BACKGROUND
Predictive models may help providers tailor asthma therapies to an individual’s risk of exacerbation. The effectiveness of asthma risk scores on provider behavior and pediatric asthma outcomes remains unknown.
OBJECTIVE
Determine the impact of an electronic health record (EHR) vendor-released model on outcomes for children with asthma.
METHODS
We implemented a vendor Risk of Pediatric Asthma Exacerbation model as a non-interruptive risk score visible in the patient schedule view beginning 2/24/2021 in allergy and pulmonology clinics with 6 volunteer providers. We conducted a difference-in-differences analysis from 2/24/2019 – 2/23/2022 with a control group of other providers in the same departments. Primary outcomes included asthma hospitalization, ED visit, or oral steroid course within 90 days of an outpatient encounter. Volunteer providers were also interviewed to identify barriers and facilitators to model use.
RESULTS
The adjusted difference-in-differences estimators for the hospitalization, ED visit, oral steroid, and composite outcomes were -0.9% (95% CI: -1.6 to -0.3), –2.4% (-3.9 to -0.8), –1.9% (-4.3 to 0.5), and –2.3% (-4.7 to 0.2). In qualitative analysis, providers generally understood the purpose of the model and felt that it was useful to flag high exacerbation risk. Trust in the model was generally calibrated against providers’ own clinical judgement.
CONCLUSIONS
This EHR vendor model implementation was associated with a significant decrease in asthma hospitalization and ED visits within 90 days of pediatric allergy and pulmonology clinic visits, but not oral steroid courses.