New blood screening algorithm reduces unnecessary Alzheimer's PET scans

A new blood-based screening algorithm dramatically reduced the number of unnecessary PET scans needed to recruit patients at risk of Alzheimer's disease for a clinical trial, according to research from scientists at the Keck School of Medicine of USC published in Alzheimer's & Dementia^®: The Journal of the Alzheimer's Association.

Known as AHEAD 3-45, the clinical trial is a phase 3 international study testing whether earlier treatment with an approved drug for Alzheimer's disease, known as lecanemab, could lead to better outcomes. Lecanemab removes sticky amyloid-beta protein aggregates that accumulate in the brain and are associated with the progression of Alzheimer's disease. The drug can slow the clinical progression of the disease by about 30% but is currently prescribed only for patients who already have symptoms of cognitive decline.

The AHEAD 3-45 trial specifically targets people with buildup of amyloid-beta, which happens early in the progression of Alzheimer's disease, sometimes decades before symptoms of cognitive impairment appear. However, only about 30% of cognitively healthy adults over 65 have amyloid levels high enough to qualify for trials like AHEAD. A major hurdle for recruiting patients to the trial is identifying and screening large numbers of people who may have hallmarks of the disease, but don't yet have obvious symptoms such as memory loss. 

Before blood plasma screening was introduced, candidates for the AHEAD 3-45 trial had to navigate a screening process that could take up to three months from first visit to enrollment. After undergoing positron-emission tomography (PET), a costly imaging scan considered the gold standard for Alzheimer's diagnosis, more than 70% of candidates would learn that they were ineligible for the trial.

When the algorithm was used in recruiting participants for the study, it cut the rate of people who received a PET scan but did not qualify for the trial from more than 70% to 31%.

The screening part of an Alzheimer's trial is usually one of the costliest parts of the clinical trial for study sites. We definitely helped reduce the burden for participating clinical sites and for patients by reducing the number of individuals having to undergo PET scans."

Oliver Langford, MS, corresponding author, modeling and simulation director at the USC Epstein Family Alzheimer's Therapeutic Research Institute, Keck School of Medicine

Using a blood-plasma screening algorithm for efficient clinical trial recruiting

In recent years, blood tests have shown increasing promise in helping to determine if someone is at risk for Alzheimer's disease. These tests measure proteins in blood plasma that are biomarkers of the disease.

The algorithmic screening tool developed by USC researchers incorporated two key blood plasma biomarkers: the amyloid-beta ratio, an earlier signal of amyloid accumulation, and p-tau217, a recently discovered marker that more reliably reflects amyloid burden in the brain.

The algorithm was developed using data from 1,080 AHEAD participants and validated in an independent dataset from the Wisconsin Registry for Alzheimer's Prevention study. In addition to blood biomarkers, the model incorporated age and APOE4 carrier status, both factors known to increase the risk of amyloid accumulation. The algorithm was refined across three successive versions during active recruitment for the study, which ran from 2020 to 2024.

First introduced in February 2022, the algorithm using the amyloid-beta ratio reduced the proportion of PET-ineligible participants from 71% to 50%. In May 2023, p-tau217 was integrated into a second version, and that figure dropped further to 31%. This enabled the trial to more efficiently enroll participants with both intermediate and elevated amyloid levels.

Central to the algorithm's design is a statistical technique called Mixture of Experts (MoE), which allows the model to account for the fact that amyloid doesn't accumulate uniformly. Rather than simply sorting participants into positive or negative categories, the team built a model that estimates where someone falls on a continuous spectrum of amyloid buildup.

"When we look at amyloid levels at a population level, we see a peak where people are amyloid-negative and another peak for those with elevated amyloid plaque buildup," said Langford. "There is a region in the intermediate range that isn't fully captured by the plasma marker alone. The Mixture of Experts approach helps model that uncertainty more effectively and is better suited to the type of data collected."

Blood testing as a tool for early detection and earlier intervention

The study's results add to a growing body of evidence that blood tests can serve as a practical first-pass filter before more intensive and costly testing.

"It's going to allow more people to access testing that can help determine whether they have Alzheimer's disease pathology," says Langford. "If you are able to go to your doctor and get a blood test done, you'll be able to understand whether you have the disease earlier."

Increasing the efficiency in screening for clinical trials like AHEAD 3-45 may also bring researchers a step closer to primary prevention of Alzheimer's disease. 

"If we can intervene earlier," said Langford, "we'll have a larger effect and hopefully prevent people from having symptoms."

About this study

In addition to Langford, the study's other authors include Rema Raman, Paul Aisen, Doris Molina-Henry, Gustavo A. Jimenez-Maggiora, Robert A. Rissman and Michael C. Donohue from the Epstein Family Alzheimer's Therapeutic Research Institute, Keck School of Medicine, University of Southern California; Reisa Sperling, Keith Johnson, Colin Birkenbihl, Madison Cuppels, and Rachel F. Buckley from Harvard Medical School, Brigham and Women's Hospital, Massachusetts General Hospital; Pallavi Sachdev, and David Li from Eisai Inc.; and Sterling C. Johnson from C2N Diagnostics.

The AHEAD Study is supported by Alzheimer's Clinical Trials Consortium (ACTC), which is funded by a Cooperative Agreement from the National Institute on Aging (NIA), National Institutes of Health (NIH) under award number U24AG057437. The study is a public-private partnership funded by the National Institute on Aging of the National Institutes of Health, Eisai, the GHR Foundation, the Alzheimer's Association, and other philanthropic organizations.