Chronic diseases such as diabetes, cardiovascular disorders, hypertension, and chronic kidney disease require long-term pharmacological treatment and continuous dosage management. Variations in patient characteristics, disease progression, physiological responses, and medication adherence often influence therapeutic outcomes. Conventional dosage determination approaches generally rely on standardized treatment guidelines that may not fully account for individual patient doi:10.48047/AFJBS.8.2.2026.125-134 variability. Artificial intelligence techniques provide opportunities to analyze patient-specific clinical information and support personalized therapeutic decision-making. This paper presents an Artificial Intelligence-Driven Computational Framework (AICF) for personalized drug delivery and dosage optimization in chronic disease management. The proposed framework integrates patient clinical records, physiological measurements, treatment history, and medication response data within a machine learning-based decision support system. Feature engineering, predictive modeling, and explainability analysis are employed to estimate personalized dosage recommendations and optimize drug administration strategies. A Random Forest based prediction model is utilized to identify appropriate dosage levels, while Shapley Additive Explanations (SHAP) are incorporated to improve interpretability and identify influential clinical factors. Experimental evaluation is conducted using chronic disease management datasets containing patient demographics, laboratory measurements, medication records, and treatment outcomes. Performance is assessed using accuracy, precision, recall, and F1-score metrics. Results demonstrate that the proposed framework effectively supports dosage prediction while providing interpretable explanations regarding treatment recommendations. The findings indicate that artificial intelligence-assisted decision support systems may contribute to individualized drug delivery planning and support evidence based chronic disease management.