How old are you, really? AI uses headshots to predict biological age and health risks
That intuitive assessment may soon get an AI upgrade.
FaceAge, a deep learning algorithm described Thursday in The Lancet Digital Health, converts a simple headshot into a number that more accurately reflects a person's biological age rather than the birthday on their chart.
Trained on tens of thousands of photographs, it pegged cancer patients on average as biologically five years older than healthy peers. The study's authors say it could help doctors decide who can safely tolerate punishing treatments, and who might fare better with a gentler approach.
'We hypothesize that FaceAge could be used as a biomarker in cancer care to quantify a patient's biological age and help a doctor make these tough decisions,' said co-senior author Raymond Mak, an oncologist at Mass Brigham Health, a Harvard-affiliated health system in Boston.
Consider two hypothetical patients: a spry 75-year-old whose biological age clocks in at 65, and a frail 60-year-old whose biology reads 70. Aggressive radiation might be appropriate for the former but risky for the latter.
The same logic could help guide decisions about heart surgery, hip replacements or end-of-life care.
Sharper lens on frailty
Growing evidence shows humans age at different rates, shaped by genes, stress, exercise, and habits like smoking or drinking. While pricey genetic tests can reveal how DNA wears over time, FaceAge promises insight using only a selfie.
The model was trained on 58,851 portraits of presumed-healthy adults over 60, culled from public datasets.
It was then tested on 6,196 cancer patients treated in the United States and the Netherlands, using photos snapped just before radiotherapy. Patients with malignancies looked on average 4.79 years older biologically than their chronological age.
Among cancer patients, a higher FaceAge score strongly predicted worse survival – even after accounting for actual age, sex, and tumor type – and the hazard rose steeply for anyone whose biological reading tipped past 85.
Intriguingly, FaceAge appears to weigh the signs of aging differently than humans do. For example, being gray-haired or balding matters less than subtle changes in facial muscle tone.
FaceAge boosted doctors' accuracy, too. Eight physicians were asked to examine headshots of terminal cancer patients and guess who would die within six months. Their success rate barely beat chance; with FaceAge data in hand, predictions improved sharply.
The model even affirmed a favorite internet meme, estimating actor Paul Rudd's biological age as 43 in a photo taken when he was 50.
Bias and ethics guardrails
AI tools have faced scrutiny for under-serving non-white people. Mak said preliminary checks revealed no significant racial bias in FaceAge's predictions, but the group is training a second-generation model on 20,000 patients.
They're also probing how factors like makeup, cosmetic surgery or room lighting variations could fool the system.
Ethics debates loom large. An AI that can read biological age from a selfie could prove a boon for clinicians, but also tempting for life insurers or employers seeking to gauge risk.
'It is for sure something that needs attention, to assure that these technologies are used only in the benefit for the patient,' said Hugo Aerts, the study's co-lead who directs MGB's AI in medicine program.
Another dilemma: What happens when the mirror talks back? Learning that your body is biologically older than you thought may spur healthy changes – or sow anxiety.
The researchers are planning to open a public-facing FaceAge portal where people can upload their own pictures to enrol in a research study to further validate the algorithm. Commercial versions aimed at clinicians may follow, but only after more validation. — AFP
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Malay Mail
34 minutes ago
- Malay Mail
New blood test with 92pc accuracy: Spotting ovarian cancer early, even when symptoms seem harmless
WASHINGTON, Aug 15 — An experimental blood test detects early-stage ovarian cancer in patients with vague symptoms that would likely be misdiagnosed using currently available methods, researchers said in a new report. Ovarian cancer is the fifth leading cause of cancer-related deaths among women, largely due to delays in diagnosis until after the disease has spread in the body, at which point it's harder to treat, according to the researchers. More than 90 per cent of patients with early-stage ovarian cancer experience symptoms that can be mistaken for benign conditions, such as bloating, abdominal pain, and digestive issues. Not only have there been no reliable blood tests for these patients, but existing invasive tests often miss early-stage ovarian tumors, the researchers noted in Cancer Research Communications. Using machine learning tools, the researchers identified multiple biomarkers – from across a wide range of molecules and processes in the body – that could be combined into a single test that detects all sub-types of the disease, at all stages, they said. Trialed at a large medical center on blood samples from nearly 400 women with possible symptoms of ovarian cancer, the test was 92 per cent accurate at identifying those with any stage of ovarian cancer and 88 per cent accurate at identifying those with Stage I or Stage II disease, according to the report. Oriana Papin-Zoghbi, chief executive officer of the company developing the new test – Denver, Colorado-based AOA Dx – said the findings show its potential to aid 'in making faster, more informed decisions for women who need urgent clarity during a challenging diagnostic process.' Preventing elders' 'leaky brain' might stave off cognitive decline The blood-brain barrier gets leakier with age, contributing to memory deficits - and new discoveries of the mechanisms behind this process might lead to new ways of preventing cognitive decline, researchers say. The blood-brain barrier - a layer of tightly-junctioned cells lining the brain's blood vessels - keeps viruses, bacteria and toxins out while allowing helpful nutrients and chemicals in. 'Basically, it's a mechanism that separates the central nervous system from everything else,' study leader Yulia Komarova of University of Illinois Chicago said in a statement. In previous research, Komarova and her colleagues found that removing a protein called N-cadherin from the cells lining blood vessels made the vessels leakier in the brain. In a new study published in Cell Reports, her team found that mice without N-cadherin could learn tasks as well as normal mice, but they quickly forgot what they learned. In further experiments, they found when N-cadherin proteins on neighboring cells interact, they stabilize a protein, called occludin, which helps form the tight junctions in the blood-brain barrier that maintains the integrity of the blood-brain barrier. Examining human brain tissue collected during epilepsy surgeries, the researchers found that samples from patients in their 40s and 50s had lower levels of N-cadherin and occludin than samples from patients in their late teens and 20s. Komarova's team is now investigating whether steps in the signaling pathway activated by N-cadherin could be therapeutic targets. 'This paper shows that actually there might be a much bigger therapeutic window for treatment of any age-related cognitive decline condition,' she said. Wildfire smoke deaths in Europe may be underestimated Previous studies may have underestimated the number of deaths related to wildfire smoke in Europe by as much as 93 per cent, according to a report in The Lancet Planetary Health. In new research, using daily mortality records from 654 contiguous regions in 32 European countries, researchers found that for every 1 microgram per cubit meter increase in wildfire smoke particles, all-cause mortality rose by 0.7 per cent, respiratory mortality by 1 per cent, and cardiovascular mortality by 0.9 per cent. Annually since 2004, short-term exposure to wildfire pollution was responsible for an average of 535 deaths from all causes, the researchers calculated – while estimates in previous studies had put that number at around 38 deaths per year, they said. 'Human-driven climate change is one of the main causes of the rising frequency and intensity of wildfires, as it creates favorable conditions for their spread and increases the number of days with very high or extremely high fire risk,' study leader Anna Alari of the Barcelona Institute for Global Health said in a statement. 'Improving estimates of (wildfire smoke related) mortality will help better track the burden of this climate change-related threat to public health.' A separate study found that as wildfire pollution levels rise, firefighters' hearts work harder, researchers wrote in Circulation Arrhythmia and Electrophysiology. After fighting the Park Fire in California, firefighters' heart rate at rest would rise by an average of 1.4 beats per minute for every 10-ug/m3 increase in particulate matter. Although the increase in resting heart rate was modest, and the rate remained within normal levels, even slight elevations have been associated with increased cardiovascular morbidity and mortality over time in large population studies. — Reuters
Free Malaysia Today
34 minutes ago
- Free Malaysia Today
S&P 500, Dow futures climb on rate-cut expectations, UnitedHealth jumps
Dow E-minis were up 0.63% and S&P 500 E-minis were up 0.06%. (EPA Images pic) NEW YORK : Futures tracking the Dow and the S&P 500 were higher today, underpinned by expectations of an interest rate cut in September, while UnitedHealth surged after Berkshire Hathaway raised its stake in the health insurer. UnitedHealth Group gained more than 12% in premarket trading after Warren Buffett's company revealed a new investment in the health insurer, while a securities filing also showed Michael Burry's Scion Asset Management included bullish positions in the company. Rising costs in the broader healthcare sector and a about 46% slump in heavyweight UnitedHealth's shares this year have left the blue-chip Dow lagging its Wall Street peers on the road to record highs. This week, however, the healthcare sector is the top performer on the benchmark S&P 500 and is on track for its best weekly performance in three. Other insurers, including Elevance, Centene and Molina added more than 4.4% each before the bell today. More broadly, the main US stock indexes are on track for their second week of gains, buoyed by expectations that the Federal Reserve (Fed) could restart its monetary policy easing cycle with a 25-basis-point interest rate cut in September. The central bank last lowered borrowing costs in December and said US tariffs could add to price pressures. However, recent labour market weakness and signs that tariff-induced inflation was yet to reflect in headline consumer prices have made investors confident of a potential dovish move next month. 'A 25bps rate cut is still almost fully priced in although it has put a dampener on tentative expectations that the Fed could deliver an even larger 50bps rate cut like last September,' analysts at MUFG said in a note. 'Market participants are still confident that the Fed will resume rate cuts in response to weakness in the labour market and the lack of pass through so far to consumer prices from higher tariffs as evident in this week's CPI report.' At 5.38am, Dow E-minis were up 285 points, or 0.63%, S&P 500 E-minis were up 3 points, or 0.06%, and Nasdaq 100 E-minis were down 46.5 points, or 0.19%. Focus will now be on July retail sales data, due later in the day, and the University of Michigan's report on consumer confidence, for clues on the health of the American consumer. Among other stocks, Applied Materials tumbled 14.8% after the chip equipment maker issued weak fourth-quarter forecasts on sluggish China demand, fueling concerns over tariff-related risks. Shares of other chip equipment makers such as KLA and Lam Research lost 6.1% and 5.6%, respectively. Intel rose 2.8% on the heels of a 20% gain this week after a report said the Trump administration was in talks with the struggling chipmaker for the US government to potentially take a stake in the company. On the commodities front, crude prices slipped to around US$65 a barrel with attention on a meeting in Alaska between US President Donald Trump and his Russian counterpart, Vladimir Putin, that markets hope could pave the way for a resolution to the Ukraine conflict. The meeting will take place at 7pm.
Malay Mail
4 hours ago
- Malay Mail
Apple revives blood oxygen feature in latest Watch models after patent row pause
SAN FRANCISCO, Aug 15 — Apple on Thursday said some of its top smartwatch models are getting a redesigned blood oxygen sensing feature, sidelined for several years by a patent dispute. Software updates will add the capability to an array of Series 9, Series 10, and Ultra 2 Apple Watch models, according to the iPhone maker. 'This update was enabled by a recent US Customs ruling,' Apple said in a blog post. Apple temporarily halted US sales of its latest smartwatch models last January as part of a patent feud with health company Masimo. Masimo, based in southern California, filed a complaint to the US International Trade Commission (ITC) which decided to halt imports of the Apple Watch models over a patented technology for detecting blood-oxygen levels. Apple manufactures the vast majority of its products overseas, giving the ITC jurisdiction over the patent feud. According to reports, Apple removed the technology from the smartwatches in question at the time and resumed selling them. Masimo argued that it invented the technology and that Apple poached key employees to win access to the know-how. But Apple contended that the ITC finding was in error and appealed the decision in US federal court. Apple strongly promotes its smartwatch's fitness and health features, which include detection of heartbeat irregularities, falls, sleep apnea, and harmful noise levels. — AFP
