Health and Me

Health And Me Desk

New AI Tool Uses Facial Photos To Predict Cancer Patients’ Survival Risk

AI Facial Recognition Technology

A single photograph of someone’s face might carry real clues about their health and how long they’re likely to live, at least according to new AI tools built by researchers at Mass General Brigham in Boston.

The team trained a large AI foundation model called FAHR-Face, short for Foundation Artificial Intelligence for Health Recognition, on more than 40 million facial images. 

From that base model, they built two specialised tools: FAHR-FaceAge, which estimates a person’s biological age from a single photo, and FAHR-FaceSurvival, fine-tuned on 34,389 photos of cancer patients to predict survival risk directly from facial appearance.

“I was pretty surprised to find out that we could pick up signs of mortality risk from just a facial photograph,” corresponding author is Dr. Raymond Mak, a radiation oncologist at Mass General Brigham Cancer Institute told CNN. The study is published in The Lancet Digital Health.

<h2>What the two tools actually look at</h2>

The two algorithms focus on entirely different parts of the face. “The 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,” Mak said, while “the mortality risk prediction algorithm is looking at a totally different part of the face... the bridge of the nose and the area under the eyes.”

<strong>Also Read:</strong> <a href="https://www.healthandme.com/health-wellness/adhd-linked-to-71-higher-risk-of-death-suicide-and-injuries-among-top-concerns-article-156375921" data-type="tilCustomLink" target="_blank">ADHD Linked To 71% Higher Risk Of Death; Suicide And Injuries Among Top Concerns</a>

Among 122 cancer patients flagged by FAHR-FaceSurvival as high-risk, 52.5% died within 90 days, compared with about 2% of the 975 patients in the lowest-risk group. Separately, 21% of patients whose biological age came back more than 20 years older than their actual age died within 90 days, against about 6% of those whose biological age was at least 10 years younger than their chronological age.

The researchers also found that cosmetic changes, including surgery, Botox, or makeup, didn’t throw off the models’ performance, according to the Mass General Brigham release.

<h2>An eerie echo of ancient medicine</h2>

The facial regions both AI models rely on, the nose, temples, and the area around the eyes, closely match what the Greek physician Hippocrates described around 400 BC in his Book of Prognostics as signs of approaching death: “the nose sharp, the eyes sunken, the temples fallen in.” 

Mak told CNN the algorithms had no exposure to Hippocrates’ text and were trained purely on photographs and outcomes data. “Hearing Hippocrates echo over millennia in our algorithms was very eerie,” he said.

Outside experts urged caution. Dr. Wilbur Lam of Emory University, who wasn’t involved in the study, called it “an extremely compelling study” with robust associations, but said its “true clinical utility... will need to be demonstrated prospectively,” and flagged open questions about how well it performs across different facial features, skin tones, and age groups.

Miroslaw Bober of the University of Surrey, also not involved in the study, said the findings shows “convincing evidence” of a statistical link but cautioned that “predicting an outcome is not the same as explaining it.” 

He noted the study never tested whether the AI model picks up anything a doctor’s own assessment wouldn’t, since doctors’ general health evaluations weren’t measured for comparison. “This is a promising proof of concept, but it is not ready for clinical use,” Bober said.

Health Conditions A-Z

health

ai-facial-recognition-technology

ai facial recognition

ai biological age estimation

facial analysis and health risks

ai cancer survival prediction

artificial intelligence in healthcare

times-network-india-health-summit-awards-2026-to-focus-on-innovation-access-self-reliance-in-healthcare

Times Network India Health Summit & Awards 2026 To Focus On Innovation, Access & Self-Reliance In Healthcare

whos-health-inequality-report-shows-how-income-education-and-gender-influence-noncommunicable-diseases-risk

WHO's Health Inequality Report Shows How Income, Education And Gender Influence Noncommunicable Diseases Risk

Health & Wellness

8 Sit-Up Variations to Strengthen Your Core and Build Stability

Benefits Of Ayurvedic Health Supplement Ashwagandha

9 Anti-Inflammatory Breakfast Options You Should Try

5 Foods You Should Avoid For PCOS, Says Gynecologist

Love Sitting With Your Legs Crossed? Here’s You Should Avoid It

6 Daily Foods That Are Secretly Increasing Your Calories

9 Brain Boosters You Should Do Everyday

Hip Exercises That Will Keep You Flexible As You Age

9 Leg Exercises Office Workers’ Should Do At Home

Benefits of Having Herbal Tea Every Morning

9 Daily Habits That Boost Your Brain Power

Lower-Body Exercises That Are Game-Changers

How Drinking Apple Cider Vinegar Helps You

Aging Myths You Should Never Believe

Superfoods That Support Your Gut Health

What Happens To Your Body When You Eat Instant Noodles Every Day?

Health Issues Premature Babies Often Face

Exercises Office Workers Should Do For Their Heart Health

Reasons Why You Should Add Raw Turmeric To Your Diet

Benefits Of Drinking Milk At Night: Why You Should Do It

Food That Provides Vitamin B12 Naturally In Your Diet

Surprising Health Benefits Of Fenugreek Seeds

9 Superfoods You Should Eat For Your Brain Health

What Does Mental Health Support Look Like At Work?

Long Stretches You Should Do To Unwind From Your Day

Colon Cancer In Young Adults: Early Symptoms You Should Know

Health Benefits Of Eating Dry Fruits Everyday

Are You At Risk For Fried Rice Syndrome?

These Tests Reveal How Well You Are Aging

Lower-Back Exercises You Should Do After A Long-Day's Work

Children’s Diet – What Kids Need To Eat For Immunity Building

Common Diabetes Myths That Could Hurt Your Health

Love Spicy Food? Here’s How It Affects Your Health

Superfood List: Veggies And Fruits You Must Have For Immunity

Foods People With IBS Should Avoid

Exercises To Improve Digestion

Easy Work Lunches You Can Make In The Morning

Hunger Vs Craving: Difference Explained In 60 seconds

These Things Can Cause Your Heart To Age Faster

High Carb Foods That Are Actually Healthy

A single photograph of someone’s face might carry real clues about their health and how long they’re likely to live, at least according to new AI tools built by researchers at Mass General Brigham in Boston.What the researchers builtThe team trained a large AI foundation model called FAHR-Face, short for Foundation Artificial Intelligence for Health Recognition, on more than 40 million facial images. From that base model, they built two specialised tools: FAHR-FaceAge, which estimates a person’s biological age from a single photo, and FAHR-FaceSurvival, fine-tuned on 34,389 photos of cancer patients to predict survival risk directly from facial appearance.“I was pretty surprised to find out that we could pick up signs of mortality risk from just a facial photograph,” corresponding author is Dr. Raymond Mak, a radiation oncologist at Mass General Brigham Cancer Institute told CNN. The study is published in The Lancet Digital Health.What the two tools actually look atThe two algorithms focus on entirely different parts of the face. “The 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,” Mak said, while “the mortality risk prediction algorithm is looking at a totally different part of the face... the bridge of the nose and the area under the eyes.”Also Read: ADHD Linked To 71% Higher Risk Of Death; Suicide And Injuries Among Top ConcernsThe resultsAmong 122 cancer patients flagged by FAHR-FaceSurvival as high-risk, 52.5% died within 90 days, compared with about 2% of the 975 patients in the lowest-risk group. Separately, 21% of patients whose biological age came back more than 20 years older than their actual age died within 90 days, against about 6% of those whose biological age was at least 10 years younger than their chronological age.The researchers also found that cosmetic changes, including surgery, Botox, or makeup, didn’t throw off the models’ performance, according to the Mass General Brigham release.An eerie echo of ancient medicineThe facial regions both AI models rely on, the nose, temples, and the area around the eyes, closely match what the Greek physician Hippocrates described around 400 BC in his Book of Prognostics as signs of approaching death: “the nose sharp, the eyes sunken, the temples fallen in.” Mak told CNN the algorithms had no exposure to Hippocrates’ text and were trained purely on photographs and outcomes data. “Hearing Hippocrates echo over millennia in our algorithms was very eerie,” he said.Not ready for the clinic yetOutside experts urged caution. Dr. Wilbur Lam of Emory University, who wasn’t involved in the study, called it “an extremely compelling study” with robust associations, but said its “true clinical utility... will need to be demonstrated prospectively,” and flagged open questions about how well it performs across different facial features, skin tones, and age groups.Miroslaw Bober of the University of Surrey, also not involved in the study, said the findings shows “convincing evidence” of a statistical link but cautioned that “predicting an outcome is not the same as explaining it.” He noted the study never tested whether the AI model picks up anything a doctor’s own assessment wouldn’t, since doctors’ general health evaluations weren’t measured for comparison. “This is a promising proof of concept, but it is not ready for clinical use,” Bober said.

ai tool uses facial photos to estimate biological age and predict cancer patients’ survival risk

About Us

Contact Us

Terms & Conditions

Privacy Policy

Company

Health and Me is a premium website with content written and curated to function as a handbook for all Health concerns.

New AI Tool Uses Facial Photos To Predict Cancer Patients’ Survival Risk

WHO's Health Inequality Report Shows How Income, Education And Gender Influence Noncommunicable Diseases Risk

ADHD Linked To 71% Higher Risk Of Death; Suicide And Injuries Among Top Concerns

Morning Walks After 60: Are You Doing Enough To Protect Your Bones?

Health Conditions A-Z

Times Network India Health Summit & Awards 2026 To Focus On Innovation, Access & Self-Reliance In Healthcare

New AI Tool Uses Facial Photos To Predict Cancer Patients’ Survival Risk

WHO's Health Inequality Report Shows How Income, Education And Gender Influence Noncommunicable Diseases Risk