Evaluation of a Decision Mining Tool for Nursing Quality Improvement by Hospital Nurses: Theory-Guided Qualitative Study

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Abstract Background Clinical decision support systems (CDSSs) are widely implemented in hospitals, yet their uptake in nursing practice remains inconsistent. While electronic health records continuously capture nursing decision data, these data are rarely used to support structured quality improvement. Decision mining offers a novel approach by reconstructing and visualizing decision logic from clinical decision logs to support retrospective reflection and protocol evaluation rather than real-time alerting. Before such tools can be integrated into quality improvement programs, their acceptance by clinical users must be empirically examined. Objective This study aimed to conduct an early-stage, user-centered evaluation of a clinical decision mining tool for nursing quality improvement and to examine how nurses evaluate the factors influencing their intention to use the tool, using the unified theory of acceptance and use of technology (UTAUT) as a conceptual organizing framework. Methods An exploratory qualitative design was used, using a theory-guided expert discussion as the primary method. A purposive sample of 5 quality improvement nurses from a large Dutch hospital participated in a 90-minute session comprising a structured prototype demonstration, a 12-item UTAUT-derived questionnaire administered as a facilitation instrument, and an expert discussion. Questionnaire scores were summarized descriptively by construct to anchor and organize the expert group discussion. Expert discussion data were analyzed using directed content analysis, with UTAUT constructs—performance expectancy, effort expectancy, attitude toward use, social influence, and behavioral intention—as sensitizing categories. Attitude toward use was included following UTAUT extensions validated in nursing informatics contexts. Results Performance expectancy scores were consistently high, driven by perceived value for protocol evaluation and data-supported quality improvement discussions. Effort expectancy was moderate and variable, reflecting concerns about data interpretation and limited data literacy rather than interface usability. Attitude toward use showed the lowest construct-level scores and the widest variation, contingent on whether the tool was framed as learning-oriented rather than a monitoring or control mechanism. Behavioral intention was relatively high for targeted use, but participants positioned adoption in structured quality improvement meetings rather than daily in bedside practice, reflecting role differentiation rather than rejection. Social influence did not emerge as a substantive theme at this preimplementation stage. Conclusions Nurses perceived strong value in the CDM tool’s capacity to make protocol adherence and decision variation transparent and discussable within quality improvement settings. Acceptance was conditional on a learning-oriented framing, interpretive scaffolding, and investment in data literacy. The findings suggest that governance framing and interpretive burden function as adoption determinants for retrospective decision support tools in ways not fully captured by standard UTAUT constructs. Retrospective decision mining may complement existing CDSSs not by adding alerts but by strengthening local data-driven learning cycles.