Researchers at the Keck School of Medicine of the University of Southern California have built a blood-based screening algorithm that sharply reduced the number of unnecessary amyloid PET scans used to select participants for an Alzheimer's clinical trial, according to ConSalud. The work, published in Alzheimer's & Dementia: The Journal of the Alzheimer's Association, was applied during recruitment for the international phase 3 AHEAD 3-45 trial. ConSalud reported on the findings on 1 November 2026.
Why it matters
Screening is one of the most expensive stages of an Alzheimer's trial for study sites, ConSalud reports. Under the previous process, candidates could spend as long as three months in selection, and more than 70% of those who underwent a PET scan — widely treated as the reference method for detecting the disease — were ultimately found not to meet the criteria for enrolment.
The algorithm changed that picture. Among people who went on to have a PET scan during recruitment, the share later judged ineligible fell from 71% to 31%, according to ConSalud. In practical terms, the tool more than halved the number of scans that turned out to be unnecessary.
What the algorithm measures
The model draws on two biomarkers measured in blood plasma. One is the ratio of beta-amyloid, which reflects the early stages of protein buildup. The other is p-tau217, a marker that allows a more precise estimate of how much amyloid has accumulated in the brain. Age and APOE4 carrier status — both linked to a higher likelihood of amyloid buildup — are also factored in, ConSalud reports.
Rather than sorting patients into simple positive or negative categories, the system uses a statistical technique called Mixture of Experts (MoE). This approach accounts for the fact that amyloid does not accumulate evenly, and it places each person somewhere along a continuous spectrum of accumulation.
The tool was built using data from 1,080 AHEAD participants and then validated against separate information from the Wisconsin Registry for Alzheimer's Prevention. Development proceeded in stages during recruitment between 2020 and 2024, according to ConSalud: the first version, introduced in February 2022, brought the rate of ineligible PET scans down from 71% to 50%, and adding p-tau217 in May 2023 pushed it to 31%.
The trial and the drug behind it
AHEAD 3-45 is testing whether giving lecanemab earlier can improve the course of the disease. The drug clears deposits of beta-amyloid protein that gather in the brain and are tied to Alzheimer's progression; it is currently indicated for people who already show symptoms of cognitive decline.
The trial, however, seeks people with amyloid buildup who do not yet have symptoms — a process that can begin decades before memory problems appear. Only about 30% of cognitively healthy adults over 65 carry amyloid at levels high enough to qualify for studies like AHEAD 3-45, ConSalud reports.
The researchers see the results as strengthening the case for blood tests as a first-line screening step before more costly imaging. "If you can go to your doctor and get a blood test, you'll be able to know if you have the disease earlier," Langford said, according to ConSalud, pointing to possible future use in prevention. "If we can intervene earlier, we'll have a greater impact and, hopefully, prevent people from developing symptoms."
ConSalud notes that its health content is produced by specialist journalists and reviewed by an expert committee, while advising readers to raise any health questions with a medical professional.
What to watch: whether the algorithm is adopted at other trial sites and studied as a routine screening step outside research settings.
