Mobile self-test can serve as early-warning system for Alzheimer’s

Harvard researchers have demonstrated a web-based program that allows cognitively normal individuals to screen themselves, unsupervised, for the type of memory decline that may signal encroaching Alzheimer’s disease.

Calling the system BRANCH for Boston Remote Assessment for Neurocognitive Health, neuropsychologist Kathryn Papp, PhD, and colleagues report that the project’s 234 participants ranged in age from 50 to 89 years old, used mainly smartphones and completed the test battery with few technical snags.

Some of the cohort also received in-person cognitive testing and some additionally received neuroimaging.

The team found BRANCH scores correlated “moderately” with those from the in-person neurocognitive batteries and that worse BRANCH performance was associated with amyloid and tau burdens as found in imaging.

The latter findings suggest that BRANCH “captures memory performance that corresponds with biomarker burden in cognitively normal individuals who may be at risk for future disease progression,” Papp and co-authors write.

Further, BRANCH “reliably captures meaningful cognitive information remotely, suggesting promise as a digital cognitive marker [that is] sensitive early in the Alzheimer’s disease trajectory,” the authors assert.

Among the limitations the authors acknowledge are the unlikelihood that tech-savvy older people with smartphones represent the older U.S. population as a whole; the cohort’s higher than average education level and the inability of the unsupervised setting to adjust for contextual conditions that would be apparent in person.

These would include such considerations as observable anxiety, boredom and task approach.

Still, Papp et al. conclude, the proof-of-concept study shows that digital programs like BRANCH may supply “reliable and meaningful cognitive data among cognitively normal individuals.”


Digital capture of cognition, unlike traditional measures, has multiple benefits including increased accessibility, automated data capture and storage, scalability, and cost-effectiveness. There is a need in Alzheimer’s disease secondary prevention for digital cognitive tests that target fundamental aspects of early memory decline and can be completed on a personal device. Here, we provided evidence for the feasibility, reliability and validity of BRANCH as a cognitive measure for use in preclinical Alzheimer’s disease.”

The study is current and available in full for free in Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring.

Around the web

The Department of Defense is gifting Case Western researchers a grant to study the use of AI in determining whether patients require surgery. 

This study brings light to the prospect of a "fully automated solution" for echocardiogram analysis, experts reported.

Experts noted a "significant" reduction in false positives and false negatives using their modified machine learning model.

Trimed Popup
Trimed Popup