Subscribe
Artificial intelligence (AI)-powered models may help identify medical conditions like diabetes and fatty liver in their early stages, according to a new study.
Using a thermal camera, the AI model can detect temperature differences that are too small to be sensed by touch in different parts of the face. These findings could provide insights into how our body is ageing and health, the study published in Cell Metabolism stated.
For example, people with diabetes and fatty liver disease are likely to have higher eye area temperatures than their healthy counterparts of the same age.
“We hope to apply thermal facial imaging in clinical settings, as it holds significant potential for early disease diagnosis and intervention,” Jackie Han from Peking University in Beijing and the paper’s corresponding author, said in a statement.
Body temperature is a key parameter that affects cell function and organism survival. Research has shown that lower body temperature is linked to a longer lifespan and slower ageing in many endothermic species, which include animals like birds and mammals that can generate and control their internal heat.
Body temperatures can increase with high metabolic rates, which in turn, can be triggered by psychological and metabolic stress. Metabolic rate is influenced by ambient temperature.
The body’s surface temperature is closely correlated with the face, and yet the temperature distribution features of the human face and its link with aging and various diseases have not been explored, the researchers wrote in their research.
So, they collected thermal facial images of 2,811 individuals, aged between 21 and 88 years from 2020 to 2022.
The team developed the ‘‘ThermoFace’’ (TF) method, which combined a facial recognition and temperature extraction system to generate thermal-image-based aging clocks. Using this, they trained AI models to predict a person’s thermal age.
Their model showed that both males and females showed a decrease in temperatures in the nose, cheeks, and eyebrows with age, beginning at around 50 years in females and around 60 years in males. Images were collected in the morning when temperatures in air-conditioned rooms were between 20C and 25C when participants were brought to a calm state of mind. Emotion and environmental temperature changes can influence the results.
People dealing with metabolic disorders such as diabetes and fatty liver showed faster thermal ageing, with higher temperatures being recorded in the eye area than their healthy counterparts of the same age. Similarly, people with elevated blood pressure also showed higher cheek temperatures.
The team analysed the blood samples of the participants to understand the factors driving these differences.
They found that the increase in temperatures around the eyes and cheeks was driven primarily due to a spike in cellular activities related to inflammation, such as repairing damaged DNAs and fighting infections.
Next, the team began another experiment to test whether exercise influenced thermal ageing. Thirty participants were a part of the study. Of them, 23 were given jump rope training for an hour for 2 weeks. Seven were not subjected to any training.
Jump training, according to the study, enhances cardiovascular health, effectively burns calories, provides full-body exercise, and improves coordination and agility.
Two weeks later, the team saw that the participants who exercised reduced their thermal age by five years.
“Limitations in sample size and tracking duration necessitate further in-depth investigation into the long-term metabolic effects of sustained physical activity,” the researchers wrote in the study.
The study noted that it would be interesting to see whether the eye area—due to its intense development of blood vessels and metabolic activities—is the most sensitive to fluctuations in metabolic status.
It also added that it would be possible to differentiate between different diseases based on thermal facial patterns as they display differential temperature changes on the cheeks, forehead, and peri-mouth regions.