Predicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset

Abstract As the COVID-19 pandemic is challenging healthcare systems worldwide, early identification of patients with a high risk of complication is crucial. We present a prognostic model predicting critical state within 28 days following COVID-19 diagnosis trained on data from US electronic health r...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mike D. Rinderknecht, Yannick Klopfenstein
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Acceso en línea:https://doaj.org/article/25648bc749dd41e6a0c177a1bd17e663
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:25648bc749dd41e6a0c177a1bd17e663
record_format dspace
spelling oai:doaj.org-article:25648bc749dd41e6a0c177a1bd17e6632021-12-02T16:17:26ZPredicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset10.1038/s41746-021-00482-92398-6352https://doaj.org/article/25648bc749dd41e6a0c177a1bd17e6632021-07-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00482-9https://doaj.org/toc/2398-6352Abstract As the COVID-19 pandemic is challenging healthcare systems worldwide, early identification of patients with a high risk of complication is crucial. We present a prognostic model predicting critical state within 28 days following COVID-19 diagnosis trained on data from US electronic health records (IBM Explorys), including demographics, comorbidities, symptoms, and hospitalization. Out of 15753 COVID-19 patients, 2050 went into critical state or deceased. Non-random train-test splits by time were repeated 100 times and led to a ROC AUC of 0.861 [0.838, 0.883] and a precision-recall AUC of 0.434 [0.414, 0.485] (median and interquartile range). The interpretability analysis confirmed evidence on major risk factors (e.g., older age, higher BMI, male gender, diabetes, and cardiovascular disease) in an efficient way compared to clinical studies, demonstrating the model validity. Such personalized predictions could enable fine-graded risk stratification for optimized care management.Mike D. RinderknechtYannick KlopfensteinNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-14 (2021)
institution DOAJ
collection DOAJ
language EN
topic Computer applications to medicine. Medical informatics
R858-859.7
spellingShingle Computer applications to medicine. Medical informatics
R858-859.7
Mike D. Rinderknecht
Yannick Klopfenstein
Predicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset
description Abstract As the COVID-19 pandemic is challenging healthcare systems worldwide, early identification of patients with a high risk of complication is crucial. We present a prognostic model predicting critical state within 28 days following COVID-19 diagnosis trained on data from US electronic health records (IBM Explorys), including demographics, comorbidities, symptoms, and hospitalization. Out of 15753 COVID-19 patients, 2050 went into critical state or deceased. Non-random train-test splits by time were repeated 100 times and led to a ROC AUC of 0.861 [0.838, 0.883] and a precision-recall AUC of 0.434 [0.414, 0.485] (median and interquartile range). The interpretability analysis confirmed evidence on major risk factors (e.g., older age, higher BMI, male gender, diabetes, and cardiovascular disease) in an efficient way compared to clinical studies, demonstrating the model validity. Such personalized predictions could enable fine-graded risk stratification for optimized care management.
format article
author Mike D. Rinderknecht
Yannick Klopfenstein
author_facet Mike D. Rinderknecht
Yannick Klopfenstein
author_sort Mike D. Rinderknecht
title Predicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset
title_short Predicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset
title_full Predicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset
title_fullStr Predicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset
title_full_unstemmed Predicting critical state after COVID-19 diagnosis: model development using a large US electronic health record dataset
title_sort predicting critical state after covid-19 diagnosis: model development using a large us electronic health record dataset
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/25648bc749dd41e6a0c177a1bd17e663
work_keys_str_mv AT mikedrinderknecht predictingcriticalstateaftercovid19diagnosismodeldevelopmentusingalargeuselectronichealthrecorddataset
AT yannickklopfenstein predictingcriticalstateaftercovid19diagnosismodeldevelopmentusingalargeuselectronichealthrecorddataset
_version_ 1718384219840839680