Title | ||
---|---|---|
Validation Of An Internationally Derived Patient Severity Phenotype To Support Covid-19 Analytics From Electronic Health Record Data |
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1093/jamia/ocab018 | JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION |
Keywords | DocType | Volume |
novel coronavirus, disease severity, computable phenotype, medical informatics, data networking, data interoperability | Journal | 28 |
Issue | ISSN | Citations |
7 | 1067-5027 | 0 |
PageRank | References | Authors |
0.34 | 0 | 41 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeffrey G. Klann | 1 | 22 | 13.78 |
Griffin Weber | 2 | 226 | 18.49 |
Hossein Estiri | 3 | 8 | 3.94 |
Bertrand Moal | 4 | 0 | 0.34 |
Paul Avillach | 5 | 0 | 0.34 |
Chuan Hong | 6 | 0 | 0.34 |
Victor Castro | 7 | 0 | 0.34 |
Thomas Maulhardt | 8 | 0 | 0.34 |
Amelia L M Tan | 9 | 0 | 0.34 |
Alon Geva | 10 | 2 | 1.38 |
Brett K Beaulieu-Jones | 11 | 0 | 0.34 |
Alberto Malovini | 12 | 20 | 3.91 |
Andrew M South | 13 | 0 | 0.34 |
Shyam Visweswaran | 14 | 5 | 1.90 |
Gilbert S. Omenn | 15 | 107 | 8.45 |
Kee Yuan Ngiam | 16 | 22 | 6.17 |
Kenneth D. Mandl | 17 | 4 | 3.46 |
Martin Boeker | 18 | 138 | 14.04 |
Karen L. Olson | 19 | 9 | 3.23 |
Danielle L Mowery | 20 | 0 | 1.01 |
Michele Morris | 21 | 4 | 1.11 |
Robert W Follett | 22 | 0 | 0.34 |
David A Hanauer | 23 | 0 | 0.34 |
R Bellazzi | 24 | 155 | 18.81 |
Jason H Moore | 25 | 0 | 0.34 |
Ne-Hooi Will Loh | 26 | 0 | 0.34 |
Douglas S Bell | 27 | 0 | 0.34 |
Kavishwar B Wagholikar | 28 | 0 | 0.34 |
Luca Chiovato | 29 | 4 | 3.20 |
Valentina Tibollo | 30 | 50 | 7.26 |
Siegbert Rieg | 31 | 0 | 0.34 |
Anthony L L J Li | 32 | 0 | 0.34 |
Vianney Jouhet | 33 | 0 | 0.34 |
Emily Schriver | 34 | 0 | 0.34 |
Malarkodi J Samayamuthu | 35 | 0 | 0.34 |
Zongqi Xia | 36 | 0 | 0.34 |
Meghan Hutch | 37 | 0 | 0.34 |
Yuan Luo | 38 | 136 | 22.83 |
Isaac S Kohane | 39 | 0 | 0.34 |
Gabriel A Brat | 40 | 0 | 0.34 |
Shawn N Murphy | 41 | 0 | 0.68 |