1
|
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 HC, Perner A, Helleberg M, Kaas-Hansen BS, Bonde M, Bonde A, Pai A, Nielsen M, Sillesen M. Developing and validating COVID-19 adverse outcome risk prediction models from a bi-national European cohort of 5594 patients. Sci Rep 2021; 11:3246. [PMID: 33547335 PMCID: PMC7864944 DOI: 10.1038/s41598-021-81844-x] [Citation(s) in RCA: 45] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2020] [Accepted: 01/12/2021] [Indexed: 12/15/2022] Open
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.
Collapse
Affiliation(s)
- Espen Jimenez-Solem
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.,Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology and Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Tonny S Petersen
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Casper Hansen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Christian Hansen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Christina Lioma
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Christian Igel
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Wouter Boomsma
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Oswin Krause
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Stephan Lorenzen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Raghavendra Selvan
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Janne Petersen
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Section of Biostatistics, Department of Public Health, University of Copenhagen, Copenhagen, Denmark.,Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology and Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Martin Erik Nyeland
- Department of Clinical Pharmacology, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Mikkel Zöllner Ankarfeldt
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark.,Copenhagen Phase IV Unit (Phase4CPH), Department of Clinical Pharmacology and Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Gert Mehl Virenfeldt
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Matilde Winther-Jensen
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | - Allan Linneberg
- Center for Clinical Research and Prevention, Copenhagen University Hospital, Bispebjerg and Frederiksberg, Copenhagen, Denmark
| | | | - Nicki Detlefsen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,DTU Compute, Denmarks Technical University, Lyngby, Denmark
| | | | | | - Marleen de Bruijne
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,Department of Radiology and Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Bulat Ibragimov
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Jens Petersen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Martin Lillholm
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Jon Middleton
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | | | | | - Anders Perner
- Department of Intensive Care Medicine, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Marie Helleberg
- Department of Infectious Diseases, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | | | - Mikkel Bonde
- Center for Surgical Translational and Artificial Intelligence Research (CSTAR), Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Alexander Bonde
- Department of Surgical Gastroenterology, Copenhagen University Hospital, Rigshospitalet, Blegdamsvej 9, 2100, Copenhagen Ø, Denmark.,Center for Surgical Translational and Artificial Intelligence Research (CSTAR), Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Akshay Pai
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.,Cerebriu A/S, Copenhagen, Denmark
| | - Mads Nielsen
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| | - Martin Sillesen
- Department of Surgical Gastroenterology, Copenhagen University Hospital, Rigshospitalet, Blegdamsvej 9, 2100, Copenhagen Ø, Denmark. .,Center for Surgical Translational and Artificial Intelligence Research (CSTAR), Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark. .,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.
| |
Collapse
|