Send Orders for Reprints to reprints@benthamscience.net Current Alzheimer Research, XXXX, XX, 1-13 1 RESEARCH ARTICLE 1567-2050/XX $65.00+.00 © XXXX Bentham Science Publishers Advancing Alzheimer's Disease Diagnosis Using VGG19 and XGBoost: A Neuroimaging-Based Method Abdelmounim Boudi 1 , Jingfei He 1,* , Isselmou Abd El Kader 2 , Xiaotong Liu 1 and Mohamed Mouhafid 1 1 School of Electronics Information and Engineering, Hebei University of Technology, Tianjin 300401, China; 2 School of International Education, Hebei University of Technology, Tianjin 300401, China Abstract: Introduction: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that currently affects over 55 million individuals worldwide. Conventional diagnostic approaches often rely on subjective clinical assessments and isolated biomarkers, limiting their accuracy and early-stage effectiveness. With the rising global burden of AD, there is an urgent need for objec- tive, automated tools that enhance diagnostic precision using neuroimaging data. Methods: This study proposes a novel diagnostic framework combining a fine-tuned VGG19 deep convolutional neural network with an eXtreme Gradient Boosting (XGBoost) classifier. The model was trained and validated on the OASIS MRI dataset (Dataset 2), which was manually balanced to ensure equitable class representation across the four AD stages. The VGG19 model was pre-trained on ImageNet and fine-tuned by unfreezing its last ten layers. Data augmentation strategies, includ- ing random rotation and zoom, were applied to improve generalization. Extracted features were classified using XGBoost, incorporating class weighting, early stopping, and adaptive learning. Model performance was evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. Results: The proposed VGG19-XGBoost model achieved a test accuracy of 99.6%, with an aver- age precision of 1.00, a recall of 0.99, and an F1-score of 0.99 on the balanced OASIS dataset. ROC curves indicated high separability across AD stages, confirming strong discriminatory power and robustness in classification. Discussion: The integration of deep feature extraction with ensemble learning demonstrated sub- stantial improvement over conventional single-model approaches. The hybrid model effectively mitigated issues of class imbalance and overfitting, offering stable performance across all dementia stages. These findings suggest the method’s practical viability for clinical decision support in early AD diagnosis. Conclusion: This study presents a high-performing, automated diagnostic tool for Alzheimer’s disease based on neuroimaging. The VGG19-XGBoost hybrid architecture demonstrates excep- tional accuracy and robustness, underscoring its potential for real-world applications. Future work will focus on integrating multimodal data and validating the model on larger and more diverse populations to enhance clinical utility and generalizability. A R T I C L E H I S T O R Y Received: March 09, 2025 Revised: May 08, 2025 Accepted: June 17, 2025 DOI: 10.2174/0115672050393604250904081342 Keywords: Alzheimer's disease, MRI, XGBoost, VGG19, classification, OASIS dataset. 1. INTRODUCTION Alzheimer's Disease (AD) is a progressive neurodegener- ative disorder that affects more than 55 million individuals worldwide, causing memory loss, cognitive decline, and im- paired functional abilities, such as dressing, toileting, and walking [1]. AD poses a growing public health crisis, with rising prevalence, high mortality, and significant societal and economic burdens [2]. As populations age, especially in *Address correspondence to this author at the School of Electronics Infor- mation and Engineering, Hebei University of Technology, Tianjin 300401, China; Email: hejingfei@hebut.edu.cn highly developed countries, the incidence of dementia, in- cluding AD, continues to rise. The Global Burden of Disease study reported a 147.95% increase in dementia cases be- tween 1990 and 2019, underscoring the urgent need for re- gionally adapted diagnostic and care strategies [3, 4]. Emerging neuroimaging and biomarker advancements, including Functional Magnetic Resonance Imaging (fMRI) and amyloid/tau detection, enable earlier AD diagnosis com- pared to subjective clinical assessments, improving out- comes and reducing caregiver burden [5-8]. The Internation- al Working Group recommends diagnosing AD only in indi- viduals with both biomarker evidence and clinical symp-