Assessment of Alzheimer-related pathologies of dementia using machine learning feature selection

Aug 3, 2026

Upload by Logic

Although dementia-related brain lesions are numerous, their relationship to dementia, interactions, and how to quantify them remain unclear. Systematically evaluating neuropathological measures by association with dementia can improve diagnostic systems and define treatment targets. This study uses machine learning feature selection to identify critical Alzheimer-related pathology features linked to dementia status in a CFAS cohort (n=186), comparing feature ranking, classification performance, and misclassification patterns.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Abstract

Introduction

This is a repository copy of Assessment of Alzheimer-related pathologies of dementia using machine learning feature selection. White Rose Research Online URL for this paper: [https://eprints.whiterose.ac.uk/197336/](https://eprints.whiterose.ac.uk/197336/) Version: Published Version Article: Rajab, M.D. , Jammeh, E. , Taketa, T. et al. (6 more authors) (2023) Assessment of Alzheimer-related pathologies of dementia using machine learning feature selection. Alzheimer's Research & Therapy, 15. 47. ISSN 1758-9193 [https://doi.org/10.1186/s13195-023-01195-9](https://doi.org/10.1186/s13195-023-01195-9) Reuse This article is distributed under the terms of the Creative Commons Attribution (CC BY) licence. This licence allows you to distribute, remix, tweak, and build upon the work, even commercially, as long as you credit the authors for the original work. More information and the full terms of the licence here: [https://creativecommons.org/licenses/](https://creativecommons.org/licenses/) Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk) including the URL of the record and the reason for the withdrawal request. [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk)[ ](eprints@whiterose.ac.uk)[https://eprints.whiterose.ac.uk/](https://eprints.whiterose.ac.uk/) Rajab etal. Alzheimer’s Research & Therapy (2023) 15:47 [https://doi.org/10.1186/s13195-023-01195-9](https://doi.org/10.1186/s13195-023-01195-9) Alzheimer’s Research & Therapy RESEARCH Open Access Assessment of Alzheimer-related pathologies of dementia using machine learning feature selection Mohammed D. Rajab 1,2, Emmanuel Jammeh 1, Teruka Taketa 1, Carol Brayne3, Fiona E. Matthews4, Li Su 1,5, Paul G. Ince 1, Stephen B. Wharton 1, Dennis Wang 1,2,6,7* and on behalf of the Cognitive Function and Ageing Neuropathology Study Group Abstract Although a variety of brain lesions may contribute to the pathological assessment of dementia, the relationship of these lesions to dementia, how they interact and how to quantify them remains uncertain. Systematically assessing neuropathological measures by their degree of association with dementia may lead to better diagnostic systems and treatment targets. This study aims to apply machine learning approaches to feature selection in order to identify critical features of Alzheimer-related pathologies associated with dementia. We applied machine learning techniques for feature ranking and classi cation to objectively compare neuropathological features and their relationship to dementia status during life using a cohort (n 186) from the Cognitive Function and Ageing Study (CFAS) . We rst tested Alzheimer’s Disease and tau markers and then other neuropathologies associated with dementia. Seven feature ranking methods using di􀀞erent information criteria consistently ranked 22 out of the 34 neuropathology features for importance to dementia classi cation. Although highly correlated, Braak neuro brillary tangle stage, beta-amyloid and cerebral amyloid angiopathy features were ranked the highest. The best-performing dementia classi er using the top eight neuropathological features achieved 79% sensitivity, 69% speci city and 75% precision. However, when assessing all seven classi ers and the 22 ranked features, a substantial proportion (40 .4%) of dementia cases was consistently misclassi ed. These results highlight the bene ts of using machine learning to identify critical indices of plaque, tangle and cerebral amyloid angiopathy burdens that may be useful for classifying dementia. Keywords Dementia, Alzheimer’s, Feature selection, Machine learning, Neuropathology, Beta-amyloid *Correspondence: Dennis Wang [dennis.wang@imperial.ac.uk](dennis.wang@imperial.ac.uk) 1 She􀀝eld Institute for Translational Neuroscience, University of She􀀝eld, She􀀝eld S10 2HQ, UK 2 Department of Computer Scienc

FAQs

What problem does the study address about dementia neuropathology?

The study addresses uncertainty about how different brain lesions relate to dementia, how they interact, and how to quantify them for diagnostic purposes.

How did the researchers use machine learning in this work?

They applied machine learning for feature ranking and classification to compare neuropathological features and their association with dementia status during life.

Which features ranked highest for dementia classification?

Despite strong correlations, Braak neurofibrillary tangle stage, beta-amyloid, and cerebral amyloid angiopathy features were consistently ranked highest.

Aug 3, 2026

Upload by Logic