AUTHOR=Niemantsverdriet Michael S. A. , Varkila Meri R. J. , Vromen-Wijsman Jacqueline L. P. , Hoefer Imo E. , Bellomo Domenico , van Vliet Martin H. , van Solinge Wouter W. , Cremer Olaf L. , Haitjema Saskia 

TITLE=Transportability and Implementation Challenges of Early Warning Scores for Septic Shock in the ICU: A Perspective on the TREWScore

JOURNAL=Frontiers in Medicine

VOLUME=Volume 8 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2021.793815

DOI=10.3389/fmed.2021.793815

ISSN=2296-858X

ABSTRACT=The increased use of electronic health records (EHR) has improved availability of routine care data for medical research. Combined with machine learning techniques this has spurred the development of Early Warning Scores (EWS) in hospitals worldwide. EWS are commonly used in the hospital where they have been developed, yet few have been transported to external settings and/or internationally. In this perspective, we describe our experiences in implementing the TREWScore, a septic shock EWS, and the transportability challenges regarding domain, predictors and clinical outcome we faced. We used data of 53,330 ICU stays from MIMIC-III and 18,013 ICU stays from the University Medical Center Utrecht (UMC), including 17,023 (31.9%) and 2,557 (14.2%) cases of sepsis, respectively. The MIMIC-III and UMC populations differed significantly regarding length of stay (6.9 days vs 9.0 days) and hospital mortality (11.6% vs 13.6%). We mapped all 54 TREWScore predictors to the UMC database: 31 were readily available, 7 required unit conversion, 14 had to be engineered, 1 predictor required text mining and 1 predictor could not be mapped. Lastly, we classified sepsis cases for septic shock using the sepsis-2 criteria. Septic shock populations (UMC 31.3%, MIMIC-III 23.3%) as well as time to shock event showed significant differences between the two cohorts. In conclusion, we identified challenges to transportability and implementation regarding domain, predictors and clinical outcome when transporting EWS between hospitals across two continents. These challenges need to be systematically addressed to improve model transportability between centers and unlock the potential clinical utility of EWS.