Sleep Test May Help Spot Alzheimer’s Early, Study Finds Scientists develop sleep test that may help spot Alzheimer’s early

Researchers have developed an artificial intelligence (AI) tool that could help identify Alzheimer’s disease by analyzing brain activity during sleep—offering what they hope could eventually become a simpler and less invasive way to detect the condition before symptoms become obvious.

The study, published in GeroScience, was led by researchers from Universidad Carlos III de Madrid and Hospital Universitario Severo Ochoa in Spain. The findings suggest that patterns in nighttime brain waves may reveal early biological changes linked to Alzheimer’s years before significant memory problems emerge.

“AI is not intended to replace any medical tests, but rather to support early diagnosis,” study author Lorena Gallego Viñarás said in a statement.

Alzheimer’s is a progressive brain disease that currently affects an estimated 7.4 million Americans aged 65 and older. It can begin causing damage years before symptoms such as memory loss, confusion and difficulty completing everyday tasks appear.

Newsweek has reached out to Lorena Gallego Viñarás for a comment.

What Sleep Reveals About the Brain

The researchers focused on sleep because it is a period when the brain is particularly active in clearing away cellular waste, including beta-amyloid, a protein associated with Alzheimer’s disease.

“Signals were recorded using a series of electrodes placed on the scalp that capture the electrical activity of neurons throughout the night,” Viñarás, from the Department of Neuroscience and Biomedical Sciences at UC3M, said.

“We used AI to analyze this electrical activity and identify certain changes that may indicate the accumulation of proteins in the brain, which will later lead to neurodegenerative diseases.”

Previous studies have suggested the relationship works in both directions: Alzheimer’s can disrupt normal sleep patterns, while poor sleep may contribute to biological processes linked to the disease’s progression.

“Recording electrical activity during sleep provides us with a window into the biological processes taking place, which, over the years, can lead to forgetfulness and the characteristic symptoms of Alzheimer’s,” study leader Arrate Muñoz-Barrutia, a professor in the Department of Neuroscience and Biomedical Sciences at Universidad Carlos III de Madrid, said in a statement.

How the AI Was Tested

The study included 42 people with mild to moderate Alzheimer’s disease and 58 cognitively healthy adults.

Participants underwent overnight sleep studies known as polysomnographies. During these tests, electrodes placed on the scalp recorded brain activity throughout the night.

Researchers then used AI and machine-learning techniques to analyze the brain-wave data. The results were compared with levels of proteins commonly used as Alzheimer’s biomarkers in cerebrospinal fluid, including beta-amyloid, tau and neurofilament light chain.

According to the researchers, the AI system was able to distinguish healthy individuals from those with Alzheimer’s with a high degree of accuracy.

Why Earlier Detection Matters

Previous research suggests cognitive decline can begin up to 15 years before a dementia diagnosis—an umbrella term for conditions that affect memory, thinking and daily functioning, with Alzheimer’s disease being the most common form.

With current available treatments showing the greatest benefit in the earliest stages, scientists are increasingly searching for ways to identify the condition sooner.

Diagnosing Alzheimer’s currently involves a combination of clinical assessments, blood tests, brain imaging and, in some cases, a lumbar puncture, or spinal tap, to analyze cerebrospinal fluid. Some of these tests can be expensive, invasive or difficult to access.

The new research explored whether sleep could provide another route to early detection.

Different Forms of Alzheimer’s

The technology also identified three distinct biological subgroups among Alzheimer’s patients.

Each group showed different patterns in disease-related protein levels, suggesting the condition may not follow the same biological pathway in every patient, even in its early stages.

The researchers said these findings could help improve understanding of how Alzheimer’s develops and potentially support more personalized approaches to diagnosis and treatment in the future.

Potential for At-Home Screening

The team believes sleep-based assessments could eventually complement blood tests that measure Alzheimer’s-related proteins.

Because sleep studies are noninvasive, researchers suggest the approach could become a relatively affordable screening tool that might even be carried out from a patient’s home.

They also noted that identifying and treating sleep disorders could have additional benefits, given the growing evidence linking disrupted sleep to cognitive decline.

“Our research seeks a tool that enables early diagnosis of Alzheimer’s, one that is non-invasive, affordable and capable of being extended to the majority of the population,” Dr. Anna Michela Gaeta, a pulmonologist at Hospital Universitario Severo Ochoa, said in a statement.

The researchers said the findings highlight the growing role that collaboration between neurology, sleep medicine and engineering could play in developing earlier ways to detect Alzheimer’s, particularly as new treatments increasingly target the disease before symptoms become severe.

Reference

Anna Michela Gaeta et al, Quantitative sleep EEG identifies CSF core biomarker-related subgroups in Alzheimer’s disease, GeroScience (2026). DOI: 10.1007/s11357-026-02266-z

Contact Newsweek editors on this story: Kara Dolman and Emma Lee-Sang