Designing a Multilevel Strategy to Enhance Secondary Prevention of Heart Disease.

Background Coronary artery calcification (CAC), the presence and severity of which strongly predict underlying coronary artery disease (CAD), can be seen on dedicated cardiac imaging studies or incidentally on noncardiac ones; however, the latter findings are commonly managed by primary care clinicians without clear accompanying recommendations and may represent an underrecognized opportunity to optimize secondary prevention of CAD. Methods Standardized practice guidelines and a multilevel implementation strategy for improving secondary prevention of cardiovascular disease through incidentally identified CAC were developed by an interdisciplinary committee. Evidence-based implementation strategies were selected1 and included integrating practice guidelines into radiology reports within the electronic medical records. Outpatient noncardiac computerized tomography scans performed before and after this initiative were retrospectively reviewed to evaluate changes in statin prescribing. Results Authors demonstrated an increase in the percentage of patients with mild CAC prescribed a statin and an increase in the percentage of patients with severe CAC prescribed a high-intensity statin after implementation of standardized practice guidelines and evidence-based implementation strategies. Conclusion Incidental CAC identification is common, particularly in those without known CAD. A multilevel implementation strategy and use of standardized practice guidelines appeared to improve provider prescribing behavior in the primary care setting and may provide an opportunity to enhance secondary CAC prevention.

Predicting hospitalizations from electronic health record data.

OBJECTIVES: Electronic health record (EHR) data have become increasingly available and may help inform clinical prediction. However, predicting hospitalizations among a diverse group of patients remains difficult. We sought to use EHR data to create and internally validate a predictive model for clinical use in predicting hospitalizations. STUDY DESIGN: Retrospective observational cohort study. METHODS: We analyzed EHR data in patients 18 years or older seen at Atrius Health from June 2013 to November 2015. We selected variables among patient demographics, clinical diagnoses, medications, and prior utilization to train a logistic regression model predicting any hospitalization within 6 months and validated the model using a separate validation set. We performed sensitivity analysis on model performance using combinations of EHR-derived, claims-derived, or both EHR- and claims-derived data. RESULTS: After exclusions, 363,855 patient-months were included for analysis, representing 185,388 unique patients. The strongest features included sickle cell anemia (odds ratio [OR], 52.72), lipidoses and glycogenosis (OR, 8.44), heart transplant (OR, 6.12), and age 76 years or older (OR, 5.32). Model testing showed that EHR-only data had an area under the receiver operating characteristic curve (AUC) of 0.84 (95% CI, 0.838-0.853), which was similar to the claims-only data (AUC, 0.84; 95% CI, 0.831-0.848) and combined claims and EHR data (AUC, 0.846; 95% CI, 0.838-0.853). CONCLUSIONS: Prediction models using EHR-only, claims-only, and combined data had similar predictive value and demonstrated strong discrimination for which patients will be hospitalized in the ensuing 6 months.