Print “PDF version

What’s New in the Patient Safety World

May 2022

Reduced Mortality Using Pneumonia Clinical Decision Support Tool



Availability of clinical decision support tools at the right time can be effective in helping clinicians care for patients. But there is a relative paucity of published data on the actual impact of CDSS on patient outcomes. Intermountain Healthcare recently reported patient outcomes after implementation of an electronic pneumonia clinical decision support tool, ePNa, at 16 community hospitals in their system (Dean 2022). Results were striking, with a 38% reduction in severity-adjusted 30-day mortality. It also improved disposition for emergency department (ED) community-acquired pneumonia (CAP) patients.


Clinical decision support tools for predicting severity of community-acquired pneumonia have long been used. Tools such as the PSI (Pneumonia Severity Index) and CURB-65 Score have been useful in suggesting which CAP patients should be hospitalized and which might merit ICU admission.


ePNa is a newer CDSS tool for managing patients with suspected CAP (Dean 2020). It is real-time clinical decision support embedded within the electronic health record, based upon American Thoracic Society/Infectious Disease Society of America guidelines for pneumonia. It utilizes data elements that are already in the electronic medical record (age, mental status, vital signs, oxygen saturation, several lab test results, and radiologic findings).


Like the prior tools, it offers suggestions about patient disposition (discharge home, admit to hospital, admit to ICU). But it also provides recommendations about antibiotic choice and microbiologic studies (such as blood culture, tests for Legionella or MRSA or viral pathogens).


Intermountain Healthcare rolled out the ePNA in clusters at 16 of their community hospitals. Almost 7000 patients were included in the analysis. ePNa was utilized by emergency department clinicians in 67% of eligible patients. Unadjusted mortality was 8.6% before and 4.8% after deployment. After adjustment for severity of illness, the odds ratio for 30-day all-cause mortality was 0.62 (P<0.001) after deployment. Lower mortality was consistent across all hospital clusters. Reductions in mortality were greatest for those patients with severe disease.


Use of the tool also improved both antibiotic selection and time to initiation of antibiotic therapy. Prescribing an antibiotic concordant with the ATS/IDSA increased from 83.5 to 90.2% (P<0.001). Mean time from emergency department admission to first antibiotic was 159.4 minutes at baseline and 150.9 after deployment (P<0.001).


Outpatient disposition from the emergency department increased from 29.2% to 46.9% and 7-day secondary hospital admission was unchanged. Both inpatient hospitalization rates and ICU admissions were reduced after implementation of ePNa.


These results are quite impressive, especially since we suspect many ED physicians were probably using tools like PSI and CURB-65 prior to implementation of ePNa. The ePNa tool appears to be easy to use, improves patient outcomes, and improves utilization of healthcare system resources. Nice work!






Dean NC, Vines CG, Carr JR, et al. A Pragmatic Stepped-wedge, Cluster-controlled Trial of Real-time Pneumonia Clinical Decision Support. American Journal Respiratory and Critical Care Medicine 2022; Online ahead of print March 8, 2022



MedCalc. PSI/PORT Score: Pneumonia Severity Index for CAP.



MedCalc. CURB-65 Score for Pneumonia Severity.



Dean NC, Vines CG, Rubin J, et al. Implementation of Real-Time Electronic Clinical Decision Support for Emergency Department Patients with Pneumonia Across a Healthcare System. AMIA Annu Symp Proc 2020; 2019: 353-362






Print “PDF version








Tip of the Week Archive


What’s New in the Patient Safety World Archive