JMIR Publications

ABSTRACT

Background:

Successful clinical decision support (CDS) tools can bring evidence-based medicine to the point-of-care to effectively improve patient outcomes. However, the impact of these tools has been limited by low provider adoption due to over-triggering, leading to alert fatigue. We have developed a tracking mechanism for monitoring trigger rate (percent of total visits for which the tool triggers) and adoption rate (percent of completed tools) of a complex CDS tool based on the Wells’ Criteria for pulmonary embolism (PE).

Objective:

Monitor and evaluate the adoption and trigger rates of the tool and to see if ongoing tool modifications would improve adoption rates.

Methods:

As part of a larger clinical trial, a CDS tool was developed using the Wells’ Criteria to calculate pre-test probability for PE at two academic tertiary center’s emergency departments (ED). The tool had multiple triggers: any order for D-dimer, computed tomography (CT) of the chest with intravenous contrast, computed tomography pulmonary angiography (CTPA), ventilation/perfusion scan, or lower extremity Doppler ultrasound. A tracking dashboard was developed using Tableau® to monitor trigger and adoption rates in real-time. Based on initial low provider adoption rates of the tool, small focus groups were conducted with key ED providers to elicit barriers to tool use. Over-triggering of the tool for non-PE-related evaluations and inability to order CT testing for intermediate risk patients were identified. Thus, the tool was modified to allow CT testing for intermediate risk group and to not trigger for CT chest with intravenous contrast orders. Additionally, a dialogue box, “Are you considering PE for this patient?” was added before the tool triggered to account for CTPAs ordered for the evaluation of aortic dissection.

Results:

In the first academic tertiary center’s ED, 95,295 patients were seen during the academic year. The tool triggered for an average of 509 patients per month (6.73%) before the modifications and this reduced to 423 patients per month (5.22%). The second academic tertiary center’s ED saw 88,956 patients during the academic year with the tool triggering for about 473 patients per month (6.38%) before the modifications, and for about 400 (5.12%) afterwards. The modifications resulted in a significant 4.5-fold and 3-fold increase in provider adoption rates. The modifications increased the average monthly adoption rate from 6.51% to 29.33% in center 1, and also increased from 14.73% to 42.64% in center 2.

Conclusions:

Close post-implementation monitoring of CDS tools may help to improve provider adoption. Adaptive modifications based on user feedback may lead to more targeted CDS with lower trigger rates, reducing alert fatigue and increasing provider adoption. This study provides an example of how iterative improvements and a post-implementation monitoring dashboard resulted in significantly improved adoption rates.