{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T19:37:49Z","timestamp":1770406669624,"version":"3.49.0"},"reference-count":49,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>This study evaluates the performance of a deep learning framework supported by a cross-replication strategy for predicting Alzheimer\u2019s disease (AD) from structural magnetic resonance imaging (MRI). EfficientNetV2-B0 was selected due to its favorable accuracy-efficiency trade-off. The workflow consisted of two stages: (i) clustering-based relabeling of the full dataset into five clinically meaningful categories, and (ii) training a classifier on the relabeled data. To assess the stability of the proposed approach, the model was trained across multiple random initializations on a fixed train\/validation\/test split. Class-wise Average Precision, macro- and micro-averaged Precision-Recall Area Under the Curve (PR\u2013AUC) and Receiver Operating Characteristic Area Under the Curve (ROC\u2013AUC), and their 95% confidence intervals were reported using bootstrap resampling. The cross-replication strategy yielded improved stability across initializations, with a mean test accuracy of 0.95 compared with 0.94 for the single-run baseline, along with consistently higher PR\u2013AUC and ROC\u2013AUC values. These findings suggest that cross-replication enhances the reliability of AD stage prediction by reducing performance variability due to stochastic initialization, although further evaluation with alternative data partitions or external validation cohorts is warranted.<\/jats:p>","DOI":"10.7717\/peerj-cs.3580","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T08:42:40Z","timestamp":1770367360000},"page":"e3580","source":"Crossref","is-referenced-by-count":0,"title":["Measuring the prediction performance of Alzheimer\u2019s disease using MR images with a deep learning model supported by a cross-replication strategy"],"prefix":"10.7717","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6482-4592","authenticated-orcid":true,"given":"Mustafa","family":"Cosar","sequence":"first","affiliation":[]}],"member":"4443","published-online":{"date-parts":[[2026,2,6]]},"reference":[{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-1","doi-asserted-by":"publisher","first-page":"8198552","DOI":"10.1155\/2021\/8198552","article-title":"Artificial intelligence-based MRI Images for brain in prediction of Alzheimer\u2019s disease","volume":"2021","author":"Bi","year":"2021","journal-title":"Journal of Healthcare Engineering"},{"issue":"2","key":"10.7717\/peerj-cs.3580\/ref-2","doi-asserted-by":"publisher","first-page":"102585","DOI":"10.1016\/j.media.2022.102585","article-title":"Reducing variations in multi-center Alzheimer\u2019s disease classification with convolutional adversarial autoencoder","volume":"82","author":"Cobbinah","year":"2022","journal-title":"Medical Image Analysis"},{"issue":"Suppl. 1","key":"10.7717\/peerj-cs.3580\/ref-3","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.jpsychires.2016.03.010","article-title":"Multimodal EEG-MRI in the differential diagnosis of Alzheimer\u2019s disease and dementia with Lewy bodies","volume":"78","author":"Colloby","year":"2016","journal-title":"Journal of Psychiatric Research"},{"key":"10.7717\/peerj-cs.3580\/ref-4","volume-title":"Artificial intelligence illuminated","author":"Coppin","year":"2004"},{"issue":"4","key":"10.7717\/peerj-cs.3580\/ref-5","doi-asserted-by":"publisher","first-page":"103455","DOI":"10.1016\/j.bspc.2021.103455","article-title":"Optimization of VGG16 utilizing the arithmetic optimization algorithm for early detection of Alzheimer\u2019s disease","volume":"74","author":"Deepa","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"issue":"2","key":"10.7717\/peerj-cs.3580\/ref-6","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.32604\/csse.2023.032231","article-title":"EfficientNetV2\u00a0Model for plant disease classification and pest recognition","volume":"45","author":"Devi","year":"2023","journal-title":"Computer Systems Science and Engineering"},{"key":"10.7717\/peerj-cs.3580\/ref-7","doi-asserted-by":"publisher","first-page":"105254","DOI":"10.1016\/j.bspc.2023.105254","article-title":"SUVR quantification using attention-based 3D CNN with longitudinal Florbetapir PET images in Alzheimer\u2019s disease","volume":"86","author":"Divya","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"issue":"3","key":"10.7717\/peerj-cs.3580\/ref-8","doi-asserted-by":"publisher","first-page":"104537","DOI":"10.1016\/j.compbiomed.2021.104537","article-title":"Deep sequence modelling for Alzheimer\u2019s disease detection using MRI","volume":"134","author":"Ebrahimi","year":"2021","journal-title":"Computers in Biology and Medicine"},{"issue":"11","key":"10.7717\/peerj-cs.3580\/ref-9","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1038\/s41583-018-0071-7","article-title":"Imaging-based parcellations of the human brain","volume":"19","author":"Eickhoff","year":"2018","journal-title":"Nature Reviews Neuroscience"},{"issue":"8","key":"10.7717\/peerj-cs.3580\/ref-10","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.3390\/diagnostics11081473","article-title":"Artificial intelligence for Alzheimer\u2019s disease: promise or challenge?","volume":"11","author":"Fabrizio","year":"2021","journal-title":"Diagnostics"},{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-11","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.clinph.2020.09.015","article-title":"Stacked autoencoders as new models for an accurate Alzheimer\u2019s disease classification support using resting-state EEG and MRI measurements","volume":"132","author":"Ferri","year":"2021","journal-title":"Clinical Neurophysiology"},{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-12","doi-asserted-by":"publisher","first-page":"012020","DOI":"10.1088\/1742-6596\/1844\/1\/012020","article-title":"Automated classification of Alzheimer\u2019s disease based on MRI image processing using convolutional neural network (CNN) with AlexNet architecture","volume":"1844","author":"Fuadah","year":"2020","journal-title":"Journal of physics: conference series"},{"issue":"3","key":"10.7717\/peerj-cs.3580\/ref-13","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1002\/hbm.26126","article-title":"An artificial-intelligence-based age-specific template construction framework for brain structural analysis using magnetic resonance images","volume":"44","author":"Gu","year":"2023","journal-title":"Human Brain Mapping"},{"key":"10.7717\/peerj-cs.3580\/ref-14","doi-asserted-by":"publisher","first-page":"101625","DOI":"10.1016\/j.media.2019.101625","article-title":"Multi-modal neuroimaging feature selection with consistent metric constraint for diagnosis of Alzheimer\u2019s disease","volume":"60","author":"Hao","year":"2020","journal-title":"Medical Image Analysis"},{"issue":"2","key":"10.7717\/peerj-cs.3580\/ref-15","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1016\/j.neuroimage.2010.10.081","article-title":"Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population","volume":"55","author":"Hinrichs","year":"2011","journal-title":"Neuroimage"},{"issue":"2","key":"10.7717\/peerj-cs.3580\/ref-16","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.cogsys.2018.12.015","article-title":"Convolutional neural network based Alzheimer\u2019s disease classification from magnetic resonance brain images","volume":"57","author":"Jain","year":"2019","journal-title":"Cognitive Systems Research"},{"issue":"4","key":"10.7717\/peerj-cs.3580\/ref-17","doi-asserted-by":"publisher","first-page":"106404","DOI":"10.1016\/j.bspc.2024.106404","article-title":"Multi-modal global-and local-feature interaction with attention-based mechanism for diagnosis of Alzheimer\u2019s disease","volume":"95","author":"Jia","year":"2024","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.7717\/peerj-cs.3580\/ref-18","doi-asserted-by":"publisher","first-page":"104678","DOI":"10.1016\/j.compbiomed.2021.104678","article-title":"Multi-model and multi-slice ensemble learning architecture based on 2d convolutional neural networks for Alzheimer\u2019s disease diagnosis","volume":"136","author":"Kang","year":"2021","journal-title":"Computers in Biology and Medicine"},{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-19","doi-asserted-by":"publisher","first-page":"102928","DOI":"10.1016\/j.artmed.2024.102928","article-title":"A systematic literature review on the significance of deep learning and machine learning in predicting Alzheimer\u2019s disease","volume":"154","author":"Kaur","year":"2024","journal-title":"Artificial Intelligence Medicine"},{"issue":"2","key":"10.7717\/peerj-cs.3580\/ref-20","doi-asserted-by":"publisher","first-page":"104400","DOI":"10.1016\/j.bspc.2022.104400","article-title":"Patch-based deep multi-modal learning framework for Alzheimer\u2019s disease diagnosis using multi-view neuroimaging","volume":"80","author":"Liu","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-21","doi-asserted-by":"publisher","first-page":"001","DOI":"10.36548\/jscp.2021.4.007","article-title":"Automatic diagnosis of Alzheimer\u2019s disease using hybrid model and CNN","volume":"3","author":"Nagarathna","year":"2022","journal-title":"International Journal of Innovative Research in Science Engineering and Technology"},{"issue":"12","key":"10.7717\/peerj-cs.3580\/ref-22","doi-asserted-by":"publisher","first-page":"5952","DOI":"10.1002\/alz.13463","article-title":"Artificial intelligence for dementia prevention","volume":"12","author":"Newby","year":"2023","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"10.7717\/peerj-cs.3580\/ref-23","doi-asserted-by":"crossref","DOI":"10.1145\/1102351.1102430","article-title":"Predicting good probabilities with supervised learning","author":"Niculescu-Mizil","year":"2005"},{"issue":"15","key":"10.7717\/peerj-cs.3580\/ref-24","doi-asserted-by":"publisher","first-page":"e34402","DOI":"10.1016\/j.heliyon.2024.e34402","article-title":"Alzheimer\u2019s disease stage recognition from MRI and PET imaging data using Pareto-optimal quantum dynamic optimization","volume":"10","author":"Odusami","year":"2024","journal-title":"Heliyon"},{"key":"10.7717\/peerj-cs.3580\/ref-25","doi-asserted-by":"publisher","first-page":"102776","DOI":"10.1016\/j.sbi.2024.102776","article-title":"Artificial intelligence for drug discovery and development in Alzheimer\u2019s disease","volume":"85","author":"Qiu","year":"2024","journal-title":"Current Opinion in Structural Biology"},{"issue":"2","key":"10.7717\/peerj-cs.3580\/ref-26","doi-asserted-by":"publisher","first-page":"447","DOI":"10.36548\/jiip.2025.2.009","article-title":"Attention enhanced CNN with LSTM model for early detection of Alzheimer\u2019s disease using longitudinal data","volume":"7","author":"Rajeswari","year":"2025","journal-title":"Journal of Innovative Image Processing"},{"issue":"8","key":"10.7717\/peerj-cs.3580\/ref-27","doi-asserted-by":"publisher","first-page":"104312","DOI":"10.1016\/j.bspc.2022.104312","article-title":"Deep learning-based classification of healthy aging controls, mild cognitive impairment and Alzheimer\u2019s disease using fusion of MRI-PET imaging","volume":"80","author":"Rallabandi","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"issue":"14","key":"10.7717\/peerj-cs.3580\/ref-28","doi-asserted-by":"publisher","first-page":"3959","DOI":"10.1049\/ipr2.12910","article-title":"A robust and clinically applicable deep learning model for early detection of Alzheimer\u2019s","volume":"17","author":"Rana","year":"2023","journal-title":"IET Image Processing"},{"key":"10.7717\/peerj-cs.3580\/ref-29","article-title":"Do ImageNet classifihers generalize to ImageNet?","author":"Recht","year":"2019"},{"key":"10.7717\/peerj-cs.3580\/ref-30","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"Journal of Computational and Applied Mathematics"},{"key":"10.7717\/peerj-cs.3580\/ref-31","doi-asserted-by":"publisher","DOI":"10.34740\/KAGGLE\/DSV\/3364939","article-title":"Alzheimer MRI preprocessed dataset [data set]","author":"Sachin","year":"2022"},{"issue":"8","key":"10.7717\/peerj-cs.3580\/ref-32","doi-asserted-by":"publisher","first-page":"950","DOI":"10.3390\/bioengineering10080950","article-title":"An approach to binary classification of Alzheimer\u2019s disease using LSTM","volume":"10","author":"Salehi","year":"2023","journal-title":"Bioengineering"},{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-33","doi-asserted-by":"publisher","first-page":"16376","DOI":"10.1109\/ACCESS.2023.3244952","article-title":"AlzheimerNet: an effective deep learning based proposition for Alzheimer\u2019s disease stages classification from functional brain changes in magnetic resonance images","volume":"11","author":"Shamrat","year":"2023","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-34","doi-asserted-by":"publisher","first-page":"103217","DOI":"10.1016\/j.bspc.2021.103217","article-title":"Alzheimers disease classification using pre-trained deep networks","volume":"71","author":"Shanmugam","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.7717\/peerj-cs.3580\/ref-35","doi-asserted-by":"publisher","first-page":"1000435","DOI":"10.3389\/fncom.2022.1000435","article-title":"Transfer learning-based modified inception model for the diagnosis of Alzheimer\u2019s disease","volume":"16","author":"Sharma","year":"2022","journal-title":"Frontiers in Computational Neuroscience"},{"key":"10.7717\/peerj-cs.3580\/ref-36","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1109\/ICSCDS53736.2022.9760858","article-title":"Alzheimer\u2019s disease analysis using Explainable Artificial Intelligence (XAI)","author":"Sudar","year":"2022"},{"key":"10.7717\/peerj-cs.3580\/ref-37","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.7717\/peerj-cs.3580\/ref-38","article-title":"EfficientNetV2: smaller models and faster training","author":"Tan","year":"2021"},{"key":"10.7717\/peerj-cs.3580\/ref-39","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1109\/EMBC.2018.8512372","article-title":"A novel multimodal MRI analysis for Alzheimer\u2019s disease based on convolutional neural network","author":"Wang","year":"2018"},{"issue":"1","key":"10.7717\/peerj-cs.3580\/ref-40","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1111\/jon.13063","article-title":"Functional magnetic resonance imaging, deep learning, and Alzheimer\u2019s disease: a systematic review","volume":"33","author":"Warren","year":"2022","journal-title":"Journal of Neuroimaging"},{"key":"10.7717\/peerj-cs.3580\/ref-41","doi-asserted-by":"publisher","first-page":"ArXiv","DOI":"10.48550\/arXiv.2106.07393","article-title":"Cross-replication reliability\u2014an empirical approach to interpreting inter-rater reliability","author":"Wong","year":"2021"},{"key":"10.7717\/peerj-cs.3580\/ref-42","doi-asserted-by":"crossref","first-page":"30849","DOI":"10.34172\/bi.30849","article-title":"A hybrid transformer-based approach for early detection of Alzheimer\u2019s disease using MRI images","volume":"15","author":"Wu","year":"2025","journal-title":"Bioimpacts"},{"issue":"3","key":"10.7717\/peerj-cs.3580\/ref-43","doi-asserted-by":"publisher","first-page":"102362","DOI":"10.1016\/j.bspc.2020.102362","article-title":"Early diagnosis model of Alzheimer\u2019s disease based on sparse logistic regression with the generalized elastic net","volume":"66","author":"Xiao","year":"2021","journal-title":"Biomedical Signal Processing and Control"},{"issue":"12","key":"10.7717\/peerj-cs.3580\/ref-44","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.3390\/molecules23123140","article-title":"An efficient classifier for Alzheimer\u2019s disease genes identification","volume":"23","author":"Xu","year":"2018","journal-title":"Molecules"},{"issue":"6","key":"10.7717\/peerj-cs.3580\/ref-45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/jmri.29157","article-title":"Advances in neuroimaging and multiple post-processing techniques for epileptogenic zone detection of drug-resistant epilepsy","volume":"60","author":"Yao","year":"2023","journal-title":"Journal of Magnetic Resonance Imaging"},{"issue":"6","key":"10.7717\/peerj-cs.3580\/ref-46","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1016\/j.nicl.2013.05.004","article-title":"Accurate multimodal probabilistic prediction of conversion to Alzheimer\u2019s disease in patients with mild cognitive impairment","volume":"2","author":"Young","year":"2013","journal-title":"NeuroImage: Clinical"},{"issue":"3","key":"10.7717\/peerj-cs.3580\/ref-47","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.neuroscience.2022.03.026","article-title":"A single model deep learning approach for Alzheimer\u2019s disease diagnosis","volume":"491","author":"Zhang","year":"2022","journal-title":"Neuroscience"},{"issue":"3","key":"10.7717\/peerj-cs.3580\/ref-48","doi-asserted-by":"publisher","first-page":"e33182","DOI":"10.1371\/journal.pone.0033182","article-title":"Predicting future clinical changes of MCI patients using longitudinal and multimodal biomarkers","volume":"7","author":"Zhang","year":"2012","journal-title":"PLOS ONE"},{"issue":"10","key":"10.7717\/peerj-cs.3580\/ref-49","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.3390\/bioengineering10101120","article-title":"Application of deep learning for prediction of Alzheimer\u2019s disease in PET\/MR imaging","volume":"10","author":"Zhao","year":"2023","journal-title":"Bioengineering"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3580.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3580.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3580.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3580.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T08:42:47Z","timestamp":1770367367000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,6]]},"references-count":49,"alternative-id":["10.7717\/peerj-cs.3580"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3580","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,6]]},"article-number":"e3580"}}