AI tool uses face photos to estimate biological age and predict cancer outcomes

Mass General Brigham findings suggest FaceAge tool could provide objective data to help inform treatment decisions in cancer care and other chronic diseases

2025-05-08

(Press-News.org) Eyes may be the window to the soul, but a person’s biological age could be reflected in their facial characteristics. Investigators from Mass General Brigham developed a deep learning algorithm called FaceAge that uses a photo of a person’s face to predict biological age and survival outcomes for patients with cancer. 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. Older FaceAge predictions were associated with worse overall survival outcomes across multiple cancer types. They also found that FaceAge outperformed clinicians in predicting short-term life expectancies of patients receiving palliative radiotherapy. Their results are published in The Lancet Digital Health.

"We can use artificial intelligence (AI) to estimate a person’s biological age from face pictures, and our study shows that information can be clinically meaningful,” said co-senior and corresponding author Hugo Aerts, PhD, director of the Artificial Intelligence in Medicine (AIM) program at Mass General Brigham. “This 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. How old someone looks compared to their chronological age really matters—individuals with FaceAges that are younger than their chronological ages do significantly better after cancer therapy.”

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’s chronological age, in addition to many other biological measures, may help determine the best course of treatment. However, like anyone, physicians may have biases about a person’s age that may influence them, fueling a need for more objective, predictive measures to inform care decisions.

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. 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.

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. 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.

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. While there was a wide range in their performance, overall, the clinicians’ predictions were only slightly better than a coin flip, even after they were given clinical context, such as the patient’s chronological age and cancer status. Yet when clinicians were also provided with the patient’s FaceAge information, their predictions improved significantly.

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. 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.

“This opens the door to a whole new realm of biomarker discovery from photographs, and its potential goes far beyond cancer care or predicting age,” said co-senior author Ray Mak, MD, a faculty member in the AIM program at Mass General Brigham. “As we increasingly think of different chronic diseases as diseases of aging, it becomes even more important to be able to accurately predict an individual’s 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.”

Authorship: Additional 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.

Disclosures: Mass General Brigham has filed provisional patents on two next-generation facial health algorithms.

Funding: This 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 – European Research Council (HA: 866504).

Paper cited: Bontempi, et al. “Decoding biological age from face photographs using deep learning.” The Lancet Digital Health, DOI: 10.1016/j.landig.2025.03.002

About Mass General Brigham

Mass General Brigham is an integrated academic health care system, uniting great minds to solve the hardest problems in medicine for our communities and the world. Mass General Brigham connects a full continuum of care across a system of academic medical centers, community and specialty hospitals, a health insurance plan, physician networks, community health centers, home care, and long-term care services. Mass General Brigham is a nonprofit organization committed to patient care, research, teaching, and service to the community. In addition, Mass General Brigham is one of the nation’s leading biomedical research organizations with several Harvard Medical School teaching hospitals. For more information, please visit massgeneralbrigham.org.

END

ELSE PRESS RELEASES FROM THIS DATE:

North Korea’s illegal wildlife trade threatens endangered species

2025-05-08

The North Korean government engages in unsustainable and illegal wildlife trade, which includes species protected under its own laws and poses a threat to biodiversity recovery in the region, finds a groundbreaking new study by UCL researchers. The report, published in Biological Conservation, found that although North Korea has a regulatory system of protected areas and protected species, these are regularly breached by people hunting and trapping wild animals for personal consumption or black market trade, either domestically or for sale to buyers in China. Additionally, the North Korean state itself is implicated in, and actively profiting from, harvesting and trade of endangered ...

Health care workers, firefighters have increased PFAS levels, study finds

2025-05-08

A study including researchers from the University of Arizona Health Sciences and published in the Journal of Exposure Science & Environmental Epidemiology found that firefighters had higher concentrations of certain per- and polyfluoroalkyl substances, or PFAS, and health care workers had moderate elevations of PFAS in their blood with significantly higher odds of two specific PFAS when compared with other essential workers. “Our study reinforces previous research showing ...

Turning light into usable energy

2025-05-08

Every time a screen flickers to life, or sunlight powers a home, energy is being transferred from light into something useful. Yet for all of its ubiquity, scientists do not fully understand the process by which light transfers energy through materials. A grant from the U.S. Department of Defense will allow UC Riverside scientists to address that mystery. The research aims to deepen scientific understanding of one of physics’ most complex interactions. The four-year, $1 million grant funds a collaborative effort between UCR theoretical chemist Bryan Wong and experimental ...

Important step towards improving diagnosis and treatment of brain metastases

2025-05-08

Brain metastases often occur as a result of advanced cancer and, despite medical innovations, are still associated with a poor prognosis. Now, an international expert committee led by the Medical University of Vienna and the Ludwig Maximilian University Hospital (LMU) in Munich has taken an important step towards improving diagnostics and therapy monitoring. A special imaging procedure, amino acid PET, can not only improve patient care, but also advance research into the development of new treatment ...

Maternal cardiometabolic health during pregnancy associated with higher blood pressure in children, NIH study finds

2025-05-08

Children born to mothers with cardiometabolic health issues before or during pregnancy may face a higher risk of elevated blood pressure in childhood and adolescence, according to a new study funded by the Environmental influences on Child Health Outcomes (ECHO) Program at the National Institutes of Health (NIH). High blood pressure in childhood often continues into adulthood and is linked to a greater risk of heart problems later in life. This ECHO research offers insights into how a mother’s heart and metabolic health before and during pregnancy may contribute to her child’s long-term cardiovascular well-being. The study analyzed data from 12,480 mother-child ...

Mercury levels in the atmosphere have decreased throughout the 21st century

2025-05-08

Mercury is released by environmental and human-driven processes. And some forms, specifically methylmercury, are toxic to humans. Therefore, policies and regulations to limit mercury emissions have been implemented across the globe. And, according to research published in ACS ES&T Air, those efforts may be working. Researchers found that atmospheric mercury levels have decreased by almost 70% in the last 20 years, mainly because human-caused emissions have been reduced. “By tracking mercury pollution over four decades at the top of the world, we show that global efforts to reduce pollution ...

This soft robot “thinks” with its legs

2025-05-08

A research team from AMOLF in Amsterdam created a soft robot that walks, hops, and swims — all without a brain, electronics, or AI. Just soft tubes, air, and some clever physics. The study published this week in Science describes one of the fastest soft robots yet, and one of the simplest. It has no computer, no software, and no sensors. And still, it moves with surprising coordination and autonomy, simply because of its body and how it interacts with the world. So, what’s really driving it? Underneath the movement is a principle you’ve probably seen, though maybe overlooked. Think of those wobbly, ...

Biologists identify targets for new pancreatic cancer treatments

2025-05-08

CAMBRIDGE, MA -- Researchers from MIT and Dana-Farber Cancer Institute have discovered that a class of peptides expressed in pancreatic cancer cells could be a promising target for T-cell therapies and other approaches that attack pancreatic tumors. Known as cryptic peptides, these molecules are produced from sequences in the genome that were not thought to encode proteins. Such peptides can also be found in some healthy cells, but in this study, the researchers identified about 500 that appear to be found only in pancreatic ...

Simple tweaks to a gene underlie the stench of rotten-smelling flowers

2025-05-08

Some plants lure pollinators not with sweet fragrances, but with the rank stench of decay. In a new study, researchers show how plants pull this off. In Asarum flowers, a gene typically used for detoxifying smelly compounds has instead evolved to produce unpleasant odors, the researchers report. The findings shed light on how plants co-opt widely conserved metabolic pathways for ecological advantage. A key feature of foul-smelling flowers is the release of malodorous volatile compounds, particularly oligosulfides like dimethyl disulfide (DMDS) and dimethyl trisulfide (DMTS). These compounds mimic the chemical signals given off by decaying material. ...

Simple, effective interventions reduce emissions from Bangladesh’s informal brick kilns

2025-05-08

Simple and inexpensive interventions aimed at making changes in how Bangladesh’s informal brink kilns operate could dramatically cut emissions and boost profits for producers, according to a new study. The findings may offer a scalable model for tackling pollution in hard-to-regulate informal industries, particularly in low- and middle-income countries (LMICs). In many LMICs, weak regulatory systems limit the effectiveness of pollution control, especially in informal industries that tend to operate outside formal governance and ...

LAST 30 PRESS RELEASES:

Urine, not water for efficient production of green hydrogen

Chip-scale polydimethylsiloxane acousto-optic phase modulator boosts higher-resolution plasmonic comb spectroscopy

Blood test for many cancers could potentially thwart progression to late stage in up to half of cases

Women non-smokers still around 50% more likely than men to develop COPD