AI-Driven Innovations in Diagnostics, Remote Monitoring, and Clinical Decision Support Systems: A Systematic Review (Preprint)

BACKGROUND Artificial Intelligence (AI) is revolutionizing healthcare through transformative applications in diagnostics, remote monitoring, and clinical decision support. As these technologies rapidly evolve, there remains a need to comprehensively map their current implementations, benefits, and challenges across healthcare settings. OBJECTIVE This systematic review aims to evaluate the role of artificial intelligence (AI) in enhancing diagnostic accuracy, enabling continuous remote patient monitoring, and supporting data-driven clinical decision-making. It systematically investigates the practical applications of AI across various medical domains, including oncology, cardiology, neurology, and medical imaging. In addition, the review identifies common barriers to adoption such as data quality issues, algorithmic bias, ethical and legal concerns, and challenges related to integration with existing healthcare infrastructure. Finally, the review highlights opportunities for the responsible and effective implementation of AI to support scalable, equitable, and patient-centered healthcare delivery. METHODS This systematic review used the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. A structured search strategy was applied across major databases, such as PubMed, IEEE Xplore, ScienceDirect, ACM Digital Library, MDPI, and Google Scholar, targeting studies published between 2020 and 2025. Only peer-reviewed, English-language articles reporting real-world applications of AI in healthcare were included. Eligible studies were critically appraised and synthesized after applying predefined inclusion and exclusion criteria. The findings were categorized into five key thematic domains: AI-Based Diagnostic Imaging, Artificial Intelligence in Remote Patient Monitoring (RPM), Clinical Decision Support Systems (CDSS) with Machine Learning, Ethical and Explainable AI in Healthcare, and AI Integration Challenges in Healthcare Systems. RESULTS Of 912 initial search results, 60 studies were thoroughly reviewed and met the inclusion criteria. The review identified diverse applications of AI that are transforming healthcare delivery. In diagnostics, AI using deep learning improves accuracy in medical imaging and disease detection across areas such as oncology and cardiology. Remote monitoring systems with AI and wearable devices enable real-time health tracking and chronic disease management. AI also supports personalized treatment by integrating multiomics and clinical data to tailor therapies. Clinical decision support tools enhance workflow efficiency and enable early intervention. Key challenges remain, including data privacy, algorithmic bias, limited explainability, and system integration. CONCLUSIONS AI rapidly reshapes healthcare by improving diagnostic accuracy, enabling real-time remote monitoring, supporting personalized treatment, and enhancing clinical decision-making. While its benefits are clear, widespread adoption depends on addressing key barriers such as data quality, algorithm transparency, ethical concerns, and integration with existing systems. Moving forward, collaborative efforts across clinical, technical, and policy domains are essential to ensure responsible, equitable, and effective implementation of AI in healthcare.