Artificial Intelligence in Healthcare: A Multidisciplinary Review of Applications and Challenges

Abstract

The application of artificial intelligence (AI) in contemporary healthcare systems is leading to the fusion of medicine, computer science, biomedical engineering, health informatics, and public health to create intelligent and data-enabled healthcare systems. This review provides a multidisciplinary overview of the basics, applications, implementation challenges, and future trends of AI in healthcare. The review highlights how AI enables clinical decision-making, preventive healthcare, patient-centric healthcare, healthcare processes, precision medicine, and population healthcare through technologies such as machine learning, explainable AI, federated learning, digital twins, the Internet of Medical Things (IoMT), and generative AI. The review also covers major implementation challenges such as data quality, interoperability, clinical validation, privacy, cybersecurity, algorithmic bias, and regulation. The results show that although AI has enhanced the quality, efficiency, and access to healthcare services, its success relies on interdisciplinarity, governance, strong digital infrastructure, and continual assessment of clinical outcomes. Research gaps are outlined, along with the requirement to develop a trustworthy, explainable, and human-centric AI system that can support sustainable and equitable healthcare services. Overall, AI can revolutionize healthcare worldwide by providing efficient and personalized medical services.