Back

Implementing an Improved STEMI Alert Notification System Workflow to Reduce Alarm Fatigue in a Community Hospital

Jacinto, J.; Jonna, S.; Alsaghir, R.; Hassan, S.; Syed, M.

2025-06-02 cardiovascular medicine
10.1101/2025.05.27.25328465 medRxiv
Show abstract

BackgroundThe assumed national average of STEMI cancellations due to inappropriate activations is approximately 15%. In the final quarter of 2022, 57.9% of hospital-wide and 55.6% of ED/EMS STEMI activations were canceled at HCA Florida Orange Park Hospital. This cancellation rate contributed to overall "alarm fatigue" and hospital staff dissatisfaction over the hospitals overuse of hospital resources. MethodsAn evaluation of the STEMI activation system revealed breakdown in communication from EMS to ED physician, inaccurate cardiology on-call schedule, and inefficient communication of case details between EMS, ED physician, and cardiologist. An algorithm was created that directed all STEMI activations from EMS to the ED physician for review, who may activate the STEMI alert or discuss the case with the on-call cardiologist. This plan was implemented and allowed a 30-day adjustment period. After this period, a prospective analysis of STEMI cancellations in the 2nd quarter of 2023 was performed with cath lab staff satisfaction surveys. ResultsThe data on retrospective analysis of the final quarter of 2022 showed a STEMI cancellation rate of 68.8% hospital-wide and 66.7% from the ED and EMS. After the 30-day implementation of the plan, the hospital-wide STEMI cancellation rate dropped to 20% and 22% from the ED and EMS in the 2nd quarter of 2023 without adverse effect on door-to-balloon time. ConclusionsThe multidisciplinary approach to the creation and implementation of the new STEMI activation algorithm resulted in a significant reduction in false activations, improved cath lab staff satisfaction, and better utilization of hospital resources.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.