Network analysis of optimal deep or machine learning strategies for classification and detection of Alzheimer’s disease based on MRI scanning

Aug 4, 2026

Upload by Aurelia

Systematic review evaluating how deep learning and machine learning models perform for classifying and detecting Alzheimer’s disease using MRI data. Background highlights rising prevalence projected toward 2050 and incomplete understanding of disease mechanisms and heterogeneity. Methods follow Cochrane-style systematic review protocols and PRISMA, with database searches and network meta-analysis plus machine-learning–driven synthesis. Results synthesize 11 eligible studies, comparing CNN, ResNet, DenseNet and related approaches. Findings indicate CNN and ResNet achieve higher classification accuracy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Background and challenges

Role of MRI and computational methods

Methods

Systematic review protocol and search strategy

Data synthesis and network meta-analysis

Results

Included studies and diagnostic models

Comparative performance of CNN and ResNet

Conclusion

Future research directions and limitations

TYPE Systematic Review PUBLISHED 30 January 2026 DOI 10.3389/fnins.2026.1644480 OPEN ACCESS EDITED BY Shiyan Yan, Beijing University of Chinese Medicine, China REVIEWED BY Milan Simic, RMIT University, Australia Varsha Nandwana, Carilion Clinic, United States *CORRESPONDENCE Jie Zhou [zhoujie518618@163.com](zhoujie518618@163.com) †These authors have contributed equally to this work RECEIVED 10 June 2025 REVISED 06 January 2026 ACCEPTED 12 January 2026 PUBLISHED 30 January 2026 CITATION Zhang Q, Ma L, Zhao L, Zhu S, Qi H, Pan Z and Zhou J (2026) Network analysis of optimal deep or machine learning strategies for classification and detection of Alzheimer’s disease based on MRI scanning. Front. Neurosci. 20:1644480 . doi: 10.3389/fnins.2026.1644480 COPYRIGHT © 2026 Zhang, Ma, Zhao, Zhu, Qi, Pan and Zhou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Network analysis of optimal deep or machine learning strategies for classification and detection of Alzheimer’s disease based on MRI scanning Qinyu Zhang 1†, Luping Ma 2†, Lulei Zhao3, Shaofeng Zhu 1, Hongyang Qi 1, Zhenzhen Pan 1 and Jie Zhou 1* 1Department of Radiology, Shaoxing Seventh People’s Hospital, Shaoxing, Zejiang, China, 2Department of Radiology, Affiliated Hospital of Shaoxing University, Shaoxing, Zejiang, China, 3Department of Radiology, Ningbo Yinzhou District Second Hospital, Ningbo, Zejiang, China Background: Alzheimer’s disease (AD) presents a significant global health challenge, with its prevalence projected to increase substantially by 2050. Despite its widespread impact, the underlying causes and mechanisms remain incompletely understood, complicating efforts toward effective diagnosis and treatment. Pathologically, AD is marked by the accumulation of senile plaquesand neurofibrillary tangles, but the relationship between these factors and disease progression is complex and heterogeneous. Objective: The present study aimed to compare the efficacy of different deep/ machine learning models based on MRI scanning. Methods: The study follows rigorous systematic review protocols, adhering to the Cochrane Handbook of Systematic Reviews and Interventions and the PRISMA guidelines. A comprehensive search strategy was employed across multiple databases, including PubMed, Web of Science, Cochrane, Medline, and EMBASE. Advanced statistical methods were used for data synthesis and analysis, incorporating network meta-analysis and machine learning techniques to evaluate the accuracy and efficacy of different diagnostic models. Results: The meta-analysis included 11 studies that met the predefined inclusion criteria. The studies employed various machine learning algorithms, including CNN, ResNet, and DenseNet, to classify AD and distinguish it from mild cognitive impairment (MCI) and healthy controls. The results indicate that CNN and ResNet consistently outperform other models in terms of classification accuracy. Additionally, the integration of nanotechnology and AI-driven diagnostics demonstrates significant potential in enhancing the diagnostic process. Conclusion: Despite challenges such as data heterogeneity and the interpretability of AI-driven models, the study highlights the transformative potential of computational techniques and advanced imaging technologies in AD diagnosis and management. The integration of network-based analyses and machine learning approaches offers promising avenues for future research, aiming to revolutionize the understanding and approach to Alzheimer’s disease. KEYWORDS Alzheimer’

FAQs

What is the main objective of the study?

To compare the effectiveness of different deep learning and machine learning models for classifying and detecting Alzheimer’s disease based on MRI scanning.

How was the systematic review conducted?

The review followed systematic review protocols aligned with the Cochrane Handbook and PRISMA, using comprehensive searches across PubMed, Web of Science, Cochrane, Medline, and EMBASE.

Which models showed the best classification performance?

CNN and ResNet consistently outperformed other models in terms of classification accuracy for distinguishing Alzheimer’s disease from mild cognitive impairment and healthy controls.

Aug 4, 2026

Upload by Aurelia