A majority of patients with heart failure (HF) do not receive adequate medical therapy as recommended by clinical guidelines. One major obstacle encountered by population health management (PHM) programs to improve medication usage is the substantial burden placed on clinical staff who must manually sift through electronic health records (EHRs) to ascertain patients' eligibility for the guidelines. As a potential solution, the study team developed a rule-based system (RBS) that automatically parses the EHR for identifying patients with HF who may be eligible for guideline-directed therapy. The RBS was deployed to streamline a PHM program at Brigham and Women's Hospital wherein the RBS was executed every other month to identify potentially eligible patients for further screening by the program staff. The study team evaluated the performance of the system and performed an error analysis to identify areas for improving the system. Of approximately 161,000 patients who have an echocardiogram in the health system, each execution of the RBS typically identified around 4200 patients. A total 5460 patients were manually screened, of which 1754 were found to be truly eligible with an accuracy of 32.1%. An analysis of the false-positive cases showed that over 38% of the false positives were due to incorrect determination of symptomatic HF and medication history of the patients. The system's performance can be potentially improved by integrating information from clinical notes. The RBS provided a systematic way to narrow down the patient population to a subset that is enriched for eligible patients. However, there is a need to further optimize the system by integrating processing of clinical notes. This study highlights the practical challenges of implementing automated tools to facilitate guideline-directed care.
Keywords: electronic health records; guideline adherence; health information systems; population health management.