A Machine Learning Approach Utilizing Normal‐appearing white matter Amyloid uptake for Amyloid Positivity Classification and Clinical progression prediction

Sungman Jo, Ji Won Han, Ki Woong Kim · 2025

Read A Machine Learning Approach Utilizing Normal‐appearing white matter Amyloid uptake for Amyloid Positivity Classification and Clinical progression prediction by Sungman Jo, Ji Won Han, Ki Woong Kim (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-11716228.txt.

Description

Sungman Jo, Ji Won Han, and Ki Woong Kim built, in a 2025 study, a learning method that calls amyloid status from white matter uptake on brain scans. Standard calls rest on cortex uptake, judged by eye or by a cutoff. The team asked whether the quiet-looking white matter holds a cleaner signal.

Scan and MRI data covered 813 people aged fifty and up from dementia clinics and a national aging study. Their method compares cortex uptake with white matter uptake and sorts people by a mixture model. Against expert visual reads, it scored 0.936 accuracy with very high sensitivity. It beat a plain cortex cutoff on several gauges. The team also checked which call best foresaw decline in people where methods disagreed.

Catalog record

CREATORSungman Jo, Ji Won Han, Ki Woong Kim
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE3 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11716228

Browse the full library · About the Tower of Babel