AI researchers craft selfie-based system for estimating biological age and cancer survival prognosis.
New and Groovy AI Tool Might Predict Your Health Ages, Bro
Yeah, you heard it right, buddy! Scientists have cooked up a new trick, and it's powered by something called artificial intelligence, or AI for short. This badass tool, named FaceAge, can guess how fast you're aging - just from a selfie! It ain't about putting you on the spot, man, it's all about your health.
So, these researchers used around 59,000 goofy faces (yeah, they had a ball with that) and used 'em to train this AI model to figure out people's "biological ages." That's their age based on their cellular health, not the date they popped out of mama's belly.
Then, they took FaceAge on a spin with about 6,200 cancer patients. Guess what? They looked five years older than their actual ages, and they had higher FaceAge readings than healthy peeps. Interesting, huh?
Not just that, but FaceAge also helped doctors make better predictions about the short-term life expectancies of cancer patients receiving palliative care. Only the best docs' predictions compared to FaceAge alone on accuracy.
Fun fact: Turns out, looking older compared to your actual age can be a big deal, according to Hugo Aerts, one of the study's authors and director of the AI in medicine program at Mass General Brigham in the US.
So, what's up next for FaceAge? The bods say it could one day help doctors and cancer patients make decisions about end-of-life care. But that's not all: it could snoop out a variety of health issues too. Dr. Ray Mak, one of the study authors and a cancer physician at Mass General Britham, said FaceAge could someday function as an "early detection system" for poor health.
"Since we're increasingly thinking about different chronic diseases as diseases of ageing, it's even more crucial to be able to accurately predict an individual's ageing trajectory," Mak said.
Let's talk limitations: Yeah, FaceAge ain't perfect. It was primarily trained on white people, and it's unclear how factors like lighting or makeup could sway the results. The researchers are now expanding their project to include more hospitals and cancer patients at different stages of the disease, as well as testing FaceAge's accuracy against datasets with plastic surgery and makeup.
As cool as FaceAge may sound, actually seeing it in action at the doc's office is still a long way off, says Mak. But he believes it "opens the door to a whole new realm of biomarker discovery from photographs."
Related read:
- Cancer before age 50 is increasing. These are the types rising among younger people
- Men's hair loss treatment linked to rare risk of suicidal thoughts, EU medicines regulator says
- Bill Gates pledges to donate 'virtually all' his fortune to global health causes over next 20 years
- This revolutionary AI tool, FaceAge, harnesses the power of artificial intelligence to predict one's rate of aging, based on a selfie.
- The researchers behind FaceAge analyzed around 59,000 selfies to train the AI model, focusing on determining individuals' "biological ages."
- In a study with about 6,200 cancer patients, FaceAge revealed that patients looked five years older than their actual ages and had higher FaceAge readings than healthy individuals.
- FaceAge was found to aid doctors in making more accurate predictions about the short-term life expectancies of cancer patients receiving palliative care.
- According to Hugo Aerts, one of the study's authors, looking older compared to one's actual age could signal various health issues.
- The potential applications of FaceAge go beyond cancer, as it could one day serve as an early detection system for a range of health-related conditions, including mental health and aging-related diseases.
