It is well known that diagnosing Alzheimer's disease (AD) accurately and early is a major clinical challenge, especially when using brain MRI data to differentiate between subtle stages of cognitive decline. This study investigated the efficacy of two deep learning models for the classification of AD stages: Vision Transformer (ViT), a transformer-based architecture, and EfficientNetB7, a convolutional neural network. To enhance classification performance and address class imbalance, extensive data preprocessing and augmentation techniques were employed on the publicly accessible 'Alzheimer’s Dataset (4 class of Images)' from Kaggle. This dataset comprises 6,400 brain MRI images categorized into four AD stages: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. Techniques applied included cropping, horizontal and vertical flipping, 20-degree rotations, histogram equalization, Gaussian noise addition, Gaussian blurring, and thresholding, aimed at improving the representation of underrepresented classes. Hyperparameter optimization was executed via a two-phase methodology: an initial grid search to determine parameter ranges, succeeded by Bayesian optimization employing an upper confidence bound acquisition function to refine learning rates, batch sizes, momentum, and weight decay values. Experimental results indicated that EfficientNetB7 attained a classification accuracy of 93.5% with F1-scores surpassing 92% for early-stage classes, whereas Vision Transformer (ViT) recorded a lower accuracy of 88.7% and exhibited diminished sensitivity to early-stage instances. The performance disparity is due to ViT's dependence on extensive training datasets, which may restrict its generalization when utilized on comparatively smaller medical imaging datasets. The results indicate that, in dataset-constrained  
scenarios, CNN-based architectures such as EfficientNetB7 may provide more consistent and effective performance. Using distinct training, validation, and test datasets, the model's generalization, training stability, and computational efficiency were assessed. With an intuitive user interface, the top-performing model, EfficientNetB7, was implemented as a web-based application to facilitate real-time supportive predictions for research demonstration. This comparative analysis demonstrated that the CNN-based EfficientNetB7 exhibited more robustness with constrained medical imaging data and was computationally economical, but the transformer-based ViT displayed increased sensitivity to dataset size and necessitated extended training to attain similar convergence. The development of a validated and deployable AI-based Alzheimer's disease diagnostic solution showed great promise for clinical use.

Research efforts in the prediction of stroke and diabetes prioritize early detection in order to enhance patient outcomes. To achieve this, a variety of methodologies are integrated. Existing studies, on the other hand, are marred by imbalanced datasets, lack of diversity in their datasets, potential bias, and inadequate model comparisons; these flaws underscore the necessity for more comprehensive and inclusive research methodologies. This paper provides a thorough assessment of machine learning algorithms in the context of early detection and diagnosis of stroke and diabetes. The research employed widely used algorithms, including Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), and XGBoost Classifier, to examine medical data and derive significant findings. The XGBoost Classifier demonstrated superior performance, with an outstanding accuracy, precision, recall, and F1-score of 87.5%. The comparative examination of the algorithms indicated that the Decision Tree, Random Forest, and XGBoost classifiers consistently exhibited strong performance across all measures. The models demonstrated impressive discrimination capabilities, with the XGBoost Classifier and Random Forest reaching accuracy rates of roughly 87.5% and 86.5% respectively. The Decision Tree Classifier exhibited notable performance, with an accuracy rate of 83%. The overall accuracy of the models was evident in the F1-score, a metric that incorporates recall and precision, where the XGBoost model exhibited a marginal improvement of 2% over the Random Forest and Decision Tree models, and 4.25 percent over the last two. The aforementioned results underscore the effectiveness of the XGBoost Classifier, which will be employed as a predictive model in this study, alongside the Random Forest and Decision Tree models, for the accurate identification of stroke and diabetes. Furthermore, combining datasets improves model performance by utilizing relative features. This integrated dataset improves the model's efficiency and creates a resilient and comprehensive prediction model, improving healthcare outcomes. The findings of this research make a valuable contribution to the advancement of AI-driven diagnostic systems, hence enhancing the quality of healthcare decision-making.