Objective
Failure to detect clinical deterioration in the hospital is common and associated with poor patient outcomes and increased healthcare costs. Our objective was to evaluate the feasibility and accuracy of real-time risk-stratification using the electronic Cardiac Arrest Risk Triage score version 1 (eCART), an electronic health record based early warning score.
Design
We conducted a prospective black-box validation study. Data were transmitted via HL7 feed in real-time to an integration engine and database server wherein the scores were calculated and stored without visualization for clinical providers. The high-risk threshold was set a priori. Timing and sensitivity of eCART activation were compared to standard of care Rapid Response Team (RRT) activation for patients who experienced a ward cardiac arrest or intensive care unit (ICU) transfer.
Setting
Three general care wards at an academic medical center
Patients
3,889 adult inpatients
Measurements and Main Results
The system generated 5,925 segments during 5,751 admissions. The area under the receiver operating characteristic curve for eCART was 0.88 for cardiac arrest and 0.80 for ICU transfer, consistent with previously published derivation results. During the study period, 8/10 patients with a cardiac arrest had high-risk eCART scores, while the RRT was activated on 2 of these patients (p<0.05). Further, eCART identified 52% (n=201) of the ICU transfers compared to 34% (n=129) by the current system (p<0.001). Patients met the high-risk eCART threshold a median of 30 hours prior to cardiac arrest or ICU transfer versus 1.7 hours for standard RRT activation.
Conclusions
eCART identified significantly more cardiac arrests and ICU transfers than standard RRT activation and did so many hours in advance.