Clinical decision support to enhance venous thromboembolism pharmacoprophylaxis prescribing for pediatric inpatients with COVID-19.

Abstract

To design and evaluate a clinical decision support (CDS) module to improve guideline concordant venous thromboembolism (VTE) pharmacoprophylaxis prescribing for pediatric inpatients with COVID-19. The proportion of patients who met our institutional clinical practice guideline's (CPG) criteria for VTE prophylaxis was compared to those who triggered a CDS alert, indicating the patient needed VTE prophylaxis, and to those who were prescribed prophylaxis pre and post the launch of a new VTE CDS module to support VTE pharmacoprophylaxis prescribing. The sensitivity, specificity, positive predictive value (PPV), negative predictive value, F1-score and accuracy of the tool were calculated for the pre- and post-intervention periods using the CPG recommendation as the gold standard. Accuracy was defined as the sum of the true positives and true negatives over the sum of the true positives, false positives, true negatives, and false negatives. Logistic regression was used to identify variables associated with correct thromboprophylaxis prescribing. A significant increase in the proportion of patients triggering a CDS alert occurred in the post-intervention period (44.3% vs. 6.9%, p<.001); however, no reciprocal increase in VTE prophylaxis prescribing was achieved (36.6% vs. 40.9%, p=.53). The updated CDS module had an improved sensitivity (55.0% vs. 13.3%), NPV (44.9% vs. 36.3%), F1-score (66.7% vs. 23.5%), and accuracy (62.5% vs. 42.0%), but an inferior specificity (78.6% vs. 100%) and PPV (84.6% vs. 100%). The updated CDS model had an improved accuracy and overall performance in correctly identifying patients requiring VTE prophylaxis. Despite an increase in correct patient identification by the CDS module, the proportion of patients receiving appropriate pharmacologic prophylaxis did not change. CDS tools to support correct VTE prophylaxis prescribing need ongoing refinement and validation to maximize clinical utility.