{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:47:12Z","timestamp":1785646032818,"version":"3.56.0"},"reference-count":43,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000601","name":"De Montfort University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000601","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/0312pnr83","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Alzheimer\u2019s disease (AD) is a progressive neurodegenerative disorder necessitating accurate and timely diagnosis for effective clinical intervention. While deep learning methods have shown promise in AD classification, many rely on computationally intensive architectures and high-dimensional feature representations. This study introduces a lightweight hybrid framework combining deep feature extraction, dimensionality reduction, and adaptive classification for MRI-based Alzheimer\u2019s disease stage classification. Methods: Utilizing MRI images from a publicly available Alzheimer\u2019s disease dataset encompassing four clinical stages (Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented), deep features were extracted using a pre-trained SqueezeNet model as a fixed feature extractor, generating 1000-dimensional feature vectors. Due to the computational complexity and for the improvement of the model efficiency, the dimensionality reduction technique, Principal Component Analysis (PCA) was then applied. This resulted in an optimum representation of 100 principal components, retaining about 96% of the variance. Then, the performances of various machine learning classifiers such as k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Decision Tree (DT), Neural Network (NN), Na\u00efve Bayes (NB), Logistic Regression (LR) and Enhanced Fuzzy Min\u2013Max Neural Network (EFMM) were tested. The accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve (AUC), and confusion matrices were used to evaluate the performance. Stratified 5-fold cross validation was used to ensure the strength of our results. Results: The findings show that PCA has a significant improvement in classification accuracy for most of the models. In particular, the EFMM classifier outperformed the other classifiers, with an accuracy of 97.19% on the independent test set. After PCA, the AUC values for classes such as Mild Demented, Moderate Demented, Non-Demented and Very Mild Demented were obtained as 97.12%, 99.97%, 93.79% and 95.26% respectively. We further validated our proposed framework using stratified 5-fold cross validation which further corroborated the robustness of our proposed framework. The EFMM achieved a mean accuracy of 98.38% \u00b1 0.36 and a mean macro-F1 score of 98.48% \u00b1 0.43. Friedman statistical testing demonstrated that there were significant differences between the performance of the classifiers evaluated (p &lt; 0.001), which further validated the performance of the EFMM. Conclusions: To sum up, the proposed SqueezeNet\u2013PCA\u2013EFMM is an effective and efficient method for Alzheimer\u2019s disease stage classification under MRI images. The combination of SqueezeNet, PCA, and EFMM\u2014led not only to high classification performance, but also to good cross validation results. Furthermore, this property of incremental learning is the intrinsic one of the EFMM and renders this framework interesting for its incorporation in the next-generation intelligent clinical decision supports in particular, as medical care evolves.<\/jats:p>","DOI":"10.3390\/diagnostics16152428","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:02:01Z","timestamp":1785510121000},"page":"2428","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PCA-Enhanced Deep Features for Alzheimer\u2019s Disease Stage Classification with EFMM"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6551-7631","authenticated-orcid":false,"given":"Marwa Mawfaq Mohamedsheet","family":"Al-Hatab","sequence":"first","affiliation":[{"name":"Technical Engineering College, Northern Technical University, Mosul 41002, Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9672-5473","authenticated-orcid":false,"given":"Ruaa H. Ali","family":"Al-Mallah","sequence":"additional","affiliation":[{"name":"Technical Engineering College for Computer and Artificial Intelligence, Northern Technical University, Mosul 41002, Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maysaloon Abed","family":"Qasim","sequence":"additional","affiliation":[{"name":"Technical Engineering College for Computer and Artificial Intelligence, Northern Technical University, Mosul 41002, Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5155-7461","authenticated-orcid":false,"given":"Mohammed Falah","family":"Mohammed","sequence":"additional","affiliation":[{"name":"Mechatronics Engineering Department, College of Engineering, University of Mosul, Mosul 41002, Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6259-0622","authenticated-orcid":false,"given":"Taha H.","family":"Rassem","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, De Montfort University, Leicester LE1 9BH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9748-6067","authenticated-orcid":false,"given":"Abdulghani Ali","family":"Ahmed","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, King\u2019s College London, London WC2R 2LS, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1016\/j.arcmed.2012.11.003","article-title":"Epidemiology of dementias and Alzheimer\u2019s disease","volume":"43","author":"Prince","year":"2012","journal-title":"Arch. Med. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.jpsychires.2023.06.016","article-title":"The association between post-traumatic stress disorder (PTSD) and cognitive impairment: A systematic review of neuroimaging findings","volume":"164","author":"Sair","year":"2023","journal-title":"J. Psychiatr. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1111\/j.1467-9566.2012.01481.x","article-title":"Making sense of nonsense: Experiences of mild cognitive impairment","volume":"35","author":"Beard","year":"2013","journal-title":"Sociol. Health Illn."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2405","DOI":"10.1038\/s41598-022-06444-9","article-title":"Predictive classification of Alzheimer\u2019s disease using brain imaging and genetic data","volume":"12","author":"Sheng","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e1","DOI":"10.1111\/j.1468-1331.2006.01605.x","article-title":"Recommendations for the diagnosis and management of Alzheimer\u2019s disease and other disorders associated with dementia: EFNS guideline","volume":"14","author":"Waldemar","year":"2007","journal-title":"Eur. J. Neurol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mitchell, A.J. (2012). The Mini-Mental State Examination (MMSE): An update on its diagnostic validity for cognitive disorders. Cognitive Screening Instruments: A Practical Approach, Springer.","DOI":"10.1007\/978-1-4471-2452-8_2"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez Montenegro, J.M., Villarini, B., Angelopoulou, A., Kapetanios, E., Garcia-Rodriguez, J., and Argyriou, V. (2020). A survey of alzheimer\u2019s disease early diagnosis methods for cognitive assessment. Sensors, 20.","DOI":"10.3390\/s20247292"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"58503","DOI":"10.1109\/ACCESS.2021.3072559","article-title":"A survey on classification algorithms of brain images in Alzheimer\u2019s disease based on feature extraction techniques","volume":"9","author":"Hazarika","year":"2021","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"158820","DOI":"10.1109\/ACCESS.2019.2945545","article-title":"Comprehensive review of artificial neural network applications to pattern recognition","volume":"7","author":"Abiodun","year":"2019","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Abdolrasol, M.G., Hussain, S.S., Ustun, T.S., Sarker, M.R., Hannan, M.A., Mohamed, R., Ali, J.A., Mekhilef, S., and Milad, A. (2021). Artificial neural networks based optimization techniques: A review. Electronics, 10.","DOI":"10.3390\/electronics10212689"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gao, M., and Mao, J. (2021). A novel active rehabilitation model for stroke patients using electroencephalography signals and deep learning technology. Front. Neurosci., 15.","DOI":"10.3389\/fnins.2021.780147"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"46278","DOI":"10.1109\/ACCESS.2019.2902252","article-title":"Brain MRI image classification for cancer detection using deep wavelet autoencoder-based deep neural network","volume":"7","author":"Mallick","year":"2019","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Al Sayaydeh, O.N., and Mohammad, M.F. (2019, January 2\u20134). Diagnosis of the Parkinson disease using enhanced fuzzy min-max neural network and OneR attribute evaluation method. Proceedings of the 2019 International Conference on Advanced Science and Engineering (ICOASE), Zakho\u2013Duhok, Iraq.","DOI":"10.1109\/ICOASE.2019.8723870"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/TNNLS.2014.2315214","article-title":"An enhanced fuzzy min\u2013max neural network for pattern classification","volume":"26","author":"Mohammed","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"124030","DOI":"10.1016\/j.eswa.2024.124030","article-title":"A flexible enhanced fuzzy min-max neural network for pattern classification","volume":"251","author":"Alhroob","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"23735","DOI":"10.1007\/s11042-022-11925-0","article-title":"Early detection of Alzheimer\u2019s disease based on the state-of-the-art deep learning approach: A comprehensive survey","volume":"81","author":"Arafa","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_17","first-page":"6678837","article-title":"An artificial intelligence approach for verifying persons by employing the deoxyribonucleic acid (DNA) nucleotides","volume":"2023","author":"Qasim","year":"2023","journal-title":"J. Electr. Comput. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"172","DOI":"10.54216\/FPA.120214","article-title":"Clinical Fusion for Real-Time Complex QRS Pattern Detection in Wearable ECG Using the Pan-Tompkins Algorithm","volume":"12","author":"Entisar","year":"2023","journal-title":"Fusion Pract. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3279","DOI":"10.11591\/eei.v11i6.4344","article-title":"Classifying healthy and infected Covid-19 cases by employing CT scan images","volume":"11","author":"Qasim","year":"2022","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"88","DOI":"10.54216\/FPA.150108","article-title":"Exploring CIE lab color characteristics for skin lesion images detection: A novel image analysis methodology incorporating color-based segmentation and luminosity analysis","volume":"15","year":"2024","journal-title":"Fusion Pract. Appl."},{"key":"ref_21","unstructured":"(2025, August 10). Alzheimer\u2019s Dataset (4 Class of Images). Available online: https:\/\/www.kaggle.com\/datasets\/preetpalsingh25\/alzheimers-dataset-4-class-of-images."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Mienye, I.D., Swart, T.G., Obaido, G., Jordan, M., and Ilono, P. (2025). Deep convolutional neural networks in medical image analysis: A review. Information, 16.","DOI":"10.3390\/info16030195"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wilkinson, C., Yawney, J., and Gadsden, S.A. (2026). Explaining explainability: A comprehensive survey on explainable artificial intelligence and relevant industry applications. Intell. Syst. Appl., 200647.","DOI":"10.1016\/j.iswa.2026.200647"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.neuroimage.2019.05.040","article-title":"Alzheimer\u2019s Disease Neuroimaging Initiative. A model of brain morphological changes related to aging and Alzheimer\u2019s disease from cross-sectional assessments","volume":"198","author":"Sivera","year":"2019","journal-title":"NeuroImage"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/TMI.2020.3022591","article-title":"Multi-view separable pyramid network for AD prediction at MCI stage by 18 F-FDG brain PET imaging","volume":"40","author":"Pan","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Tuvshinjargal, B., and Hwang, H. (2022). VGG-C transform model with batch normalization to predict Alzheimer\u2019s disease through MRI dataset. Electronics, 11.","DOI":"10.3390\/electronics11162601"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"110804","DOI":"10.1016\/j.asoc.2023.110804","article-title":"EDCNNS: Federated learning enabled evolutionary deep convolutional neural network for Alzheimer disease detection","volume":"147","author":"Lakhan","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101940","DOI":"10.1016\/j.jksuci.2024.101940","article-title":"Classification of Alzheimer\u2019s disease using MRI data based on Deep Learning Techniques","volume":"36","author":"Sorour","year":"2024","journal-title":"J. King Saud. Univ. Comput. Inf. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2383219","DOI":"10.1080\/21681163.2024.2383219","article-title":"Alzheimer\u2019s disease multiclass detection through deep learning models and post-processing heuristics","volume":"12","author":"Ioannou","year":"2024","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Vis."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s40708-024-00238-7","article-title":"Ensemble of vision transformer architectures for efficient Alzheimer\u2019s Disease classification","volume":"11","author":"Shaffi","year":"2024","journal-title":"Brain Inform."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"100771","DOI":"10.1016\/j.simpa.2025.100771","article-title":"MRI-based Alzheimer\u2019s disease classification using Vision Transformer and time-series transformer: A step-by-step guide","volume":"25","author":"Alp","year":"2025","journal-title":"Softw. Impacts"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"111065","DOI":"10.1016\/j.compbiomed.2025.111065","article-title":"Regional attention-enhanced vision transformer for accurate Alzheimer\u2019s disease classification using sMRI data","volume":"197","author":"Jomeiri","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"695","DOI":"10.11591\/ijai.v15.i1.pp695-706","article-title":"Deep feature-based multi-class Alzheimer\u2019s disease classification with statistical performance evaluation","volume":"15","author":"Qasim","year":"2026","journal-title":"IAES Int. J. Artif. Intell. (IJ-AI)"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"117365","DOI":"10.1016\/j.marpolbul.2024.117365","article-title":"SR-SqueezeNet: A lightweight hyperspectral identification model for oil spills based on smoothed activation functions","volume":"211","author":"Li","year":"2025","journal-title":"Mar. Pollut. Bull."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JPROC.2021.3060483","article-title":"Explaining deep neural networks and beyond: A review of methods and applications","volume":"109","author":"Samek","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_36","first-page":"20","article-title":"A review on heart disease prediction using machine learning and data analytics approach","volume":"181","author":"Marimuthu","year":"2018","journal-title":"Int. J. Comput. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Goel, S., Deep, A., Srivastava, S., and Tripathi, A. (2019, January 21\u201322). Comparative analysis of various techniques for heart disease prediction. Proceedings of the 2019 4th International Conference on Information Systems and Computer Networks (ISCON), Mathura, India.","DOI":"10.1109\/ISCON47742.2019.9036290"},{"key":"ref_38","first-page":"500","article-title":"Exploring a link between fasting perspective and different patterns of diabetes using a machine learning approach","volume":"12","author":"Ansari","year":"2022","journal-title":"Educ. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/A:1022643204877","article-title":"Induction of decision trees","volume":"1","author":"Quinlan","year":"1986","journal-title":"Mach. Learn."},{"key":"ref_40","unstructured":"Tabesh, P., Lim, G., Khator, S., and Dacso, C. (2010, January 5\u20139). A support vector machine approach for predicting heart conditions. Proceedings of the IISE Annual Conference, Institute of Industrial and Systems Engineers (IISE), Cancun, Mexico."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"56129","DOI":"10.1109\/ACCESS.2019.2911955","article-title":"A critical review on selected fuzzy min-max neural networks and their significance and challenges in pattern classification","volume":"7","author":"Alhroob","year":"2019","journal-title":"IEEE Access"},{"key":"ref_42","first-page":"635","article-title":"Survey of fuzzy min\u2013max neural network for pattern classification variants and applications","volume":"27","author":"Mohammed","year":"2018","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"ref_43","first-page":"20150202","article-title":"Principal component analysis: A review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philos. Trans. Ser. A Math. Phys. Eng. Sci."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/15\/2428\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:12:40Z","timestamp":1785643960000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/15\/2428"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":43,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16152428"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16152428","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]}}}