\n A simple selfie could hold surprising clues to your overall health and longevity, especially among people with cancer.\n <\/p>\n
\n Researchers at Mass General Brigham in Boston have developed artificial intelligence models that they say can predict a cancer patient\u2019s biological age and chances of survival using nothing more than a single photograph of their face.\n <\/p>\n
\n The research, published Monday in the journal The Lancet Digital Health<\/a>, suggests that facial analysis could become an additional tool for doctors to consider when evaluating a patient\u2019s chances of survival and when deciding which treatment approaches may work best for their cancer patients.\n <\/p>\n \n \u201cI was pretty surprised to find out that we could pick up signs of mortality risk from just a facial photograph,\u201d said study author Dr. Raymond Mak, a radiation oncologist at Mass General Brigham Cancer Institute and a faculty member in the Artificial Intelligence in Medicine program at Mass General Brigham.\n <\/p>\n \n The AI models \u2013 trained on more than 40 million facial images \u2013 specifically assess different aspects of the face to gauge a cancer patient\u2019s overall health and biological age. Unlike chronological age, which measures the number of years a person has lived, biological age reflects how well the body has aged at the cellular and physical level.\n <\/p>\n \n \u201cThe age estimation algorithm is looking at the area around the temples, the area on the forehead, above the eyes and then what we call the nasolabial fold, the line that connects the nose down to the corner of your mouth,\u201d Mak said of what parts of the face the AI models consider when assessing biological age.\n <\/p>\n \n \u201cIn contrast, the mortality risk prediction algorithm is looking at a totally different part of the face,\u201d Mak said. \u201cIt\u2019s looking at the bridge of the nose and the area under the eyes.\u201d\n <\/p>\n \n Eerily, the same regions of the face that the AI model assesses to predict biological age and survival are the same parts that Greek physician and philosopher Hippocrates referenced in the Book of Prognostics<\/a>, written around 400 B.C., when he described \u201cthe nose sharp, the eyes sunken, the temples fallen in\u201d as signs of muscle wasting<\/a> and mortality risk.\n <\/p>\n \n \u201cTo think that our algorithms might be replicating that wisdom of Hippocrates from millennia ago was mind-blowing to us,\u201d Mak said.\n <\/p>\n \n The AI algorithms had no awareness of Hippocrates\u2019 ancient texts, because \u201cour algorithms are trained purely on face photographs and then whether somebody died or not, or their age,\u201d Mak said.\n <\/p>\n \n \u201cIt does not factor in the text, knowledge or wisdom that\u2019s aggregated on the internet,\u201d he added. \u201cSo hearing Hippocrates echo over millennia in our algorithms was very eerie.\u201d\n <\/p>\n \n Mak and his colleagues originally built a robust AI model called the Foundation Artificial Intelligence for Health Recognition-Face (FAHR-Face) that was trained on more than 40 million facial images spanning diverse ages and ethnic backgrounds.\n <\/p>\n \n The model was then fine-tuned and used as a foundation to build two other models that could perform specific tasks: The FAHR-FaceAge model estimates the biological age of someone based on a single photo, and the FAHR-FaceSurvival model predicts a cancer patient\u2019s chances of survival by combining facial features with other clinical information.\n <\/p>\n \n With the FAHR-FaceSurvival model, the researchers found that among 122 cancer patients who were indicated by the model to have a high risk of death, more than half \u2013 52.5% \u2013 died within 90 days of the assessment, as predicted. In comparison, only about 2% of the 975 patients in the lowest-risk FAHR-FaceSurvival group died within 90 days.\n <\/p>\n \n When evaluating the FAHR-FaceAge model, the researchers found that 21% of the 1,060 patients whose biological age was more than 20 years above than their chronological age died within 90 days. In comparison, about 6% of the 4,195 patients with biological ages at least 10 years younger than their chronological age died within 90 days.\n <\/p>\n \n The researchers found that cosmetic changes to the face \u2013 such as surgery, injectables like Botox or makeup \u2013 did not affect the AI models\u2019 performance.\n <\/p>\n \n The study authors emphasize that their AI models are not intended to replace physicians or existing clinical evaluations. Instead, they describe the technology as an emerging tool that could someday help inform a doctor\u2019s assessment of a patient\u2019s health or their decision-making around treatment options.\n <\/p>\n \n \u201cIf we can pick up accelerated aging or higher mortality scores early, we might be able to screen for those or identify patients who may benefit from further testing for serious conditions earlier,\u201d Mak said.\n <\/p>\n \n And while the new study was conducted only among cancer patients, Mak said more research could reveal whether similar findings may emerge among otherwise healthy people who may be interested in their longevity.\n <\/p>\n \n The study\u2019s use of AI technology is fascinating but still needs to be evaluated clinically, said Dr. Wilbur Lam, research chair and professor of pediatrics and biomedical engineering at Emory University.\n <\/p>\n \n \u201cThis is an extremely compelling study that stems from a large data set and its associations between facial images and biological age as well as cancer survival risk appear to be robust. Its true clinical utility, however, will need to be demonstrated prospectively,\u201d Lam, who was not involved in the study, said in an email.\n <\/p>\n \n \u201cMoreover, as the authors themselves allude to, whether this tool can be accurately used for specific subpopulations remains a question,\u201d he said. \u201cFor example, how strong the effects are for people with specific facial features, skin color, age groups will also need to be prospectively tested in order for the technology to be clinically implemented.\u201d\n <\/p>\n