AI-DRIVEN CLINICAL DECISION SUPPORT SYSTEMS: EVALUATING IMPACT ON DIAGNOSIS AND TREATMENT ACCURACY

Abstract

AI-driven Clinical Decision Support Systems (CDSS) are investigated in this study to evaluate their efficacy and limitations in enhancing diagnostic and treatment accuracy within healthcare settings. Integrating artificial intelligence into CDSS promises to reduce human error, improve patient outcomes, and optimize clinical workflows. Through a mixed-methods approach involving quantitative analysis of diagnostic concordance rates and qualitative assessments of clinician trust and system usability, this study evaluates real-world applications across multiple healthcare environments. Results demonstrate significant improvements in diagnostic precision and treatment recommendations, particularly in imaging-based and primary care scenarios. However, challenges such as algorithmic transparency, data bias, and integration into clinical workflows persist. This paper contributes to the growing literature on AI in healthcare by offering a critical evaluation of CDSS performance, supported by empirical evidence and comparative studies.