Latest news with #biologicalAge
Medical News Today
04-07-2025
- Health
- Medical News Today
Could a single brain scan predict the risk of age-related conditions like dementia?
People age at different rates, partly due to genetics but largely because of lifestyle.A person's rate of aging can indicate how likely they are to develop age-related disorders, such as researchers have developed a method based on a single brain scan in middle age that could predict how fast a person is likely to suggest that their method, which can predict the aging rate of both brain and body, may detect who should implement lifestyle changes to reduce their risk of age-related people appear to age more slowly than others. This is partly due to genetics, which studies suggest accounts for around 25% of the variation in longevity but is largely due to lifestyle and the in lifestyle, such as following a healthy diet, exercising regularly, getting adequate sleep, not smoking, and not drinking alcohol to excess, can help slow a person's rate of aging and delay or prevent age-related disorders.A person's rate of aging is often referred to as their biological age — how old their cells are — which can vary greatly from their chronological age, or the number of years since their birth. Measuring this can be a group of researchers from Duke, Harvard, and the University of Otago, New Zealand, have developed a method of predicting how fast a person will age, based on a single brain scan performed around the age of 45. In their study, which is published in Nature Aging, the researchers suggest that the Dunedin Pace of Aging Calculated from NeuroImaging (DunedinPACNI) could help researchers determine how aging affects health, and help them evaluate the effectiveness of anti-aging strategies.'The study developed and validated a new MRI-based biomarker called DunedinPACNI which shows not only a score for brain age, i.e. how old the brain looks, but also shows connections to cognitive decline and other health measures, allowing to perhaps predict how quickly a person ages and how their health will evolve later in life,' Madalina Tivarus, PhD, associate professor of Imaging Sciences and Neuroscience at the Del Monte Institute for Neuroscience at the University of Rochester, not involved in the study, told Medical News scan can predict biological aging'The idea of using a routine MRI brain scan to do a 'aging check-up' is very interesting and exciting,' Tivarus told study builds on the Dunedin Study, previous research conducted in the same cohort of participants. This study, which followed a group of 1,037 people born in Dunedin, New Zealand in 1972–'73, looked at age-related changes in gene methylation to create an epigenetic the Dunedin Study, researchers regularly tested participants' blood pressure, body mass index (BMI), glucose (blood sugar) and cholesterol levels, lung and kidney function, and even gum recession and tooth almost 20 years, they used the overall pattern of change across these health markers to generate a score for how fast each person was the latest study, researchers used a single MRI scan of the brain performed when participants were aged 45, which they correlated with the Dunedin Study aging data. They then developed their DunedinPACNI to estimate rate of aging using only information from the MRI evaluate the Dunedin PACNI as a tool for predicting age-related health outcomes, they analyzed it against datasets from the Alzheimer's Disease Neuroimaging Initiative (ADNI), UK Biobank, and Latin American Brain Health found that their prediction accuracy was in line with more established epigenetic with faster DunedinPACNI scores had several indicators of more rapid aging, including:worse balance, slower gait, weaker lower and upper body strength, and poorer coordinationself-reported worse health and more physical limitations poorer performance on cognitive function tests greater childhood-to-adulthood cognitive declineolder physical MacSweeney, MD, CEO and consultant Neuroradiologist at Re:Cognition Health, who was not involved in this research, highlighted how important brain imaging could be, telling MNT that:'The researchers observed that individuals with higher DunedinPACNI scores, indicating faster brain aging, were also more likely to experience health deterioration in other organ systems, such as cardiovascular and respiratory health. The fact that brain imaging can reflect systemic aging suggests the brain may serve as a biomarker for overall biological age, offering a non-invasive, accessible measure of aging processes throughout the body.'Novel brain scan better predictive tool than existing MRI measuresTivarus enthused that:'This study is exciting because it shows that MRI scans might be used not just to detect disease, but also to track how the brain is aging long before problems begin. However, it's still early days. While promising, DunedinPACNI still needs to be tested more widely in larger and more diverse populations across different ages, ethnicities, and health backgrounds. It did perform well across multiple large datasets, but more global validation is needed.'The researchers compared the DunedinPACNI with measures of hippocampal and ventricular volume, which are commonly used MRI-based measures of brain aging, using UK Biobank and ADNI found that faster DunedinPACNI was more consistently and strongly associated with poor cognition, poor health, frailty, and risk of dementia, disease and mortality than either of these was impressed by the study structure.'The study methodology has some important strengths such as it is using a robust, decades-long longitudinal dataset, uses sound statistical methods, and has been validated extensively using imaging data from other large studies,' she she also pointed out that there were 'some limitations, such as the specific population data used to train the model (mostly European ancestry, from a specific geographical location), its performance in younger or pediatric populations is untested, [and] it infers dynamic processes from one static image (one MRI snapshot).' 'While I don't think it is ready for clinical use, DunedinPACNI appears to be a promising imaging biomarker of biological aging,' Tivarus told us.'The tool empowers people to take proactive steps'As people are living longer, but not necessarily healthier, lives, the ability to predict who is more likely to develop dementia or other age-related illness is becoming increasingly important. The researchers hope that their tool might eventually help clinicians do that well before symptoms, allowing interventions to reduce the risk of conditions developing.'Identifying accelerated aging in midlife provides a critical window of opportunity for intervention. Knowing one's biological age, as distinct from chronological age, could motivate individuals to adopt healthier habits, such as improved diet, increased physical activity or better sleep. By highlighting risk decades in advance, the tool empowers people to take proactive steps that may slow or even reverse aspects of biological aging.' – Emer MacSweeney, MD
Medscape
20-06-2025
- Health
- Medscape
Epigenetic Clocks: New Types, New Promises, New Skepticism
Will birthdays go the way of the Betamax and Blackberry? Our culture is always eager to move away from old things toward new things and these days if you want to know how old you are, the number of candles on your cake is just one clue — and maybe not even the best clue. Epigenetic clocks measure what's happening inside you on a cellular level and they might say you're aging faster (or slower) than you thought based on changes to your DNA. First developed in 2013 as research tools, epigenetic clocks are now widely accessible through direct-to-consumer test kits. Send in a sample of your DNA and receive your results — your 'biological age' — within weeks. Can this give the average layperson valuable insights? Should doctors be using them to help predict how one patient might get sick or how long another might live? Yes, no, and maybe are all legit answers here depending on who's asking and who's being asked. Right now, epigenetic clocks are in the same spot as other highly hyped medical tech — like artificial intelligence, like wearables, like implantables — in that they're not really 'there' yet and yet everyone wants them to be. Researchers already use them, of course. They have extensive clinical potential and simultaneously excite health-conscious consumers: How quickly can I know how old I really am? The tests have evolved quickly and will continue to do so. For example: Some tests require you to draw a little blood or spit in a tube, but one of the latest tests uses an at-home cheek swab instead. In a study published in Frontiers in Aging , US company Tally Health showed its CheekAge epigenetic clock can predict the risk for early death. For every SD increase in CheekAge score, study participants faced a 21% higher risk for death before their next check-in with researchers, which was scheduled every 3 years. 'We believe that epigenetic aging clocks currently can serve as useful indicators of health and lifestyle, which is often missing from the care conversation, and should be part of routine preventative care,' said Max Shokhirev, PhD, head of Computational Biology and Data Science at Tally Health. Epigenetic clocks can also help researchers compare populations over time, track users in specific contexts, or stratify clinical trial participants into high-risk or low-risk groups, Shokhirev said. However, some experts say there is plenty of room for improvement as the science behind epigenetic clocks advances. Although companies tout the accuracy of their clocks, results can vary by years or decades, leaving test takers confused. Sometimes the test results come with suggestions for boosting longevity, including products the testing companies want to sell you. Then there's the biggest question: If you can improve your score, will you truly live better or longer? How to Build a Clock Instead of tracking time, epigenetic clocks detect patterns in DNA methylation, a chemical reaction that attaches molecules called methyl groups to DNA. All your cells have the same DNA, and methylation determines which genes get turned on and off, said Eric Verdin, MD, president and chief executive officer of the Buck Institute for Research on Aging. For example, the gene for hemoglobin is turned on in red blood cells through methylation. The same gene is switched off in other cells, such as neurons. 'As we age, the precision of this epigenetic mechanism gets a little loose,' said Verdin. Cells lose some specificity, and genes turn on and off in the wrong places, a phenomenon known as epigenetic drift. 'Now we can measure this epigenetic drift during aging, and that's what the clocks are based on,' said Verdin. Methylation happens in about 28 million spots, known as methylation sites, in our genomes. To make the first epigenetic clocks, the Hannum and Horvath clocks, researchers analyzed blood samples from hundreds to thousands of people. They examined DNA methylation in a small fraction of methylation sites. They used the data to build a mathematical model that predicts age based on DNA methylation. The math behind the first clocks revolved around age. Today, scientists use second-generation epigenetic clocks such as PhenoAge and GrimAge, which also incorporate health-related variables, such as white blood cell counts and smoking history. One clock, DunedinPACE, reveals a rate of aging rather than a set number. Second-generation clocks likely have more predictive value for your health than earlier versions, said Verdin. Research suggests epigenetic age can foretell some health outcomes, such as working memory or surviving a stay at the intensive care unit, better than chronological age, the number you celebrate on your birthday. However, more research is needed to see how epigenetic clocks stack up to more established tests and screening tools. In one new study in the Journal of the American Heart Association , PhenoAge and GrimAge were not as good at predicting cardiovascular disease as the widely used Framingham Risk Score. Marketing to consumers is the most predictable advance in the tech. The cost for a single test runs between $250 and $500. Some companies also offer monthly subscriptions including repeat testing and recommended supplements. Insurance companies don't cover these tests for healthy people. Some insurers, like Aetna, will cover epigenetic tests when someone has symptoms of a specific disease and knowing the results could affect treatment. But these tests are different from epigenetic clocks — they detect specific epigenetic disease signatures instead of the markers that give an overall picture of health. (And it's difficult to get coverage for these, too: In one study in Genetics in Medicine , insurers covered just 11% of methylation-based genetic tests ordered by physicians for people with a diagnosis suspected to have a genetic component.) Clocking Test Results Some longevity testing companies use one or more second-generation clocks to estimate age. Some use their own proprietary clocks. So let's say you take a test: How much stock should you put in your results? As Verdin said, 'I've done all of my clocks, and my age varies from 40 to 67, all DNA methylation, which is, in my opinion, an indication that these tools are not ready for prime time.' (Note: As of publication time, Verdin is 68 years old.) Results vary because each clock has its own math, based on a unique combination of methylation sites and study participants. The numbers on your reports might not be useful in isolation, said Verdin. Instead, think of them as variables you can track over time. 'Where they have more value is if you use always the same clock, and you introduce a number of interventions,' said Verdin. 'For example, you start intermittent fasting, or you start metformin, or you do this intervention or that intervention, and if you see your clock moving in the right direction, that will be a good sign.' If you try this method, time follow-up tests carefully. DNA methylation isn't as static as people assume, said Verdin. Like measuring cortisol or blood sugar, it varies by time of day, skewing clock results by up to 5 years. 'You should always do them at exactly the same time, and hopefully, do it the same kind of day,' he said. 'You don't want to do one on a Sunday, when you're well rested, you're not stressed versus the Tuesday or Friday morning when you're super stressed.' Timing isn't the only problem that can affect your results and how to interpret them. 'Emerging research shows that there are race and ethnic disparities in terms of how the clock performs,' said Andres Cardenes, PhD, an assistant professor of epidemiology and population health at Stanford University, Stanford, California. Blame a lack of diversity in the data used to develop many epigenetic clocks. Most samples came from White people in the western part of the world. Cardenes' team is collecting more DNA methylation samples from underrepresented groups so future clocks can be applicable to all. The Lure of Slow Aging and Cheating Death An interesting way to think about this: Getting old is very new to the human experience. And some humans handle it better than others. An epigenetic clock can signal how well you are aging. But no one has figured out how to cheat death forever, so the question remains: How much can you realistically increase your life expectancy? A new study in Nature Aging shows that improvements in human life expectancy have slowed since 1990. Study author S. Jay Olshansky, PhD, professor of epidemiology and biostatistics at the University of Illinois, Chicago, said this isn't bad news — it reflects how dramatically we improved survival during the 20th century through developments like antibiotics and refrigeration. 'This slowdown in the rate of increase is a product of us doing our job exceedingly well in medicine and public health and enabling people to live long enough to experience aging,' he said. Olshansky's team said it's unlikely that more than 15% of women and 5% of men will live to 100 unless we find a way to slow down biologic aging drastically. 'The problem is that when you succeed so well as humanity has, you expose the population to the underlying biological process of aging when they get to older ages, which is currently an immutable process,' he said. That's not for lack of effort. Many scientists are searching for ways to reverse aging. Epigenetic clocks might help people measure the effectiveness of interventions aimed at improving health and extending life, said Olshansky. But pay attention to what else testing companies are selling, like dietary supplements, he said. 'As long as they're not accompanied by embellished claims that you can somehow reverse your biological aging, or slow your biological aging, or live longer and healthier as a result of whatever it is that they're selling, then I think they're okay,' said Olshansky. 'I think they can actually provide some useful and valuable information.' The results might simply push you to do things that have already been shown to help people live healthier and longer, such as eating well and exercising. 'What we need to understand is that these biomarkers are becoming attractive because they track with general things that we know are helpful and healthy as well,' said Cardenes. 'For example, a diet rich in fruits and vegetables, particularly vegetables, has been shown to decelerate some of these clocks.' Research in Aging Cell also suggests that exercise slows down aging as measured by epigenetic clocks. On the Clock: What Does the Future Hold? The science behind epigenetic clocks is evolving fast. Researchers are working to make them more accurate and useful. For example, using epigenetic clocks, Verdin's team noticed that SARS-CoV-2 infections increased people's biologic ages by about 15 years. Postinfection, people had influxes of memory T cells that mirrored age-related changes in immune function. Verdin's team then made a clock that excluded methylation sites sensitive to these changes. It's now available through TruDiagnostic. More opportunity lies in the millions of DNA methylation sites yet to be tapped, said Verdin. Today's epigenetic clocks only probe hundreds to thousands of them. 'There's going to be even more interesting data coming in the future,' he said. Also new will be what and how clocks measure. A study in Aging late last year showed strong results of cell-specific clocks analyzing brain cells for Alzheimer's and liver cells for liver disease. Meanwhile, a new blood-based clock measures 'intrinsic capacity,' the sum of mobility, cognition, mental health, vision, hearing, and nutrition/vitality. All aimed at improving function in aging patients (and perhaps addressing health span and lifespan simultaneously). Researchers have also developed phenotypic clocks that examine biomarkers like blood pressure and cholesterol. The organ-specific clocks look to be most useful in detecting early deterioration by body part. 'Your longevity is determined by your frailty point,' said Verdin. 'In your case, it might be your heart, and some other person, it might be their liver. The first organ that's going to fail is going to determine your longevity.' Cardenes and others are also exploring how environmental factors affect clocks. 'We want to understand the very early marks that either chemical or social environments might leave in our genome,' he said. Will epigenetic clocks make their way into routine clinical practice? Probably, proponents say, but in what form? 'In the future, patients might be prescribed a low-cost biological age test for their doctors to know the rate of biological aging and detect any organs that need particular attention, years before the patient develops a disease of aging,' said David Sinclair, PhD, professor in the Department of Genetics at Harvard Medical School, Boston, co-founder of Tally Health, and chairman of the Scientific Advisory Board at InsideTracker. 'The test could also be used one day to confirm lifestyle and health factors such as smoking history and alcohol intake.' Verdin sees potential in pairing epigenetic clocks with other new clocks based on blood proteins and metabolites. 'My argument is that for these clocks, as clinical tools, to become important or more relevant, you have to use several,' said Verdin. 'I would not rely only on epigenetic. I would use proteomics, metabolomics, and hopefully get to a picture that is sort of a comprehensive picture.' More research is still needed to determine the value of epigenetic clocks, said Cardenes. 'What does it mean for people to get this test?' he said. 'Is it changing outcomes? At the end of the day, are people going to do things that will improve their health and longevity? It's still unclear whether this is helpful or not.'
Yahoo
13-05-2025
- Health
- Yahoo
How Old Are You Really? New Test Calculates Biological Age and Longevity With 90% Accuracy
"Hearst Magazines and Yahoo may earn commission or revenue on some items through these links." You've heard it for years: Age is just a number. But there's been a huge focus lately on biological age, which is how old your cells are. There are a bunch of different ways to calculate this number, including tests you can order online. But researchers have just discovered a new way of calculating your biological age—and they say it's the most accurate one you'll find. It's called the Health Octo Tool, and it uses a slew of different metrics to figure out your biological age. Meet the experts: David Cutler, M.D., a family medicine physician at Providence Saint John's Health Center in Santa Monica, CA; Parul Goyal, M.D., a geriatrician at Vanderbilt Health in Nashville; Shabnam Salimi, M.D., Ph.D., physician-scientist and an investigator at the University of Washington Medicine Healthy Aging & Longevity Research Institute Here's why there's so much buzz around it right now, plus why knowing your biological age may help you live longer. The Health Octo tool is a new health assessment tool that uses several metrics taken from a physical exam and routine lab tests. When used together, it can help determine a person's biological age and predict their risk of disability and death, according to a scientific paper published in Nature Communications. The tool centers around an aging concept called health entropy, which is how much molecular and cellular damage the body accumulates over time, as well as how that damage impacts organs and bodily systems. To create the tool, the researchers analyzed data from the Baltimore Longitudinal Study on Aging, analyzing participants' medical history as well as data from physical exams and other medical tests. The researchers also included data from two other large studies on more than 45,000 adults. The scientists created what they called a Body Organ Disease Number, which was based on the number of organ systems, like the cardiovascular, respiratory, and central nervous systems, that were impacted by disease. They also factored in whether a person had a history of cancer or stroke to get a score between one and 14. The researchers also created something called a Speed-Body Clock and Speed-Body Age to break down how a person's biological age impacts their walking speed (which is a common measure of function in older people). Also in the mix: Disability-Body Clock and Disability Body Age, which analyzes how getting older impacts the risk of developing cognitive and physical disability. All of those metrics can be gathered from a person's medical history, physical exam, and test results to calculate a person's aging process. Ultimately, the researchers say that the Health Octo tool is better than major tests used for assessing biological age, including the frailty index, a widely-used test that looks at a person's susceptibility to age-related health issues. The researchers found that the test can predict the odds of developing disability and death with 90% or higher accuracy. The Health Octo tool uses some of the same data from existing biological tests, but takes things a step further. Many of the tests that are currently used focus on the impact of certain diseases, but don't consider how those diseases and minor disorders impact a person's overall health, the researchers explained in the paper. 'Health decline is multi-dimensional,' says lead study author Shabnam Salimi, M.D., Ph.D., physician-scientist and an investigator at the University of Washington Medicine Healthy Aging & Longevity Research Institute. 'So, we decided to develop a multi-dimensional health metric that captures intrinsic aging and rate of aging.' Knowing your biological age has become more of a fun health flex lately, but doctors say it's important to know this number beyond bragging rights. 'There is some value to seeing the things you should be doing,' says David Cutler, M.D., a family medicine physician at Providence Saint John's Health Center in Santa Monica, CA. Meaning, if you know your diet isn't as clean as it should be, and your biological age is older than your chronological age (i.e. how many years you've been alive), it should be a wake-up call to do things differently. 'Biological aging mechanisms underlie accumulation of chronic diseases,' Dr. Salimi says. 'So, translating health to rate of aging can help to better understand biological aging mechanisms and response to interventions that target biological age.' Parul Goyal, M.D., a geriatrician at Vanderbilt Health in Nashville, agrees. 'Knowing your biological age is a good tool so that patients are more aware of what their health looks like,' she says. 'They can then make proactive, positive changes in their health to be more physically fit and emotionally engaged.' While Dr. Cutler points out that 'you probably know that you should be doing things differently anyway,' if you're not on top of your health habits, he notes that a higher biological age may motivate some people to make changes. Of course, that doesn't mean that it will. 'Is that going to make people drink less, avoid smoking, and eat better? We don't know,' Dr. Cutler says. Doctors recommend doing a lot of different things to age in a healthy way, although none are shocking. Here's the advice Dr. Cutler and Dr. Goyal share with their patients: Eat a healthy, varied diet—ideally the Mediterranean diet. Limit alcohol or avoid it entirely. Don't smoke or quit smoking. Try to be active on a daily basis. Stay on top of routine healthcare, including cancer screenings. Wear a helmet when you ride a bike. Use your seatbelt in the car. Try to minimize stress in your life. Focus on getting good sleep. Try to stay mentally stimulated. Socialize with friends and family. Dr. Salimi says that she and her fellow researchers are now working on developing an app to make the Health Octo Tool easier to use. You Might Also Like Can Apple Cider Vinegar Lead to Weight Loss? Bobbi Brown Shares Her Top Face-Transforming Makeup Tips for Women Over 50
Yahoo
11-05-2025
- Health
- Yahoo
AI can tell how old your body really is and how quickly you're aging using just a selfie
When you buy through links on our articles, Future and its syndication partners may earn a commission. A new artificial intelligence (AI) model can predict a person's biological age — the state of their body and how they're aging — from a selfie. The model, dubbed FaceAge, estimates how old a person looks compared to their chronological age, or the amount of time that's passed since their birth. FaceAge's makers say their tool could help doctors decide on the best course of treatment for diseases like cancer. But one outside expert told Live Science that before it is used that way, follow-up data needs to show it actually improves treatment outcomes or quality of life. When a doctor is treating a cancer patient, "one of the first things they do is they try to assess how well the individual is doing," Hugo Aerts, director of the AI in Medicine Program at Mass General Brigham, said in a news briefing on May 7. "This is often a very subjective assessment, but it can influence a lot of future decisions" about their treatment, including how aggressive or intense their treatment plan should be, he added. For example, doctors may decide a patient who looks younger and more fit for their age may tolerate an aggressive treatment better and eventually live longer than a patient who looks older and more frail, even if the two have the same chronological age. FaceAge could make that decision easier by turning doctors' subjective estimates into a quantitative measure, the study authors wrote in the new study published May 8 in the journal Lancet Digital Health. By quantifying biological age, the model could offer another data point in helping doctors decide which treatment to recommend. Aerts and his colleagues trained the model on more than 58,000 photos of people ages 60 years and older who were assumed to be of average health for their age at the time the photo was taken. In this training set, the researchers had the model estimate chronological ages and assumed that the people's biological ages were similar, though the scientists noted that this assumption is not true in every case. The team then used FaceAge to predict the ages of more than 6,000 people with cancer. Cancer patients looked about five years older, on average, than their chronological ages, the team found. FaceAge's estimates also correlated with survival after treatment: The older a person looked, regardless of their chronological age, the lower their chances of living longer. By contrast, chronological age was not a good predictor of survival in cancer patients, the team found. FaceAge isn't ready for hospitals or physicians' offices yet. For one, the dataset used to train the model was pulled from IMDb and Wikipedia — which may not represent the general population, and may also not account for factors like plastic surgery, lifestyle differences, or images that have been digitally retouched. Further studies with larger and more representative training sets are needed to understand how those factors impact FaceAge estimations, the authors said. And the researchers are still improving the algorithm with additional training data and testing its efficacy for other conditions besides cancer. They're also investigating what factors the model draws on to make its predictions. But once it's finalized, FaceAge could, for example, help doctors tailor the intensity of cancer treatments like radiation and chemotherapy to specific patients, study co-author Dr. Ray Mak, a radiation oncologist at Mass General Brigham, said during the briefing. A clinical trial for cancer patients, comparing FaceAge to more traditional measures of a patient's frailty, is starting soon, Mak added. RELATED STORIES —Sped-up 'biological aging' linked to worse memory —New tool estimates your immune 'age,' predicts risk of disease —Will humans ever be immortal? Ethical guidelines surrounding how FaceAge information can be used, such as whether health insurance or life insurance providers could access FaceAge estimates to make coverage decisions, should be established before rolling out the model, the researchers said. "It is for sure something that needs attention, to assure that these technologies are used only for the benefit of the patient," Aerts said in the briefing. Doctors would also need to carefully consider when and how they use FaceAge in clinical settings, said Nicola White, a palliative care researcher at University College London who was not involved in the study. "When you're dealing with people, it's very different to dealing with statistics," White told Live Science. A long-term study assessing whether involving FaceAge in treatment decisions improved patients' quality of life is needed, she said. The researchers noted the AI tool wouldn't be making calls about treatment on its own. "It's not a replacement for clinician judgement," Mak said. But FaceAge could become part of a physician's toolkit for personalizing a treatment plan, "like having another vital sign data point."
Malay Mail
10-05-2025
- Health
- Malay Mail
How old are you, really? AI uses headshots to predict biological age and health risks
WASHINGTON, May 10 — Doctors often start exams with the so-called 'eyeball test' – a snap judgment about whether the patient appears older or younger than their age, which can influence key medical decisions. 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
