Alzheimer's Disease (AD) is a chronic neurodegenerative disease that affects a large portion of the global population, and early and accurate diagnosis is the key component to proper management and treatment. This work presents the MAGNet model, a novel Deep Learning (DL) architecture for AD classification based on multi-modal imaging data. The MAGNet model uses multi-modal attention that is capable of hierarchically fusing structural MRI, functional MRI, and PET scans to obtain different kinds of information. The MAGNet model was tested on three datasets, with an overall accuracy of 96.2% when distinguishing between the AD, MCI, and CN groups. The proposed approach surpasses benchmark models by achieving 3.5% better accuracy and 5.2% higher sensitivity for early MCI diagnosis. Moreover, the MAGNet model offers interpretable results, employing attention visualization to support clinicians' decisions. MAGNet has the potential to predict cognitive scores and brain age with MMSE errors of 1.8 and a brain age of 2.3 years.

The persistent challenge of COVID-19 vaccine hesitancy hinders global efforts to achieve herd immunity. As a public health barrier, vaccine hesitancy diminishes the impact of immunization programs and prolongs population-level vulnerability. This study investigates vaccine acceptance factors by developing a predictive model based on sociodemographic, health, and lifestyle variables, including smoking status. Data were collected through a structured survey of 500 participants representing diverse demographic backgrounds. The survey included questions on demographics, smoking status, prior COVID-19 infection, health conditions, and attitudes toward vaccine safety. We employed Google Cloud’s Vertex AI AutoML to train and evaluate multiple machine learning classification algorithms. Random Forest and Support Vector Machines (SVM) achieved the highest predictive performance among these. The final model demonstrated strong classification accuracy (93%) and a high AUC score (0.96), underscoring its robustness. Feature importance analysis revealed that individuals concerned about long-term vaccine safety were 2.5 times more likely to be vaccinehesitant. The perception of low personal risk from COVID-19 was also a major contributing factor. By contrast, lifestyle variables such as smoking status had a comparatively weaker association with hesitancy. This study contributes to the growing application of machine learning in public health by presenting a scalable, interpretable framework for identifying populations at higher risk of vaccine hesitancy. These findings provide actionable insights for health authorities, emphasizing the need for communication strategies that directly address safety concerns and risk misperception. Tailored outreach should prioritize individual swith lower educational attainment, where hesitancy was notably more prevalent. These contributions offer a foundation for more effective vaccine campaigns and broader pandemic response efforts