Electronic Cardiac Arrest Risk Triage eCART
More than 200,000 patients in the hospital experience cardiac arrest each year. Of these patients, nearly 80% do not survive. Hospitalized patients outside of intensive care units (ICU) are especially vulnerable because of infrequent physiologic measurements that may cause patients to be less closely monitored. Studies have shown that even delaying transferring patients to the ICUs for a few hours may increase morbidity and mortality.
The eCART uses readily available electronic health record and administrative data (28 variables) to risk stratify ward patients in real time. Research has shown that vital sign abnormalities occur hours before cardiac arrest, which suggests that many of these events could be detected. The algorithm returns a single value that summarizes the risk of clinical decompensation and tracks the score over time to examine trends .
The data output of the eCART algorithm can be inserted into an electronic medical record, a dashboard, even a mobile app. This allows for potentially the following: improved clinical deteroriation rates, reduced cardiac arrest rates on general wards, and reduced ICU bed utilization and costs.
- Churpek MM et al. Multicenter development and validation of risk stratification tool for ward patients. Am J Respir Crit Care Med. Sep 2014; 190(6):649-55.
- Churpek MM et al. Derivation of a cardiac arrest prediction model using ward vital signs. Crit Care Med. July 2012; 40(7):2102-8.
- Churpek MM et al. Using electronic health record data to develop and validate a prediction model for adverse outcomes in the wards. Crit Care Med. Apr 2014; 42(4):841-8.
- Churpek MM, Yuen TC, Edelson DP. Predicting clinical deterioration in the hospital: the impact of outcome selection. Resuscication. May 2013; 84(5):564-8.
- Churpek MM, Yuen TC, Edelson DP. Risk stratification of hospitalzed patients on the wards. Chest. 2013 Jun; 143(6)1758-65.