Usability Testing of an Explainable AI-enhanced Tool for Clinical Decision Support: Insights from the Reflexive Thematic Analysis
For clinicians and healthcare AI developers, this work provides a qualitative framework to guide explainability features, though it is incremental as it builds on existing concepts.
This study conducted a usability test with 20 U.S. clinicians to develop a concrete framework and operational definition of explainability for AI-enhanced clinical decision support tools, aiming to improve clinician acceptance.
Artificial intelligence-augmented technology represents a considerable opportunity for improving healthcare delivery. Significant progress has been made to demonstrate the value of complex models to enhance clinicians` efficiency in decision-making. However, the clinical adoption of such models is scarce due to multifaceted implementation issues, with the explainability of AI models being among them. One of the substantially documented areas of concern is the unclear AI explainability that negatively influences clinicians` considerations for accepting the complex model. With a usability study engaging 20 U.S.-based clinicians and following the qualitative reflexive thematic analysis, this study develops and presents a concrete framework and an operational definition of explainability. The framework can inform the required customizations and feature developments in AI tools to support clinicians` preferences and enhance their acceptance.