Validation of an internationally derived patient severity phenotype to support COVID-19 analytics from electronic health record data
Jeffrey G. Klann, Hossein Estiri, Griffin M. Weber, Bertrand Moal, Paul Avillach, Chuan Hong, Amelia L M Tan, Brett K. Beaulieu‐Jones, Víctor M. Castro, Thomas Maulhardt, Alon Geva, Alberto Malovini, Andrew M. South, Shyam Visweswaran, Michele Morris, Malarkodi J Samayamuthu, Gilbert S. Omenn, Kee Yuan Ngiam, Kenneth D. Mandl, Martin Boeker, Karen L. Olson, Danielle L. Mowery, Robert W Follett, David A. Hanauer, Riccardo Bellazzi, Jason H. Moore, Ne Hooi Will Loh, Douglas S. Bell, Kavishwar B. Wagholikar, Luca Chiovato, Valentina Tibollo, Siegbert Rieg, Anthony L.L.J. Li, Vianney Jouhet, Emily Schriver, Zongqi Xia, Meghan R. Hutch, Yuan Luo, Isaac S. Kohane, Gabriel A. Brat, Shawn N. Murphy
Abstract
OBJECTIVE: The Consortium for Clinical Characterization of COVID-19 by EHR (4CE) is an international collaboration addressing coronavirus disease 2019 (COVID-19) with federated analyses of electronic health record (EHR) data. We sought to develop and validate a computable phenotype for COVID-19 severity. MATERIALS AND METHODS: Twelve 4CE sites participated. First, we developed an EHR-based severity phenotype consisting of 6 code classes, and we validated it on patient hospitalization data from the 12 4CE clinical sites against the outcomes of intensive care unit (ICU) admission and/or death. We also piloted an alternative machine learning approach and compared selected predictors of severity with the 4CE phenotype at 1 site. RESULTS: The full 4CE severity phenotype had pooled sensitivity of 0.73 and specificity 0.83 for the combined outcome of ICU admission and/or death. The sensitivity of individual code categories for acuity had high variability-up to 0.65 across sites. At one pilot site, the expert-derived phenotype had mean area under the curve of 0.903 (95% confidence interval, 0.886-0.921), compared with an area under the curve of 0.956 (95% confidence interval, 0.952-0.959) for the machine learning approach. Billing codes were poor proxies of ICU admission, with as low as 49% precision and recall compared with chart review. DISCUSSION: We developed a severity phenotype using 6 code classes that proved resilient to coding variability across international institutions. In contrast, machine learning approaches may overfit hospital-specific orders. Manual chart review revealed discrepancies even in the gold-standard outcomes, possibly owing to heterogeneous pandemic conditions. CONCLUSIONS: We developed an EHR-based severity phenotype for COVID-19 in hospitalized patients and validated it at 12 international sites.