Validation of machine learning models to detect neuropathologies

Farooq Kamal, Cassandra Morrison, Michael Oliver, Mahsa Dadar · 2025

Read Validation of machine learning models to detect neuropathologies by Farooq Kamal, Cassandra Morrison, Michael Oliver, Mahsa Dadar (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-11709769.txt.

Description

Farooq Kamal and co-authors validate machine learning models for brain pathology in a 2025 study. White matter bright spots on scans grow with age and track with thinking decline, yet their exact role in Alzheimer's disease stays debated. The team asked which scan, clinical, and personal features best predict hidden brain pathology measures. Data came from sixty-five participants in a major Alzheimer's imaging program.

Several model families were trained for both continuous and yes-no outcomes, from tangles staging to plaque scores. Feature selection kept the top seven predictors for each target. The work checks whether algorithms can flag pathology in living patients from ordinary data. Good prediction would spare patients invasive tests and help trials recruit the right participants.

Catalog record

CREATORFarooq Kamal, Cassandra Morrison, Michael Oliver, Mahsa Dadar
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE2 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11709769

Browse the full library · About the Tower of Babel