Unknown

Dataset Information

0

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.


ABSTRACT: Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further analysis. SARS-CoV-2 positive cases from the United Kingdom Biobank was used for external validation. The ML models predicted the risk of death (Receiver Operation Characteristics-Area Under the Curve, ROC-AUC) of 0.906 at diagnosis, 0.818, at hospital admission and 0.721 at Intensive Care Unit (ICU) admission. Similar metrics were achieved for predicted risks of hospital and ICU admission and use of mechanical ventilation. Common risk factors, included age, body mass index and hypertension, although the top risk features shifted towards markers of shock and organ dysfunction in ICU patients. The external validation indicated fair predictive performance for mortality prediction, but suboptimal performance for predicting ICU admission. ML may be used to identify drivers of progression to more severe disease and for prognostication patients in patients with COVID-19. We provide access to an online risk calculator based on these findings.

SUBMITTER: Jimenez-Solem E 

PROVIDER: S-EPMC7864944 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

altmetric image

Publications

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients.

Jimenez-Solem Espen E   Petersen Tonny S TS   Hansen Casper C   Hansen Christian C   Lioma Christina C   Igel Christian C   Boomsma Wouter W   Krause Oswin O   Lorenzen Stephan S   Selvan Raghavendra R   Petersen Janne J   Nyeland Martin Erik ME   Ankarfeldt Mikkel Zöllner MZ   Virenfeldt Gert Mehl GM   Winther-Jensen Matilde M   Linneberg Allan A   Ghazi Mostafa Mehdipour MM   Detlefsen Nicki N   Lauritzen Andreas David AD   Smith Abraham George AG   de Bruijne Marleen M   Ibragimov Bulat B   Petersen Jens J   Lillholm Martin M   Middleton Jon J   Mogensen Stine Hasling SH   Thorsen-Meyer Hans-Christian HC   Perner Anders A   Helleberg Marie M   Kaas-Hansen Benjamin Skov BS   Bonde Mikkel M   Bonde Alexander A   Pai Akshay A   Nielsen Mads M   Sillesen Martin M  

Scientific reports 20210205 1


Patients with severe COVID-19 have overwhelmed healthcare systems worldwide. We hypothesized that machine learning (ML) models could be used to predict risks at different stages of management and thereby provide insights into drivers and prognostic markers of disease progression and death. From a cohort of approx. 2.6 million citizens in Denmark, SARS-CoV-2 PCR tests were performed on subjects suspected for COVID-19 disease; 3944 cases had at least one positive test and were subjected to further  ...[more]

Similar Datasets

| S-EPMC3890557 | biostudies-literature
| S-EPMC10518974 | biostudies-literature
| S-EPMC7261727 | biostudies-literature
| S-EPMC9255527 | biostudies-literature
| S-EPMC7318303 | biostudies-literature
| S-EPMC4770814 | biostudies-other
| S-EPMC9856360 | biostudies-literature
| S-EPMC8767133 | biostudies-literature
| S-EPMC10836286 | biostudies-literature
| S-EPMC8530399 | biostudies-literature