How AI Can Identify Alzheimer’s Risk Factors

March 20, 2024

There’s been much in the media recently about artificial intelligence, or AI. Now scientists are using AI to spot previously unknown potential risk factors for Alzheimer’s disease.

The analysis, from researchers at the University of California, San Francisco, used computers to review medical records from more than 5 million patients from the university’s Memory and Aging Center. The study identified 749 individuals who had been diagnosed with Alzheimer’s disease for whom at least seven years of health data was available. Using a type of AI known as machine learning, they compared the patients’ medical histories over those seven years with over 250,000 peers of similar age who had not been diagnosed with Alzheimer’s. The medical histories included information about diagnosed diseases as well as lab and medical testing results.

The investigators found, not surprisingly, that patients with heart disease or high cholesterol were at increased risk of developing Alzheimer’s disease years down the road. Numerous earlier studies have shown a strong link between heart disease, including hypertension and high cholesterol, and an increased risk of dementia.

But the analysis revealed other potential Alzheimer’s risk factors as well, some of which have been suggested by earlier reports. In both men and women, having depression was tied to an increased risk of Alzheimer’s disease, as was low blood levels of vitamin D. In men, erectile dysfunction and an enlarged prostate were likewise tied to an increased Alzheimer’s risk. And in women, osteoporosis, marked by brittle bones, showed a particularly strong link to an increased risk of Alzheimer’s disease. The researchers also identified a gene tied to osteoporosis that could one day prove a potential treatment target.

“This is a first step towards using AI on routine clinical data, not only to identify risk as early as possible, but also to understand the biology behind it,” said the study’s lead author, Alice Tang, an MD/PhD student at UCSF. “The power of this AI approach comes from identifying risk based on combinations of diseases.” The findings were published in the journal Nature Aging.

The links do not prove that having a condition like osteoporosis or low vitamin D levels causes Alzheimer’s disease; they only show an association. Many people who have these conditions will never develop dementia. But the findings do suggest that having one of these conditions could raise your risk of developing Alzheimer’s disease. 

The study did not look at whether treating conditions like osteoporosis or low vitamin D would lower Alzheimer’s risk. But the researchers are following up with additional analysis to see whether treatment might mitigate the risk.

Knowing you are at higher risk for Alzheimer’s might spur you to adopt lifestyle measures that might lower your risk. Being physically active, eating a heart healthy diet, staying socially engaged, keeping hearing intact, and not smoking, for example, have been shown to prevent up to 40 percent of known cases of Alzheimer’s disease and other forms of dementia.

By ALZinfo.org, The Alzheimer’s Information Site. Reviewed by Eric Schmidt, Ph.D., Fisher Center for Alzheimer’s Research Foundation at The Rockefeller University. 

Source: Alice S. Tang; Katherine P. Rankin; Gabriel Cerono; et al: “Leveraging electronic health records and knowledge networks for Alzheimer’s disease prediction and sex-specific biological insights.” Nature Aging, February 21, 2024 


Alzheimer's Articles