UC San Francisco scientists have found a way to predict Alzheimer’s disease up to seven years before symptoms appear by analyzing patient records using machine learning.

The conditions that most affected Alzheimer’s prognosis were high cholesterol and, for women, the bone-weakening disease osteoporosis.

This work shows the promise of using artificial intelligence (AI) to find patterns in clinical data that can then be used against large genetic databases to determine who is at risk. running Researchers hope that one day it will speed up the diagnosis and treatment of Alzheimer’s and other complex diseases.

“This is the first step toward using AI on routine clinical data, not only to identify risk as early as possible, but also to understand the biology behind it,” said Alice Tang, lead author of the study. who is an MD/PhD student in it. Sirota Lab at UCSF. “The power of this AI approach comes from identifying risk based on combinations of diseases.”

The results are declared on 21 February 2024. Nature Aging.

Clinical data and predictive power

Scientists have long sought to discover the biological drivers and early predictors of Alzheimer’s disease, a progressive and ultimately fatal form of dementia that destroys memory. Alzheimer’s affects about 6.7 million Americans, nearly two-thirds of whom are women. The risk of developing the disease increases with age, and women live longer than men, but it is not fully understood why more women than men develop the disease.

Researchers used UCSF’s clinical database of more than 5 million patients to look for conditions in patients who were diagnosed with Alzheimer’s at UCSF’s Memory and Aging Center and compared those who did not. who were without AD and found that they could identify with 72 percent predictive power. The disease will develop until seven years ago.

Several factors, including high blood pressure, high cholesterol and vitamin D deficiency, were predictive in both men and women. Erectile dysfunction and an enlarged prostate were also predictive for men. But for women, osteoporosis was an especially important predictor.

This does not mean that everyone with bone disease, which is common in older women, will develop Alzheimer’s.

“It is this combination of diseases that allows our model to predict the onset of AD,” said Tang, “Our finding that osteoporosis is a predictive factor for women is a significant predictor of bone health and dementia risk.” highlights the biological interactions between

A health medicine approach

To understand the biology underlying the model’s predictive power, the researchers turned to public molecular databases and a special tool developed at UCSF called SPOKE (Scalable Precision Medicine Oriented Knowledge Engine) by Sergio Baranzini. , Ph.D., was developed in the lab of Neurology and member of the UCSF Weill Institute for Neurosciences.

SPOKE is essentially a database of databases that researchers can use to identify patterns and potential molecular targets for therapy. It picked up the known association between Alzheimer’s and high cholesterol through a variant of the apolipoprotein E gene APOE4. But, when combined with genetic databases, it also identified a link between osteoporosis and Alzheimer’s in women, through a variant in a little-known gene called MS4A6A.

Ultimately, the researchers hope the approach can be used with other hard-to-diagnose diseases like lupus and endometriosis.

“This is a great example of how we can leverage patient data through machine learning to predict which patients will develop Alzheimer’s,” said the study’s senior author, Marina Sirota, PhD. It’s more likely to happen, and to understand the reasons why,” said the study’s senior author, Marina Sirota, Ph.D. Associate Professor at the Bacher Computational Health Sciences Institute at UCSF.