Algorithmic tool may improve screening of patients for an Alzheimer's clinical trial

by Keck School of Medicine of USC

edited by Gaby Clark, reviewed by Robert Egan

Gaby Clark

Scientific Editor

Meet our editorial team
Behind our editorial process

Robert Egan

Senior Editor

Meet our editorial team
Behind our editorial process Editors' notes

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

peer-reviewed publication

trusted source

proofread

The GIST Add as preferred source

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 the journal Alzheimer's & Dementia.

Known as AHEAD 3-45, the clinical trial is a phase 3 international study testing whether earlier treatment with an approved Alzheimer's drug, 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 to recruit 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," said corresponding author Oliver Langford, MS, modeling and simulation director at the USC Epstein Family Alzheimer's Therapeutic Research Institute at the Keck School of Medicine. "We definitely helped reduce the burden for participating clinical sites and for patients by reducing the number of individuals having to undergo PET scans."

Using a blood plasma screening algorithm for efficient clinical trial recruitment

In recent years, blood tests have shown increasing promise in helping to determine whether 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," said 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 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."

Publication details

More efficient screening for preclinical Alzheimer's clinical trials using mixture of experts, Alzheimer's & Dementia (2026). DOI: 10.1002/alz.71681

Journal information: Alzheimer's & Dementia

Key medical concepts

Alzheimer's DiseasePositron-Emission Tomography

Clinical categories

NeurologyLaboratory medicine Provided by Keck School of Medicine of USC Who's behind this story?

Gaby Clark

MA in English, copy editor since 2021 with experience in higher education and health content. Dedicated to trustworthy science news. Full profile →

Robert Egan

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

Citation: Algorithmic tool may improve screening of patients for an Alzheimer's clinical trial (2026, September 9) retrieved 9 September 2026 from https://medicalxpress.com/news/2026-09-algorithmic-tool-screening-patients-alzheimer.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.