{"id":90701,"date":"2025-05-10T18:26:08","date_gmt":"2025-05-10T18:26:08","guid":{"rendered":"https:\/\/www.europesays.com\/uk\/90701\/"},"modified":"2025-05-10T18:26:08","modified_gmt":"2025-05-10T18:26:08","slug":"ai-tool-reads-faces-to-predict-health-aging-and-cancer-outcomes","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/uk\/90701\/","title":{"rendered":"AI Tool Reads Faces to Predict Health, Aging, and Cancer Outcomes"},"content":{"rendered":"<p><strong>Summary: <\/strong>Researchers have developed an AI tool called FaceAge that uses facial photos to estimate biological age and predict survival outcomes in cancer patients. In a study involving over 6,000 patients, those with cancer had FaceAges about five years older than their chronological age, and higher FaceAges were linked to poorer survival.<\/p>\n<p>The tool outperformed clinicians in predicting short-term life expectancy for patients receiving palliative radiotherapy, especially when integrated into their decision-making. These findings suggest that facial features could serve as powerful, non-invasive biomarkers for aging and disease, opening new doors in precision medicine.<\/p>\n<p><strong>Key Facts:<\/strong><\/p>\n<ul class=\"wp-block-list\">\n<li><strong>FaceAge AI:<\/strong> Predicts biological age and survival using facial photos.<\/li>\n<li><strong>Cancer Insight:<\/strong> Patients with cancer appeared ~5 years older than their actual age.<\/li>\n<li><strong>Clinical Boost:<\/strong> FaceAge improved doctors\u2019 predictions of life expectancy in palliative care.<\/li>\n<\/ul>\n<p><strong>Source: <\/strong>Mass General<\/p>\n<p><strong>Eyes may be the window to the soul, but a person\u2019s biological age could be reflected in their facial characteristics. <\/strong><\/p>\n<p>Investigators from Mass General Brigham developed a deep learning algorithm called FaceAge that uses a photo of a person\u2019s face to predict biological age and survival outcomes for patients with cancer.<\/p>\n<p>They found that patients with cancer, on average, had a higher FaceAge than those without and appeared about five years older than their chronological age.<\/p>\n<p>  <img fetchpriority=\"high\" decoding=\"async\" width=\"1200\" height=\"799\" src=\"https:\/\/www.europesays.com\/uk\/wp-content\/uploads\/2025\/05\/AI-face-aging-cancer-neuroscience.jpg\" alt=\"This shows a woman's face with a digital overlay.\"  \/> Results showed that cancer patients appear significantly older than those without cancer, and their FaceAge, on average, was about five years older than their chronological age. Credit: Neuroscience News<\/p>\n<p>Older FaceAge predictions were associated with worse overall survival outcomes across multiple cancer types.\u00a0<\/p>\n<p>They also found that FaceAge outperformed clinicians in predicting short-term life expectancies of patients receiving palliative radiotherapy.<\/p>\n<p>Their results are published in\u00a0The Lancet Digital Health.<\/p>\n<p>\u201cWe can use artificial intelligence (AI) to estimate a person\u2019s biological age from face pictures, and our study shows that information can be clinically meaningful,\u201d said co-senior and corresponding author\u00a0Hugo Aerts, PhD, director of the Artificial Intelligence in Medicine (AIM) program at Mass General Brigham.<\/p>\n<p>\u201cThis work demonstrates that a photo like a simple selfie contains important information that could help to inform clinical decision-making and care plans for patients and clinicians.<\/p>\n<p>\u201cHow old someone looks compared to their chronological age really matters\u2014individuals with FaceAges that are younger than their chronological ages do significantly better after cancer therapy.\u201d<\/p>\n<p>When patients walk into exam rooms, their appearance may give physicians clues about their overall health and vitality. Those intuitive assessments combined with a patient\u2019s chronological age, in addition to many other biological measures, may help determine the best course of treatment.<\/p>\n<p>However, like anyone, physicians may have biases about a person\u2019s age that may influence them, fueling a need for more objective, predictive measures to inform care decisions.<\/p>\n<p>With that goal in mind, Mass General Brigham investigators leveraged deep learning and facial recognition technologies to train FaceAge. The tool was trained on 58,851 photos of presumed healthy individuals from public datasets.<\/p>\n<p>The team tested the algorithm in a cohort of 6,196 cancer patients from two centers, using photographs routinely taken at the start of radiotherapy treatment.<\/p>\n<p>Results showed that cancer patients appear significantly older than those without cancer, and their FaceAge, on average, was about five years older than their chronological age.<\/p>\n<p>In the cancer patient cohort, older FaceAge was associated with worse survival outcomes, especially in individuals who appeared older than 85, even after adjusting for chronological age, sex, and cancer type.<\/p>\n<p>Estimated survival time at the end of life is difficult to pin down but has important treatment implications in cancer care. The team asked 10 clinicians and researchers to predict short-term life expectancy from 100 photos of patients receiving palliative radiotherapy.<\/p>\n<p>While there was a wide range in their performance, overall, the clinicians\u2019 predictions were only slightly better than a coin flip, even after they were given clinical context, such as the patient\u2019s chronological age and cancer status.<\/p>\n<p>Yet when clinicians were also provided with the patient\u2019s FaceAge information, their predictions improved significantly.<\/p>\n<p>Further research is needed before this technology could be considered for use in a real-world clinical setting. The research team is testing this technology to predict diseases, general health status, and lifespan.<\/p>\n<p>Follow-up studies include expanding this work across different hospitals, looking at patients in different stages of cancer, tracking FaceAge estimates over time, and testing its accuracy against plastic surgery and makeup data sets.<\/p>\n<p>\u201cThis opens the door to a whole new realm of biomarker discovery from photographs, and its potential goes far beyond cancer care or predicting age,\u201d said co-senior author\u00a0Ray Mak, MD,\u00a0a faculty member in the AIM program at Mass General Brigham.<\/p>\n<p>\u201cAs we increasingly think of different chronic diseases as diseases of aging, it becomes even more important to be able to accurately predict an individual\u2019s aging trajectory. I hope we can ultimately use this technology as an early detection system in a variety of applications, within a strong regulatory and ethical framework, to help save lives.\u201d<\/p>\n<p><strong>Authorship:<\/strong>\u00a0Additional Mass General Brigham authors include Dennis Bontempi, Osbert Zalay, Danielle S. Bitterman, Fridolin Haugg, Jack M. Qian, Hannah Roberts, Subha Perni, Vasco Prudente, Suraj Pai, Christian Guthier, Tracy Balboni, Laura Warren, Monica Krishan, and Benjamin H. Kann.<\/p>\n<p><strong>Disclosures:<\/strong>\u00a0Mass General Brigham has filed provisional patents on two next-generation facial health algorithms.<\/p>\n<p><strong>Funding:<\/strong>\u00a0This project received financial support from the National Institutes of Health (HA: NIH-USA U24CA194354, NIH-USA U01CA190234, NIH-USA U01CA209414, and NIH-USA R35CA22052; BHK: NIH-USA K08DE030216-01), and the European Union \u2013 European Research Council (HA: 866504).<\/p>\n<p>About this AI, aging, and Cancer research news<\/p>\n<p class=\"has-background\" style=\"background-color:#ffffe8\"><strong>Author: <\/strong><a href=\"http:\/\/neurosciencenews.com\/cdn-cgi\/l\/email-protection#3c4e565d4f50534b7c515b5e12534e5b\" target=\"_blank\" rel=\"noreferrer noopener\">Ryan Jaslow<\/a><br \/><strong>Source: <\/strong><a href=\"https:\/\/mgb.org\" target=\"_blank\" rel=\"noreferrer noopener\">Mass General<\/a><br \/><strong>Contact: <\/strong>Ryan Jaslow \u2013 Mass General<br \/><strong>Image: <\/strong>The image is credited to Neuroscience News<\/p>\n<p class=\"has-background\" style=\"background-color:#ffffe8\"><strong>Original Research: <\/strong>Open access.<br \/>\u201c<a href=\"https:\/\/doi.org\/10.1016\/j.landig.2025.03.002\" target=\"_blank\" rel=\"noreferrer noopener\">FaceAge, a deep learning system to estimate biological age from face photographs to improve prognostication: a model development and validation study<\/a>\u201d by\u00a0Hugo Aerts et al. Lancet Digital Health<\/p>\n<p><strong>Abstract<\/strong><\/p>\n<p><strong>FaceAge, a deep learning system to estimate biological age from face photographs to improve prognostication: a model development and validation study<\/strong><\/p>\n<p>Background<\/p>\n<p>As humans age at different rates, physical appearance can yield insights into biological age and physiological health more reliably than chronological age. In medicine, however, appearance is incorporated into medical judgements in a subjective and non-standardised way.<\/p>\n<p>In this study, we aimed to develop and validate FaceAge, a deep learning system to estimate biological age from easily obtainable and low-cost face photographs.<\/p>\n<p>Methods<\/p>\n<p>FaceAge was trained on data from 58\u2009851\u00a0presumed healthy individuals aged 60\u00a0years or older: 56\u2009304\u00a0individuals from the IMDb\u2013Wiki dataset (training) and 2547 from the UTKFace dataset (initial validation).<\/p>\n<p>Clinical utility was evaluated on data from 6196 patients with cancer diagnoses from two institutions in the Netherlands and the USA: the MAASTRO, Harvard Thoracic, and Harvard Palliative cohorts FaceAge estimates in these cancer cohorts were compared with a non-cancerous reference cohort of 535\u00a0individuals.<\/p>\n<p>To assess the prognostic relevance of FaceAge, we performed Kaplan\u2013Meier survival analysis and Cox modelling, adjusting for several clinical covariates. We also assessed the performance of FaceAge in patients with metastatic cancer receiving palliative treatment at the end of life by incorporating FaceAge into clinical prediction models.<\/p>\n<p>To evaluate whether FaceAge has the potential to be a biomarker for molecular ageing, we performed a gene-based analysis to assess its association with senescence genes.<\/p>\n<p>Findings<\/p>\n<p>FaceAge showed significant independent prognostic performance in various cancer types and stages.<\/p>\n<p>Looking older was correlated with worse overall survival (after adjusting for covariates per-decade hazard ratio [HR] 1\u00b7151, p=0\u00b7013\u00a0in a pan-cancer cohort of n=4906; 1\u00b7148, p=0\u00b7011\u00a0in a thoracic cohort of n=573; and 1\u00b7117, p=0\u00b7021\u00a0in a palliative cohort of n=717).<\/p>\n<p>We found that, on average, patients with cancer looked older than their chronological age (mean increase of 4\u00b779\u00a0years with respect to non-cancerous reference cohort, p<\/p>\n<p>We found that FaceAge can improve physicians\u2019 survival predictions in patients with incurable cancer receiving palliative treatments (from area under the curve 0\u00b774 [95% CI 0\u00b770\u20130\u00b778] to 0\u00b78 [0\u00b776\u20130\u00b783]; p<\/p>\n<p>FaceAge was also significantly associated with molecular mechanisms of senescence through gene analysis, whereas age was not.<\/p>\n<p>Interpretation<\/p>\n<p>Our results suggest that a deep learning model can estimate biological age from face photographs and thereby enhance survival prediction in patients with cancer.<\/p>\n<p>Further research, including validation in larger cohorts, is needed to verify these findings in patients with cancer and to establish whether the findings extend to patients with other diseases.<\/p>\n<p>Subject to further testing and validation, approaches such as FaceAge could be used to translate a patient\u2019s visual appearance into objective, quantitative, and clinically valuable measures.<\/p>\n<p>Funding<\/p>\n<p>US National Institutes of Health and EU European Research Council.<\/p>\n","protected":false},"excerpt":{"rendered":"Summary: Researchers have developed an AI tool called FaceAge that uses facial photos to estimate biological age and&hellip;\n","protected":false},"author":2,"featured_media":90702,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3163],"tags":[1152,323,1942,7203,215,1204,3725,105,3690,2680,219,220,53,16,15],"class_list":{"0":"post-90701","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-aging","9":"tag-ai","10":"tag-artificial-intelligence","11":"tag-brain-cancer","12":"tag-brain-research","13":"tag-cancer","14":"tag-deep-learning","15":"tag-health","16":"tag-machine-learning","17":"tag-mass-general","18":"tag-neurobiology","19":"tag-neuroscience","20":"tag-technology","21":"tag-uk","22":"tag-united-kingdom"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@uk\/114484948735688460","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/90701","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/comments?post=90701"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/90701\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media\/90702"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media?parent=90701"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/categories?post=90701"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/tags?post=90701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}