Cumulus Neuroscience Presents Data at AAIC 2026 Annual Meeting Showing a Two-Minute Digital Task Matches or Outperforms Clinical Benchmarks for Alzheimer's Trial Pre-enrichment

Across three independent studies, the NeuLogiq® Platform two-minute tablet-based Symbol Swap task delivered clinically meaningful discrimination between control, MCI and Alzheimer's dementia groups and detected blood-biomarker-defined pathology — including in clinically normal individuals — with accuracy matching or exceeding the ADAS-Cog, MoCA and MMSE benchmarks.

LONDON, July 15, 2026 /PRNewswire/ -- Cumulus Neuroscience (Cumulus; The Company), a global digital health company focused on advancing neuroscience clinical trials and patient care through improved data, today presented data on its Symbol Swap digital cognitive task at the Alzheimer's Association International Conference 2026. The poster titled, 'A Brief Digital Symbol-Coding Task Outperforms Clinical Benchmarks for Alzheimer's Trial Pre-enrichment,' reports interim data on Symbol Swap — a two-minute, tablet-based implementation of the classic Symbol Coding (Digit Symbol Substitution) Task that measures executive function — across one completed at-home study and two large in-clinic studies.

Across three independent studies, Symbol Swap matched or exceeded the pre-enrichment performance of established clinical cognitive screeners in just two minutes, delivering clinically meaningful discrimination between control, MCI and Alzheimer's dementia groups while dramatically reducing participant and site burden. It showed robust associations with biomarker-defined Alzheimer's pathology (blood plasma pTau-217), even in clinically normal individuals who would typically score well on standard tests — suggesting it could flag those most likely to be amyloid- or tau-positive and improve the efficiency of downstream plasma, PET or CSF screening. Digitally administered and automatically scored, Symbol Swap scales readily across large, multi-site trials in both in-clinic and at-home workflows, making it an attractive first-line enrichment filter — preceding plasma biomarkers or feeding composite digital endpoints — with the potential to cut screen-failure rates and accelerate recruitment into Alzheimer's trials.

"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," said Brian Murphy, PhD, Cumulus Co-Founder and CSO. "This data confirms that Symbol Swap may be a powerful first-line filter, preceding plasma biomarkers or feeding a multimodal composite. We are grateful to all the study participants and research collaborators who made these important findings possible."

Symbol Swap was evaluated in CNS-101, a first-of-its-kind validation study that measured functional neurophysiology with the NeuLogiq Platform at home in patients living with mild Alzheimer's dementia and healthy controls (compared with the ADAS-Cog); the Fastball i4i study (in-clinic; compared with the MoCA); and the Global Alzheimer's Platform (GAP) BioHermes-002 study (20 sites across the US, Canada and Europe; compared with the MMSE). Pathology status in CNS-101 and the Fastball i4i study was defined by the AlzPath phosphorylated-tau 217 assay. Data presented from the Fastball i4i study and BioHermes-2 study are interim.

"The Bio-Hermes-002 study is focused on enrolling participants with or without memory concerns to help evaluate blood or digital tests that may help identify the presence of amyloid plaques or tau tangles in the brain, the hallmark pathologies associated with Alzheimer's disease," said Lammert Albers, Chief Commercial Officer for GAP. "The data presented by Cumulus suggests that digital assessments, including Symbol Swap, may help identify individuals who are more likely to have underlying Alzheimer's pathology and could support more efficient selection of participants for follow-up blood-based biomarker testing. This approach has the potential to shorten enrollment timelines and lower screening costs."

A second poster featuring NeuLogiq data titled 'Multi-domain Digital Endpoints for Decentralized Alzheimer's Trials: Experience from the CNS-101 Study (NeuLogiq^®),' was presented by Dr. James Rowe, Professor of Cognitive Neurology at the University of Cambridge and Principal Investigator on CNS-101. This study confirmed NeuLogiq Platform cognitive and EEG assessments were well tolerated by study participants, and their sensitivity could enable smaller, more efficient trials.

"Alzheimer's trials have long depended on assessments that are burdensome for participants and difficult to use at scale," said Dr. James Rowe, Professor of Cognitive Neurology at the University of Cambridge and Principal Investigator on CNS-101. "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. That sensitivity makes it possible to design smaller, more efficient trials — reducing the burden on patients while lowering the time and cost to test new therapies."

"Getting the right participants into trials is one of the most expensive and frustrating bottlenecks in Alzheimer's drug development today," said Tina Sampath, CEO of Cumulus. "A low-cost, patient-friendly, automatically scored task that runs at home or in clinic, and points to who is most likely to be biomarker-positive, has real potential to cut screen-failure rates and ease the burden on patients and sites. The two posters presented at AAIC tell a connected story: alongside Symbol Swap's power to enrich at the front end, our CNS-101 data show that NeuLogiq's multi-domain cognitive and EEG endpoints are well tolerated and sensitive enough to enable smaller, more efficient trials — together, that's a path to substantially reducing the cost and timeline of every study where they're deployed."

Cumulus supports precision in CNS clinical trials for its industry partners by enabling remote monitoring of patients across multiple domains of brain function. To learn more, visit www.cumulusneuro.com.

About Cumulus Neuroscience

With a mission to generate the data and insights required to accelerate diagnosis and management of central nervous system (CNS) disorders for millions of patients and caregivers around the world, Cumulus Neuroscience is advancing NeuLogiq®, an AI-based, multi-domain digital biomarker platform to enable better, faster decision making in neurology and neuropsychiatry clinical trials and patient care. Designed for and with 10 of the world's leading pharma companies, the platform enables decentralized trials and is already making a difference in the development of therapies for Alzheimer's Disease, depression and schizophrenia.