Thermal image of a person’s face

Thermal image of a person's face. (Image by Anita van den Broek on Shutterstock)

New study shows how thermal imaging could one day be used as a routine part of checkups at the doctor’s office

BEIJING — Facial scans could soon do more than unlock your smartphone or identify you at the airport. Researchers have unveiled a novel way to assess aging and detect metabolic diseases using nothing more than the heat patterns on your face. This innovative approach, dubbed “ThermoFace,” could revolutionize how we monitor health and aging in the future.

Imagine walking into a doctor’s office and, instead of undergoing a battery of tests, simply having your picture taken by a special camera. This camera doesn’t capture your smile or the twinkle in your eye, but rather the intricate patterns of heat across your face. According to the new research, these thermal images contain a wealth of information about your biological age and overall health.

The study, led by researchers from Peking University and other institutions in China, analyzed thermal facial images of over 2,800 individuals aged 20 to 90. They discovered that the distribution of heat on our faces changes in distinct ways as we age. For instance, the nose and cheeks tend to cool down as we get older, while other areas like the forehead and around the eyes may become warmer.

But ThermoFace isn’t just about predicting your chronological age. The researchers found that the difference between a person’s predicted “thermal age” and their actual age correlated strongly with various health indicators. People whose thermal age appeared older than their actual age were more likely to have metabolic issues like high blood pressure or elevated blood sugar levels.

Perhaps most excitingly, the study suggests that ThermoFace could be used to detect certain metabolic diseases with high accuracy. The system was particularly good at identifying conditions like fatty liver disease and hypertension, often spotting these issues before traditional diagnostic methods.

facial temperatures
Average facial temperatures of three aging-status groups among women 50-60 years old. (CREDIT: Zhengqing Yu and Jing-Dong J Han)

Aging is a natural process,” says Jing-Dong Jackie Han, the paper’s corresponding author at Peking University in Beijing. “But our tool has the potential to promote healthy aging and help people live disease-free.”

The implications of this research are far-reaching. Imagine a future where a quick facial scan at your annual check-up could provide early warnings about your health, allowing for earlier interventions and lifestyle changes. Or consider how this technology could be used in remote or underserved areas, where access to complex medical testing is limited.

Interestingly, the study also found that lifestyle factors can influence your thermal age. People who reported getting adequate sleep tended to have “younger” thermal faces, while those with poor sleep habits appeared older. The researchers even conducted a small experiment where volunteers engaged in a two-week jump rope exercise program. Remarkably, after just two weeks, the participants’ thermal ages decreased by an average of five years!

This finding highlights the dynamic nature of our biological age. While we can’t turn back the clock on our chronological age, this study suggests that healthy lifestyle choices can indeed make us biologically younger – and it shows up on our faces.

The ThermoFace technology also revealed some fascinating differences between men and women in how their faces age. Women tended to show age-related changes in their facial heat patterns earlier than men, around age 50 compared to 60 for men. This aligns with other research suggesting that the timing and process of aging can differ between sexes.

While the technology is still in its early stages, the researchers envision a future where thermal imaging could become a standard tool in healthcare, providing a quick, non-invasive way to assess overall health and aging. They suggest it could be particularly useful for monitoring the effectiveness of anti-aging interventions or lifestyle changes.

As we continue to search for ways to extend our healthspan – the number of years we live in good health – tools like ThermoFace could prove invaluable. By giving us a literal picture of our biological age, they may motivate us to make healthier choices and allow doctors to catch potential health issues earlier.

The heat of your face, it turns out, has quite a story to tell. As this technology develops, we may all find ourselves taking a closer look in the thermal mirror, seeing not just our reflections, but a window into our health and longevity.

The findings are published in the journal Cell Metabolism.

Paper Summary


The researchers collected thermal facial images from over 2,800 Han Chinese individuals using a special infrared camera. They developed a method called “ThermoFace” to process these images, which involved identifying key facial landmarks and dividing the face into 897 small triangular regions. For each region, they recorded the maximum and minimum temperatures, as well as the temperature variation. The researchers then used various statistical and machine learning techniques, including deep learning algorithms, to analyze this data and create models that could predict age and detect certain health conditions.

Key Results

The study found that facial heat patterns change in predictable ways with age, such as cooling in the nose and cheek areas. The researchers developed several models to predict age based on these thermal patterns, with the best model achieving an average accuracy within about 5 years of a person’s actual age. They also found that the difference between predicted thermal age and actual age correlated with various health indicators, particularly those related to metabolism.

The models were able to detect certain metabolic diseases, like fatty liver and hypertension, with high accuracy (over 80% in some cases). Additionally, lifestyle factors like sleep and exercise were found to influence thermal age, with a two-week exercise program reducing thermal age by an average of 5 years.

“The thermal clock is so strongly associated with metabolic diseases that previous facial imaging models were not able to predict these conditions,” Han says.

Study Limitations

The study has several limitations. First, it was conducted primarily on Han Chinese individuals, so its applicability to other ethnic groups is uncertain. The researchers also note that factors like emotion, outdoor temperature, and seasonal influences could affect facial temperature, although they tried to control for these variables. The sample size, while large, may not be sufficient to capture all the variability in human aging and health conditions. Additionally, the exercise intervention study had a small sample size and short duration, requiring further investigation to confirm long-term effects.

Takeaways: What This Means for the Future

This study introduces a novel, non-invasive method for assessing biological age and health status using thermal facial imaging. The technology shows promise for early detection of metabolic diseases and could provide a quick, easy way to monitor overall health and the effectiveness of lifestyle interventions.

The researchers suggest that ThermoFace could be particularly useful in situations where traditional medical testing is not readily available. However, they emphasize that more research is needed to fully understand the relationship between facial temperature patterns and various health conditions.

The study also highlights the potential for simple lifestyle changes, like improved sleep and regular exercise, to have measurable effects on biological aging. As this technology develops, it could become a valuable tool in preventative healthcare, helping individuals and doctors to spot potential health issues early and track the effectiveness of interventions over time.

“We hope to apply thermal facial imaging in clinical settings, as it holds significant potential for early disease diagnosis and intervention,” Han says.

About StudyFinds Staff

StudyFinds sets out to find new research that speaks to mass audiences — without all the scientific jargon. The stories we publish are digestible, summarized versions of research that are intended to inform the reader as well as stir civil, educated debate. StudyFinds Staff articles are AI assisted, but always thoroughly reviewed and edited by a Study Finds staff member. Read our AI Policy for more information.

Our Editorial Process

StudyFinds publishes digestible, agenda-free, transparent research summaries that are intended to inform the reader as well as stir civil, educated debate. We do not agree nor disagree with any of the studies we post, rather, we encourage our readers to debate the veracity of the findings themselves. All articles published on StudyFinds are vetted by our editors prior to publication and include links back to the source or corresponding journal article, if possible.

Our Editorial Team

Steve Fink


Chris Melore


Sophia Naughton

Associate Editor

Leave a comment