age of his body biologically. And artificial intelligence (AI) is proposed, of a simple photo, to reveal this age, the renowned scientific review Digital Health informs you.
Algorithm called deep learning, Faceage trained in tens of thousands of photos. In particular, it made it possible to determine that cancer patients had an average of five more years, from an organic point of view, than healthy people.
Scientists are increasingly considering biological age, that is, the age of the cells, differs from the chronological age, the existence of an individual. In their study published in Lancet Digital Health, researchers believe Faceage could help doctors to determine a patient’s real capacity to withstand heavy treatments without risk. And I could opt, if necessary, for less invasive alternatives.
Provide data from a simple selfie
“Our hypothesis is that Faceage could be used as a biomarker in the treatment of cancer to quantify the biological age of a patient and help the doctor make these difficult decisions,” said the co -author of the Raymond Mak study, a Brigham Oncologist general, a Harvard University Hospital.
For example: a 75 -year -old man whose biological age is 65 years old and a 60 -year -old person whose biological age is 70 years old. Invasive radiotherapy could actually be appropriate for the first, but risky for the second.
The same logic could guide decisions on cardiac surgery, hip prostheses or the final attention of life. Human beings age at different rhythms depending on their genes, stress, physical exercise and certain habits such as smoking or drinking alcohol.
If faces genetic tests can already reveal the wear of the DNA over time, Faceage promises to provide data from a simple selfie. This tool was trained at 58,851 portraits for adults over 60 years a priori healthy, selected public data.
Then it was tested in 6,196 cancer patients in the United States and the Netherlands, from photos taken just before radiotherapy. Result: patients with malignant tumors seem to be on average 4.79 years older than their chronological age.
Among cancer patients, the higher this figure, the greater the possibilities of survival, even after taking into account the official age, sex and the type of tumor. And the risk increases abruptly for any person whose biological age exceeds 85 years.
Ethical risks
For Faceage, the signs generally associated with old age, such as gray hair or baldness, import less than subtle in the muscle tone of the face.
Therefore, the tool allows to improve the degree of precision of doctors. Eight of them were invited to examine the photos of terminal cancer patients and guess who would die in the six months. Its success rate was barely higher than an evaluation in the ladle. But with Faceage data, their predictions have improved significantly.
For the anecdote, Faceage estimated in 43 the biological era of actor Paul Rudd, in a photo taken when I was 50.
IA tools are sometimes criticized for being interested in whites. Raymond Mak, co -author of the study, claims to have noticed any significant racial bias in Faceage predictions. The group also continues to train for a second generation model in 20,000 patients.
But this technological advance is not, so often, without their concerns: it could seduce insurers or employers who are still trying to evaluate the risks as well as possible.
Co -author of the study and head of AI in the medical programs of General Mass Brigham, Hugo Aerts demands that “guarantee that these technologies are only used in the patient’s interest.”
Source: BFM TV
