Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Can AI Predict If You Will Age Healthily or Not?

DZone's Guide to

Can AI Predict If You Will Age Healthily or Not?

As societies across the world age, the goal in healthcare has turned towards ensuring people age as healthily as possible.

· AI Zone ·
Free Resource

The most visionary programmers today dream of what a robot could do, just like their counterparts in 1976 dreamed of what personal computers could do. Read more on MistyRobotics.com and enter to win your own Misty. 

As societies across the world age, the goal in healthcare has turned towards ensuring people age as healthily as possible. A recent study from Salk's Integrative Biology Laboratory suggests AI can help to predict the likelihood of that happening.

It's fairly well established that our biological and chronological ages are not always the same. Some of the factors that influence this discrepancy are also becoming better understood, with things like diet and physical activity being believed to play a part.

The researchers attempted to discover whether AI can help and trained an algorithm on skin cells from people ranging from the very young to the very old. They were specifically looking for any molecular signatures that could be used to predict age.

"This experiment was designed to determine whether there are molecular signatures of aging across the entire range of the human life span," the researchers say. "We want to develop algorithms that can predict healthy aging and non-healthy aging and try to find the differences."

Skin Analysis

The researchers focused on a particular type of skin cell called dermal fibroblasts. These cells generate the kind of connective tissue used when our skin heals from injury. The cells were chosen because they're relatively easy to obtain but are also believed to contain strong signatures of aging.

The team believes that their work is robust, as it included such a wide spread of ages in the dataset used to train the algorithm. What's more, their work has also been made available to the public so that other researchers can build upon it.

When the algorithm was tested on fibroblasts from 10 patients with a known condition called progeria, which accelerates aging, the system was able to correctly predict their biological age to be around a decade more than their calendar age.

The researchers are conscious that their findings are not taken to conflate cause and effect, but nonetheless, they do believe that such an approach could eventually be used by doctors to help them predict when to start screening patients for age-related conditions or to recommend healthier lifestyle choices. For that to happen, however, they accept that more research needs to be done, and they plan to work on determining whether these signatures exist in other types of cells as the first step.

"Aging is a driver of so many diseases including Alzheimer's and other neurologic problems," the researchers conclude. "If we are able to show that the changes we've seen in fibroblasts are connected with aging in other types of cells, we may eventually be able to use these signatures to develop targeted interventions."

Robot Development Platforms: What the heck is ROS and are there any frameworks to make coding a robot easier? Read more on MistyRobotics.com

Topics:
artificial intelligence ,machine learning ,ai in healthcare ,skin analysis

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}