Quantifying System and Data Readiness for Automated Clinical Decision Support

点击翻译按钮获取中文摘要

ABSTRACT Automated clinical decision support (CDS) tools (e.g., provider alerts and reminders, or context relevant treatment information), embedded within electronic health record (EHR) systems, have been shown to improve provider compliance with practice guidelines and improve patient outcomes. The routine use of automated CDS is a fundamental component of the national healthcare reform strategy endorsed by the Centers for Medicare and Medicaid Services, the Office of the National Coordinator for Health IT, and two presidents. Once an organization identifies a clinical “practice gap” and corresponding CDS application, such as a provider alert, a number of technical and social issues must be addressed to ensure that the CDS intervention fits well in current work flows, is acceptable to providers, and functions as intended. At present, there is no guidance for potential CDS implementers on how to align their local data structures with the patient data “input” requirements of formal algorithm-based guidelines, nor is there a model to quantify the readiness of an organization or the resources that will be needed to integrate different CDS applications into local EHR systems. This proposed research will quantify the alignment of CDS data requirements (“inputs”) with EHR data structures, the quality of the data collected, and provider preferences. We propose to combine these metrics into a feasibility assessment for CDS implementation that can be used by organizations to prioritize CDS projects and by disease advocacy organizations and professional societies to identify CDS opportunities with the broadest potential for implementation and impact.