Universität zu Köln

Lohner, Valerie ORCID: 0000-0001-5589-9701, Badhwar, Amanpreet ORCID: 0000-0003-3414-3395, Detcheverry, Flavie E. ORCID: 0000-0002-9909-9754, García, Cindy L., Gellersen, Helena M. ORCID: 0000-0001-7544-2311, Khodakarami, Zahra, Lattmann, René ORCID: 0009-0005-1620-2007, Li, Rui, Low, Audrey ORCID: 0000-0002-9960-9849, Mazo, Claudia ORCID: 0000-0003-1703-8964, Metz, Amelie ORCID: 0000-0001-9104-5383, Parent, Olivier ORCID: 0000-0002-3177-0353, Phillips, Veronica ORCID: 0000-0002-4383-9434, Saeed, Usman, Tan, Sean Y. W., Tamburin, Stefano ORCID: 0000-0002-1561-2187, Llewellyn, David J., Rittman, Timothy ORCID: 0000-0003-1063-6937, Waters, Sheena ORCID: 0000-0001-7241-2272 and Bernal, Jose ORCID: 0000-0003-3167-5134 (2025). Machine learning applications in vascular neuroimaging for the diagnosis and prognosis of cognitive impairment and dementia: a systematic review and meta-analysis. Alzheimer's Research & Therapy, 17 (1). Springer Nature. ISSN 1758-9193

PDF s13195-025-01815-6.pdf Bereitstellung unter der CC-Lizenz: Creative Commons Attribution. Download (4MB)

Abstract

[Artikel-Nr.: 183] 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 generalisability of their models on external datasets, and six lacked clear diagnostic criteria. Conclusions Interest in incorporating CSVD markers into ML models for neurodegenerative disease classification is on the rise, and their performance suggests that this is worth further exploration. Serious methodological issues, including inconsistent reporting, limited generalisability testing, and other potential biases, are unfortunately common and hinder further adoption. Our targeted recommendations provide a roadmap to accelerate the integration of ML into clinical practice.

Item Type:	Article
Creators:	Creators Email ORCID ORCID Put Code Lohner, Valerie UNSPECIFIED https://orcid.org/0000-0001-5589-9701 UNSPECIFIED Badhwar, Amanpreet UNSPECIFIED https://orcid.org/0000-0003-3414-3395 UNSPECIFIED Detcheverry, Flavie E. UNSPECIFIED https://orcid.org/0000-0002-9909-9754 UNSPECIFIED García, Cindy L. UNSPECIFIED UNSPECIFIED UNSPECIFIED Gellersen, Helena M. UNSPECIFIED https://orcid.org/0000-0001-7544-2311 UNSPECIFIED Khodakarami, Zahra UNSPECIFIED UNSPECIFIED UNSPECIFIED Lattmann, René UNSPECIFIED https://orcid.org/0009-0005-1620-2007 UNSPECIFIED Li, Rui UNSPECIFIED UNSPECIFIED UNSPECIFIED Low, Audrey UNSPECIFIED https://orcid.org/0000-0002-9960-9849 UNSPECIFIED Mazo, Claudia UNSPECIFIED https://orcid.org/0000-0003-1703-8964 UNSPECIFIED Metz, Amelie UNSPECIFIED https://orcid.org/0000-0001-9104-5383 UNSPECIFIED Parent, Olivier UNSPECIFIED https://orcid.org/0000-0002-3177-0353 UNSPECIFIED Phillips, Veronica UNSPECIFIED https://orcid.org/0000-0002-4383-9434 UNSPECIFIED Saeed, Usman UNSPECIFIED UNSPECIFIED UNSPECIFIED Tan, Sean Y. W. UNSPECIFIED UNSPECIFIED UNSPECIFIED Tamburin, Stefano UNSPECIFIED https://orcid.org/0000-0002-1561-2187 UNSPECIFIED Llewellyn, David J. UNSPECIFIED UNSPECIFIED UNSPECIFIED Rittman, Timothy UNSPECIFIED https://orcid.org/0000-0003-1063-6937 UNSPECIFIED Waters, Sheena UNSPECIFIED https://orcid.org/0000-0001-7241-2272 UNSPECIFIED Bernal, Jose UNSPECIFIED https://orcid.org/0000-0003-3167-5134 UNSPECIFIED
URN:	urn:nbn:de:hbz:38-800999
Identification Number:	10.1186/s13195-025-01815-6
Journal or Publication Title:	Alzheimer's Research & Therapy
Volume:	17
Number:	1
Number of Pages:	19
Date:	7 August 2025
Publisher:	Springer Nature
ISSN:	1758-9193
Language:	English
Faculty:	Faculty of Medicine
Divisions:	Faculty of Medicine > Innere Medizin > Klinik III für Innere Medizin - Kardiologie, Pneumologie, Angiologie und internistische Intensivmedizin
Subjects:	Medical sciences Medicine
Uncontrolled Keywords:	Keywords Language Machine learning ; Dementia ; Cerebral small vessel disease ; Artificial intelligence ; Neuroimaging ; Cognitive impairment ; Alzheimer’s dementia ; Neurodegenerative diseases English
['eprint_fieldname_oa_funders' not defined]:	Publikationsfonds UzK
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/80099