Multivariable Diagnostic Models for Differentiating Alzheimer’s Disease, Vascular Dementia, and Mixed Dementia: A Systematic Review
Journal of Clinical Medicine · 15.11.2026 · 15 (22) · 8942
DOI: 10.3390/jcm15228942 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Journal of Clinical Medicine, online erschienen am 15.11.2026. Verfasst von Otari Okroadze und 8 weiteren Autor:innen. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Demenz
Abstract (Originalsprache)
Background/Objectives: Differentiating Alzheimer’s disease (AD), vascular dementia or vascular cognitive impairment (VaD/VCI), and mixed dementia remains challenging because their clinical and biological features overlap. This systematic review evaluated the diagnostic performance, methodological quality, and clinical applicability of multivariable models developed for this differential diagnosis.
Methods
The review was prospectively registered in International Prospective Register of Systematic Reviews (PROSPERO;CRD420261479586). Bibliographic sources were searched for publications from 1 January 2016 to 8 September 2026 without language restrictions. Supplementary registry searches were conducted during revision. Two reviewers independently conducted study selection and data extraction using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) framework. Model-development quality, evaluation risk of bias, and applicability were assessed using Prediction model Risk Of Bias ASsessment Tool for regression and artificial intelligence methods (PROBAST+AI). A structured synthesis without meta-analysis was performed.
Results
Searches identified 5316 records; 51 publications were included. Primary synthesis groups comprised 21 direct AD–VaD/VCI-related comparisons, three classifications involving mixed dementia or AD with cerebrovascular disease, 14 multiclass, one-versus-rest, or multilabel frameworks, and 13 qualitative-only publications. Eighteen publications reported exact areas under the receiver operating characteristic curve (AUCs) for AD–VaD/VCI-related comparisons, ranging from 0.51 to 0.97 across model configurations and evaluation settings. Four publications (7.8%) reported independent external validation across different diagnostic tasks, not four validations of direct AD–VaD classifiers. No applicable development assessment was rated low concern, and no evaluation assessment was rated low risk of bias.
Conclusions
Reported performance supports further investigation, but routine clinical utility has not been established. Clear target definitions, fixed-model external validation, and clinical impact studies are needed, particularly for mixed dementia.
Zitieren
APA
Okroadze, O., Yerkhojayeva, N., Mukasheva, A., Turtayeva, A., Abdraimova, S., Yurikova, O., Yelubayeva, A., Escott-Price, V., & Zharkinbekova, N. (2026). Multivariable Diagnostic Models for Differentiating Alzheimer’s Disease, Vascular Dementia, and Mixed Dementia: A Systematic Review. Journal of Clinical Medicine, 15(22), 8942. https://doi.org/10.3390/jcm15228942
Vancouver
Okroadze O, Yerkhojayeva N, Mukasheva A, Turtayeva A, Abdraimova S, Yurikova O, et al. Multivariable Diagnostic Models for Differentiating Alzheimer’s Disease, Vascular Dementia, and Mixed Dementia: A Systematic Review. Journal of Clinical Medicine. 2026;15(22):8942. doi:10.3390/jcm15228942
BibTeX
@article{Okroadze2026,
author = {Okroadze, Otari and Yerkhojayeva, Nigara and Mukasheva, Aziza and Turtayeva, Aigul and Abdraimova, Saltanat and Yurikova, Oxana and Yelubayeva, Altynay and Escott-Price, Valentina and Zharkinbekova, Nazira},
title = {Multivariable Diagnostic Models for Differentiating Alzheimer’s Disease, Vascular Dementia, and Mixed Dementia: A Systematic Review},
journal = {Journal of Clinical Medicine},
year = {2026},
volume = {15},
number = {22},
pages = {8942},
doi = {10.3390/jcm15228942}
}
EUVIMED