Expert Systems Using Fuzzy Logic for the Early Alzheimer’s Disease Diagnosis
Wasit Journal of Computer and Mathematics Science · 30.06.2026 · 5 (2) · 27-43
DOI: 10.31185/wjcms.517 ↗Kurz gefasst
Fachartikel in der Zeitschrift Wasit Journal of Computer and Mathematics Science, online erschienen am 30.06.2026. Verfasst von Mohammed Mahdi Hashim und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Demenz
Abstract (Originalsprache)
Alzheimer’s disease continues to be an important international health concern and early, accurate diagnosis is essential for treatment initiation and management of the disease. However, early identification of Alzheimer ’s disease (AD) remains a formidable challenge, mainly attributed to the complex underlying pathology and clinical heterogeneity along with conventional neuroimaging and cognitive tests possessing limited accuracy when applied individually. In this work, we aim to improve the sensitivity and specificity of detection for early-stage AD by developing a hybrid method based on MRI neuroimaging features woven with data from cognitive assessments through using a fuzzy-based expert system combined with machine-learning techniques. Cognitive data were collected from 60 subjects using a structured questionnaire covering multiple cognitive domains and MR-derived structural features, representative of neurodegeneration patterns. In particular, a fuzzy inference system was used to model the uncertainty and to represent nonlinear relationships frequently seen in medical data, then its output data were analyzed by a supervised classifier. Various cross-validation methods were used to validate the performance of the proposed model and an overall accuracy 91.9%, predictive accuracy 92.5%, sensitivity 91.1%F1-score ~91.5% and Area Under the Curve (AUC) AUC = 0.94 with our results defined a high discriminative effect size large to very large supported by Lakehead Bayesian Test. In addition, prodigious find the pressure of statistical significance testing and confidence interval checking implied composites that were references to fortune. . In conclusion, our results indicate that the development of fuzzy expert-based hybrid models merging neuroimaging and cognitive data has great potential for state-of-the-art early accurate classification of individuals with Alzheimer’s disease, thus providing a new promising reliable screening tool useful for clinical decision-making.
Zitieren
APA
Hashim, M. M., Nahi, A. A., Ali, A. K., & Ciobanu, V. (2026). Expert Systems Using Fuzzy Logic for the Early Alzheimer’s Disease Diagnosis. Wasit Journal of Computer and Mathematics Science, 5(2), 27-43. https://doi.org/10.31185/wjcms.517
Vancouver
Hashim MM, Nahi AA, Ali AK, Ciobanu V. Expert Systems Using Fuzzy Logic for the Early Alzheimer’s Disease Diagnosis. Wasit Journal of Computer and Mathematics Science. 2026;5(2):27-43. doi:10.31185/wjcms.517
BibTeX
@article{Hashim2026,
author = {Hashim, Mohammed Mahdi and Nahi, Abdullah A. and Ali, Amna Kadhim and Ciobanu, Vlad},
title = {Expert Systems Using Fuzzy Logic for the Early Alzheimer’s Disease Diagnosis},
journal = {Wasit Journal of Computer and Mathematics Science},
year = {2026},
volume = {5},
number = {2},
pages = {27--43},
doi = {10.31185/wjcms.517}
}
EUVIMED