AI-DRIVEN DISEASE PREDICTION AND DIAGNOSIS: A SYSTEMATIC REVIEW OF MACHINE LEARNING AND DEEP LEARNING APPROACHES

The rapid advancement of artificial intelligence (AI) has significantly transformed the healthcare sector, particularly in the domain of disease prediction and diagnosis. This paper presents a comprehensive and systematic review of recent research on AI-driven healthcare prediction systems, focusing on machine learning and deep learning methodologies. The study highlights the growing importance of intelligent systems in analysing complex healthcare data and generating reliable predictions that support early disease detection and improved clinical decision-making. Although AI has brought remarkable improvements in predictive healthcare, several challenges remain, including data quality, interpretability, privacy concerns, and integration with real-world clinical workflows. This review examines a wide range of recent studies to identify commonly used algorithms, datasets, and evaluation strategies, while also analysing their strengths and limitations. Furthermore, the paper discusses the potential impact of AI-based healthcare prediction on patient outcomes and healthcare efficiency. The findings demonstrate that AI plays a crucial role in accurate disease diagnosis, healthcare forecasting, and large-scale health data analysis by leveraging electronic health records and reconstructing patient medical histories. Finally, the study outlines key challenges and proposes future research directions aimed at maximizing the effectiveness and adoption of AI in disease diagnosis and predictive healthcare systems.