Machine‐learning analysis of real‐world multimodal data collected autonomously at home detects dementia more precisely than a traditional composite scale

Laura M Rueda‐Delgado, Alison R Buick, Hugh Nolan, James B Rowe, Brian Murphy · 2025

Read Machine‐learning analysis of real‐world multimodal data collected autonomously at home detects dementia more precisely than a traditional composite scale by Laura M Rueda‐Delgado, Alison R Buick, Hugh Nolan, James B Rowe, Brian Murphy (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11712194.txt.

Description

Standard dementia tests need trained staff, clinic visits, and a patient's best day. Laura Rueda-Delgado and co-authors tested a home-based digital platform in 2025 that collects many kinds of data on its own. Volunteers with mild Alzheimer dementia and matched controls used tablets at home for tasks, plus brain-wave recordings awake and asleep.

From an early two-week burst, the team drew over a thousand sessions and hundreds of features. A learning model using all features separated patients from controls a bit better than a standard test battery. Features from the tablet tasks alone did just as well. The authors say home data can match clinic scales and allow finer tracking of disease severity over time.

Catalog record

CREATORLaura M Rueda‐Delgado, Alison R Buick, Hugh Nolan, James B Rowe, Brian Murphy
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE3 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11712194

Browse the full library · About the Tower of Babel