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

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients. / Jimenez-Solem, Espen; Petersen, Tonny S; Hansen, Casper; Hansen, Christian; Lioma, Christina; Igel, Christian; Boomsma, Wouter; Krause, Oswin; Lorenzen, Stephan; Selvan, Raghavendra; Petersen, Janne; Nyeland, Martin Erik; Ankarfeldt, Mikkel Zöllner; Virenfeldt, Gert Mehl; Winther-Jensen, Matilde; Linneberg, Allan; Ghazi, Mostafa Mehdipour; Detlefsen, Nicki; Lauritzen, Andreas David; Smith, Abraham George; de Bruijne, Marleen; Ibragimov, Bulat; Petersen, Jens; Lillholm, Martin; Middleton, Jon; Mogensen, Stine Hasling; Thorsen-Meyer, Hans-Christian; Perner, Anders; Helleberg, Marie; Kaas-Hansen, Benjamin Skov; Bonde, Mikkel; Bonde, Alexander; Pai, Akshay; Nielsen, Mads; Sillesen, Martin.

I: Scientific Reports, Bind 11, Nr. 1, 3246, 2021.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Jimenez-Solem, E, Petersen, TS, Hansen, C, Hansen, C, Lioma, C, Igel, C, Boomsma, W, Krause, O, Lorenzen, S, Selvan, R, Petersen, J, Nyeland, ME, Ankarfeldt, MZ, Virenfeldt, GM, Winther-Jensen, M, Linneberg, A, Ghazi, MM, Detlefsen, N, Lauritzen, AD, Smith, AG, de Bruijne, M, Ibragimov, B, Petersen, J, Lillholm, M, Middleton, J, Mogensen, SH, Thorsen-Meyer, H-C, Perner, A, Helleberg, M, Kaas-Hansen, BS, Bonde, M, Bonde, A, Pai, A, Nielsen, M & Sillesen, M 2021, 'Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients', Scientific Reports, bind 11, nr. 1, 3246. https://doi.org/10.1038/s41598-021-81844-x

APA

Jimenez-Solem, E., Petersen, T. S., Hansen, C., Hansen, C., Lioma, C., Igel, C., Boomsma, W., Krause, O., Lorenzen, S., Selvan, R., Petersen, J., Nyeland, M. E., Ankarfeldt, M. Z., Virenfeldt, G. M., Winther-Jensen, M., Linneberg, A., Ghazi, M. M., Detlefsen, N., Lauritzen, A. D., ... Sillesen, M. (2021). Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients. Scientific Reports, 11(1), [3246]. https://doi.org/10.1038/s41598-021-81844-x

Vancouver

Jimenez-Solem E, Petersen TS, Hansen C, Hansen C, Lioma C, Igel C o.a. Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients. Scientific Reports. 2021;11(1). 3246. https://doi.org/10.1038/s41598-021-81844-x

Author

Jimenez-Solem, Espen ; Petersen, Tonny S ; Hansen, Casper ; Hansen, Christian ; Lioma, Christina ; Igel, Christian ; Boomsma, Wouter ; Krause, Oswin ; Lorenzen, Stephan ; Selvan, Raghavendra ; Petersen, Janne ; Nyeland, Martin Erik ; Ankarfeldt, Mikkel Zöllner ; Virenfeldt, Gert Mehl ; Winther-Jensen, Matilde ; Linneberg, Allan ; Ghazi, Mostafa Mehdipour ; Detlefsen, Nicki ; Lauritzen, Andreas David ; Smith, Abraham George ; de Bruijne, Marleen ; Ibragimov, Bulat ; Petersen, Jens ; Lillholm, Martin ; Middleton, Jon ; Mogensen, Stine Hasling ; Thorsen-Meyer, Hans-Christian ; Perner, Anders ; Helleberg, Marie ; Kaas-Hansen, Benjamin Skov ; Bonde, Mikkel ; Bonde, Alexander ; Pai, Akshay ; Nielsen, Mads ; Sillesen, Martin. / Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients. I: Scientific Reports. 2021 ; Bind 11, Nr. 1.

Bibtex

@article{0ae374c8ae4248c393d978cb6f45d2dd,
title = "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.",
author = "Espen Jimenez-Solem and Petersen, {Tonny S} and Casper Hansen and Christian Hansen and Christina Lioma and Christian Igel and Wouter Boomsma and Oswin Krause and Stephan Lorenzen and Raghavendra Selvan and Janne Petersen and Nyeland, {Martin Erik} and Ankarfeldt, {Mikkel Z{\"o}llner} and Virenfeldt, {Gert Mehl} and Matilde Winther-Jensen and Allan Linneberg and Ghazi, {Mostafa Mehdipour} and Nicki Detlefsen and Lauritzen, {Andreas David} and Smith, {Abraham George} and {de Bruijne}, Marleen and Bulat Ibragimov and Jens Petersen and Martin Lillholm and Jon Middleton and Mogensen, {Stine Hasling} and Hans-Christian Thorsen-Meyer and Anders Perner and Marie Helleberg and Kaas-Hansen, {Benjamin Skov} and Mikkel Bonde and Alexander Bonde and Akshay Pai and Mads Nielsen and Martin Sillesen",
year = "2021",
doi = "10.1038/s41598-021-81844-x",
language = "English",
volume = "11",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "nature publishing group",
number = "1",

}

RIS

TY - JOUR

T1 - Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients

AU - Jimenez-Solem, Espen

AU - Petersen, Tonny S

AU - Hansen, Casper

AU - Hansen, Christian

AU - Lioma, Christina

AU - Igel, Christian

AU - Boomsma, Wouter

AU - Krause, Oswin

AU - Lorenzen, Stephan

AU - Selvan, Raghavendra

AU - Petersen, Janne

AU - Nyeland, Martin Erik

AU - Ankarfeldt, Mikkel Zöllner

AU - Virenfeldt, Gert Mehl

AU - Winther-Jensen, Matilde

AU - Linneberg, Allan

AU - Ghazi, Mostafa Mehdipour

AU - Detlefsen, Nicki

AU - Lauritzen, Andreas David

AU - Smith, Abraham George

AU - de Bruijne, Marleen

AU - Ibragimov, Bulat

AU - Petersen, Jens

AU - Lillholm, Martin

AU - Middleton, Jon

AU - Mogensen, Stine Hasling

AU - Thorsen-Meyer, Hans-Christian

AU - Perner, Anders

AU - Helleberg, Marie

AU - Kaas-Hansen, Benjamin Skov

AU - Bonde, Mikkel

AU - Bonde, Alexander

AU - Pai, Akshay

AU - Nielsen, Mads

AU - Sillesen, Martin

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

U2 - 10.1038/s41598-021-81844-x

DO - 10.1038/s41598-021-81844-x

M3 - Journal article

C2 - 33547335

VL - 11

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 3246

ER -

ID: 256852594