Salk University's artificial intelligence might be able to predict whether a person will age healthily and gracefully or suffer from numerous age-related diseases.
In a recently published paper, a team of scientists analyzed skin cells of over 100 people aged 1 to 94 years old. They wanted to see whether skin cells would show signatures of aging and then fed the data to a custom machine-learning algorithms that was able to predict a person's age.
The scientists hope that this can be used to understand the biological processes of aging and address health conditions associated with it. Details of the study were published in the journal Genome Biology.
Age Is More Than Just A Number
Not everyone ages the same way. Some people exhibit signs of old age and get diseases associated with old age early in their lives because of an unhealthy lifestyle. Some age better, remaining strong and healthy even after 80 or 90 years old.
There is a difference between chronological aging, as in the amount of time that a person has been alive, and biological aging, which refers to how well the body is functioning. The researchers hope to explore the factors behind why some people age better than others.
"This experiment was designed to determine whether there are molecular signatures of aging across the entire range of the human life span," stated Saket Navlakha, an assistant professor and one of the authors of the study. "We want to develop algorithms that can predict healthy aging and nonhealthy aging, and try to find the differences."
For the study, the researchers looked at a specific type of skin cell called dermal fibroblasts, which is responsible for generating connective tissues and helping the skin cells. They brought samples to the lab to multiply, then used RNA sequencing (RNA-Seq) to look for biomarkers that changes when people grow older.
The machine learning was tasked to sort the RNA-Seq data and found biomarkers that indicate old age. The team was able to predict each person's age with only less than eight years error on average.
Machine Learning In A Hospital Setting
If their findings are validated, the researchers think that doctors can use the biomarkers found in the study to figure out when to screen patients for age-related diseases and give the advice to make healthy lifestyle changes.
"Aging is a driver of so many diseases, including Alzheimer's and other neurologic problems," added Navlakha. "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."
They warned, however, that the biomarkers, while it predicts aging, does not cause aging. More research needs to be done before the findings can be used in a hospital setting or to develop preventive treatments for diseases.