Corners of eyes ‘provide best clues for predicting age’

The best way to predict a person’s age is to look at the skin around the corners of their eyes, according to a new study.

Researchers used an artificial intelligence (AI) system to predict age – and it was accurate to within 2.3 years.

They used a ‘photographic ageing clock’ that can tell a person’s age just from a small region of the face.

Humans can predict age with reasonable accuracy – but factors such as different ethnic groups can throw some people off.

But the new AI system is able to predict across all types of people fast, with near a perfect precision.

The PhotoAgeClock was developed by researchers from Haut.AI in collaboration with Insilico Medicine.

More than 8,400 anonymised, high-resolution left and right eye corner photos were scanned by the system.

The findings, published in the journal Ageing, were generated by algorithms that scanned thousands of peoples faces.

It was found that the eye corner and eyelid areas specifically had the most significant impact on age prediction.

Researchers claim that it is now possible to determine age by only using photos of the corners of the eye.

Anastasia Georgievskaya, CEO of Haut AI, said: “We are very happy to collaborate on this important artificial intelligence project.

“The future of consumer business is in personalisation and I hope that this study will lay the foundation for AI-powered consumer skincare and healthcare.

“Skin is our largest and one of the most important organs, understanding the many biological processes in skin using AI may lead to the many breakthroughs down the road.”

Dr Alex Zhavoronkov, CEO of Insilico Medicine, said: “Deep neural networks are often perceived as the black boxes; however, this is a common misconception – ageing research helps make DNNs more interpretable.

“This study shows what area of the face is most important for age estimation but when you do it on other data types like gene or protein expression, it is possible to see what genes are more important and construct the causal networks.

“I personally believe that the AI ageing clocks are among the most important breakthroughs in longevity biotechnology and we will see the many advances resulting from similar studies.

“As for this study, you may want to take care of the eye corners if you want to look younger to some of the age predictors.”

Estonia-based artificial intelligence company Insilico aim to use the new system to evaluate the impact of different lifestyles.

Their new system can also have an impact on smart sensors installed in clothing and ‘wearables’ such as fitness watches by using their data.

Researchers claim that their system will soon be able to measure the rate of ageing at any level.

By Daniel Hammond

Leave a Reply