The Role of Explainable AI in Enhancing Trust and Adoption in Clinical Decision Support Systems

Abstract

AI-based Clinical Decision Support Systems (CDSS) have emerged as powerful tools in the healthcare sector, assisting in diagnosis, prognostics, and treatment planning. Clinical Decision Support Systems driven by AI research have theoretical benefits, but the acceptance of CDSS driven by AI is frequently hampered due to the skepticism of clinicians, and this skepticism is bridled by the "black box" nature of these models. Explainable AI (XAI) methods attempt to fill this gap by giving outputs that are transparent, interpretable and easy to comprehend. To that end, this study analyzes the influence of XAI on trust and adoption of AI-enabled CDSS among health care professionals. Through a mixed-method approach of quantitative surveys and experimental data, we show that explainability improves clinician confidence that further improves the adoption of CDSS tools. This implies these findings come with their data driven( statistical tests and graphs) validation