The Impact of AI-Powered Clinical Decision Support Systems on Clinical Decision-Making and Treatment Quality: A Systematic Review

Abstract

Introduction: Artificial intelligence (AI) is revolutionizing clinical decision-making processes by leveraging vast data generated from health records and delivery systems. This enhances safety and quality of care decisions, making Clinical Decision Support Systems (CDSS) essential tools in healthcare, thereby improving clinicians' decisions and patient outcomes.

Methodology: A systematic review was conducted across PubMed, Google Scholar and Cochrane Library, that assessed the use of AI-powered CDSS. Following title and abstract screening, full-text articles were evaluated for methodological quality and compliance to the inclusion criteria. The data extraction process concentrated on study design, AI technologies used, reported outcomes, and proof of AI-CDSS impact on patient and clinical outcomes. A total of 32 studies were included after the screening of the articles, encompassing various study designs and healthcare applications. The analysis focused on evaluating the type of AI technologies employed, their effects on clinical decision-making and treatment quality, and the challenges faced during implementation.

Results: The review found that ML algorithms, including Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs), were predominant among the included studies. Significant improvements were noted in the diagnostic accuracy (reported in 18 studies) and timely medical interventions (12 studies). Personalized treatment recommendations were facilitated in 10 studies, further optimizing treatment protocols in 08 studies. However, challenges such as data privacy concerns and the need for clinician training were highlighted in 10 studies, while ethical considerations were reported in 05 studies.

Conclusion: This systematic review underscores the potential of AI-powered CDSS to significantly enhance clinical decision-making and treatment quality. While AI technologies improve diagnostic and therapeutic processes, their successful integration into clinical practice requires addressing ethical concerns, clinical training, and data management challenges. Future research should focus on long-term impacts, real-world applications, and strategies for overcoming barriers to AI adoption in healthcare settings.

Key words: Artificial Intelligence, Machine Learning, Clinical Decision Support Systems, CDSS, healthcare.