Validation of an internationally derived patient severity phenotype to support COVID-19 analytics from electronic health record data.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Klann Jeffrey G, Estiri Hossein, Weber Griffin M, Moal Bertrand, Avillach Paul, Hong Chuan, Tan Amelia L M, Beaulieu-Jones Brett K, Castro Victor, Maulhardt Thomas, Geva Alon, Malovini Alberto, South Andrew M, Visweswaran Shyam, Morris Michele, Samayamuthu Malarkodi J, Omenn Gilbert S, Ngiam Kee Yuan, Mandl Kenneth D, Boeker Martin, Olson Karen L, Mowery Danielle L, Follett Robert W, Hanauer David A, Bellazzi Riccardo, Moore Jason H, Loh Ne-Hooi Will, Bell Douglas S, Wagholikar Kavishwar B, Chiovato Luca, Tibollo Valentina, Rieg Siegbert, Li Anthony L L J, Jouhet Vianney, Schriver Emily, Xia Zongqi, Hutch Meghan, Luo Yuan, Kohane Isaac S, Consortium for Clinical Characterization of COVID-19 by EHR (4CE) (CONSORTIA AUTHOR), Brat Gabriel A, Murphy Shawn N
Аннотация
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.