This systematic review explores the applications of High-Performance Computing (HPC) in AI-driven disease prediction models, emphasizing the role of machine learning (ML) and deep learning (DL) algorithms in advancing healthcare diagnostics. HPC, by enabling rapid data processing and complex simulations, has become indispensable in analyzing large-scale medical data, such as genomic sequencing, biomedical imaging, and electronic health records (EHRs). Through the application of AI, particularly ML and DL models, healthcare systems can achieve more accurate disease predictions and personalized treatment strategies. These models, which learn from vast amounts of medical records and images, improve over time, becoming more precise in diagnosing conditions such as cancer and diabetes. This review assesses the effectiveness, scalability, and practical applications of HPC and AI in healthcare diagnostics, including drug discovery and disease progression modeling. We conducted a comprehensive literature search in multiple databases, including PubMed, Scopus, and IEEE Xplore, focusing on studies published between 2020 and 2025. After applying inclusion and exclusion criteria, 600 relevant studies were selected. The findings underscore the transformative potential of HPC and AI in healthcare, highlighting the accuracy and efficiency these technologies offer in disease prediction and treatment. Future research should focus on enhancing unsupervised learning algorithms and integrating HPC-enabled AI solutions into automated healthcare delivery systems, such as those supported by 5G networks and advanced neural networks. This review provides a critical overview of current advancements and sets the stage for further innovations in AI-driven healthcare diagnostics.