Machine learning applications in vascular neuroimaging for the diagnosis and prognosis of cognitive impairment and dementia - a systematic review and meta-analysis

Aug 5, 2026

Upload by Aurelia

Cerebral small vessel disease (CSVD) drives stroke, dementia, disability, and mortality worldwide, motivating accurate prediction of cognitive impairment and dementia. A systematic review and meta-analysis evaluated how neuroimaging CSVD markers support machine learning (ML) for diagnosis and prognosis, and assessed methodological evolution and barriers to clinical translation. Searches followed PRISMA and used PRoSPERO preregistration; ML performance was aggregated with area under the curve (AUC).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusions

Introduction

CSVD and its clinical impact

CSVD and Alzheimer’s disease

Lohner etal. Alzheimer's Research & Therapy (2025) 17:183 [https://doi.org/10.1186/s13195-025-01815-6](https://doi.org/10.1186/s13195-025-01815-6) Alzheimer's Research & Therapy RESEARCH Open Access Machine learning applications in vascular neuroimaging for the diagnosis and prognosis of cognitive impairment and dementia: a systematic review and meta-analysis Valerie Lohner 1*, Amanpreet Badhwar2,3,4,5, Fl avie E. Detcheverry2,3,4,5, Cindy L. García6,7, Helena M. Gellersen8,9,10, Zahra Khodakarami 11,12, René Lattmann8,13, Rui Li 14, Audrey Low 15, Claudia Mazo 16, Amelie Metz6,7, Olivier Parent6,7, Veronica Phillips 17, Usman Saeed 18,19, SeanY. W. Tan 14, Stefano Tamburin20, David J. Llewellyn21, Timothy Rittman 14, Sheena Waters22 and Jose Bernal8,13,23 Abstract Background Cerebral small vessel disease (CSVD) is a common neurological condition that contributes to strokes, dementia, disability, and mortality worldwide. We conducted a systematic review and meta-analysis to investigate the use of neuroimaging CSVD markers in machine learning (ML) based diagnosis and prognosis of cognitive impairment and dementia, and identify both methodological changes over time and barriers to clinical translation. Methods Following the PRISMA guidelines, we systematically searched for original studies that used both neuroimaging CSVD markers and ML methods for diagnosing and prognosing neurodegenerative diseases (preregistration in PROSPERO: CRD42022366767) . Each paper was independently reviewed by a pair of reviewers at all stages, with a third consulted to resolve conflicts. We meta-analysed the effectiveness of ML models to distinguish healthy controls from Alzheimer’s dementia and cognitive impairment, using area under the curve (AUC) as the performance metric. Results We identified 75 studies: 43 on diagnosis, 27 on prognosis, and 5 on both. Nearly 60% of studies were published in the past two years, reflecting a growing interest in using CSVD markers in ML-based diagnosis and prognosis of neurodegenerative diseases, especially Alzheimer’s dementia. This rising interest may be linked to the strong performance of such models: according to our meta-analysis, ML approaches using CSVD markers perform well in differentiating healthy controls from Alzheimer’s dementia (AUC 0.88 [95%-CI 0.85–0. 92]) and cognitive impairment (AUC 0.84 [95%-CI 0.74–0. 95]) . However, the growing interest has not been matched by methodological rigour: only 16 studies met the criteria for inclusion in the meta-analysis due to inconsistent reporting, only five assessed the general isability of their model s on external datasets, and six lacked clear diagnostic criteria. *Correspondence: Valerie Lohner [valerie.lohner@uk-koel n.de](valerie.lohner@uk-koel n.de) Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/l](http://creativecommons.org/l)icenses/by/4.0/. Lohner et al. Alzheimer's Research & Therapy (2025) 17:183 Page 2 of 19 Conclusions Interest in incorporating CSVD markers into ML models for neurodegenerative disease classification is on the rise, and their performan

FAQs

What question does the systematic review address?

The review evaluates how neuroimaging CSVD markers combined with machine learning are used for diagnosing and prognosing cognitive impairment and dementia, and what methodological barriers slow clinical adoption.

How were studies selected and assessed?

Following PRISMA guidelines, the review searched original studies using both CSVD neuroimaging markers and machine learning, with independent screening by paired reviewers and a third reviewer for conflicts.

What do the meta-analysis results suggest about ML performance and study quality?

ML approaches using CSVD markers performed well in separating healthy controls from Alzheimer’s dementia and from cognitive impairment based on AUC metrics. However, methodological rigor was limited, with many studies excluded due to inconsistent reporting and few evaluating external generalizability.

Aug 5, 2026

Upload by Aurelia