Developing and implementing a heart failure data mart for research and quality improvement

摘要

Objective: The purpose of this project was to build and formatively evaluate a near-real time heart failure (HF) data mart. Heart Failure (HF) is a leading cause of hospital readmissions. Increased efforts to use data meaningfully may enable healthcare organizations to better evaluate effectiveness of care pathways and quality improvements, and to prospectively identify risk among HF patients. Methods and procedures: We followed a modified version of the Systems Development Life Cycle: 1) Conceptualization, 2) Requirements Analysis, 3) Iterative Development, and 4) Application Release. This foundational work reflects the first of a two-phase project. Phase two (in process) involves the implementation and evaluation of predictive analytics for clinical decision support. Results: We engaged stakeholders to build working definitions and established automated processes for creating an HF data mart containing actionable information for diverse audiences. As of December 2017, the data mart contains information from over 175,000 distinct patients and >100 variables from each of their nearly 300,000 visits. Conclusion: The HF data mart will be used to enhance care, assist in clinical decision-making, and improve overall quality of care. This model holds the potential to be scaled and generalized beyond the initial focus and setting.