A two-minute digital cognitive assessment developed by Cumulus Neuroscience performed as well as or better than established clinical screening tools used to identify participants for Alzheimer’s disease clinical trials, according to data presented at the Alzheimer’s Association International Conference (AAIC) 2026.

Results from three independent studies showed that the company’s tablet-based Symbol Swap task successfully distinguished healthy participants, people with mild cognitive impairment (MCI) and those with Alzheimer’s dementia while also identifying blood biomarker-defined Alzheimer’s pathology, including in individuals who appeared cognitively normal using conventional assessments.

The findings suggest the digital assessment could help improve the efficiency of Alzheimer’s clinical trial recruitment by identifying participants who are more likely to have underlying disease pathology before more costly biomarker testing.

Clinical trials for Alzheimer’s disease increasingly rely on pre-enrichment strategies to identify participants with amyloid or tau pathology before enrolment. Improving this early screening process has the potential to reduce screen failures, shorten recruitment timelines and lower the cost of developing new therapies.

According to Cumulus, Symbol Swap matched or exceeded the performance of three widely used cognitive assessments — ADAS-Cog, MoCA and MMSE — while requiring only two minutes to complete. The assessment is delivered on a tablet and scored automatically, allowing it to be used both in clinics and remotely.

The task was evaluated across the company’s at-home CNS-101 study and two larger clinic-based studies, including the Fastball i4i study and the Global Alzheimer’s Platform BioHermes-002 study, which spans 20 research sites across the USA, Canada and Europe.

In two of the studies, pathology status was confirmed using blood plasma pTau-217, an increasingly important biomarker associated with Alzheimer’s disease.

Brian Murphy, co-founder and chief scientific officer of Cumulus Neuroscience, said: “It is striking that a two-minute, patient-friendly task can match or beat assessments that take a trained clinician 10 to 45 minutes to administer — and that it picks up Alzheimer’s pathology even in study participants who look cognitively normal on standard tests.”

He added that the findings suggest Symbol Swap could serve as an initial screening tool before blood biomarker testing or become part of future multi-modal digital endpoints used in Alzheimer’s research.

A second presentation at AAIC highlighted data from the CNS-101 study, showing that the company’s NeuLogiq platform, which combines digital cognitive assessments with electroencephalography (EEG), was well tolerated by participants and demonstrated sufficient sensitivity to support smaller and potentially more efficient Alzheimer’s clinical trials.

James Rowe, professor of cognitive neurology at the University of Cambridge and principal investigator for CNS-101, said: “In CNS-101 we found that multi-domain digital cognitive and EEG measures from the NeuLogiq Platform were well tolerated by people living with Alzheimer’s disease and sensitive enough to capture meaningful change.”

Cumulus believes combining rapid digital cognitive testing with physiological measurements could streamline participant selection while reducing the burden on patients and trial sites. As Alzheimer’s drug development increasingly incorporates blood biomarkers and digital endpoints, tools capable of identifying suitable participants quickly and consistently are expected to play a growing role in future clinical research.