@article{9135d72b77144c5bb51266995a9c69d9,
title = "Establishment of CORONET, COVID-19 Risk in Oncology Evaluation Tool, to Identify Patients With Cancer at Low Versus High Risk of Severe Complications of COVID-19 Disease On Presentation to Hospital",
abstract = "Purpose: Patients with cancer are at increased risk of severe COVID-19 disease, but have heterogeneous presentations and outcomes. Decision-making tools for hospital admission, severity prediction, and increased monitoring for early intervention are critical. We sought to identify features of COVID-19 disease in patients with cancer predicting severe disease and build a decision support online tool, COVID-19 Risk in Oncology Evaluation Tool (CORONET).Methods: Patients with active cancer (stage I-IV) and laboratory-confirmed COVID-19 disease presenting to hospitals worldwide were included. Discharge (within 24 hours), admission (≥ 24 hours inpatient), oxygen (O 2) requirement, and death were combined in a 0-3 point severity scale. Association of features with outcomes were investigated using Lasso regression and Random Forest combined with Shapley Additive Explanations. The CORONET model was then examined in the entire cohort to build an online CORONET decision support tool. Admission and severe disease thresholds were established through pragmatically defined cost functions. Finally, the CORONET model was validated on an external cohort. Results: The model development data set comprised 920 patients, with median age 70 (range 5-99) years, 56% males, 44% females, and 81% solid versus 19% hematologic cancers. In derivation, Random Forest demonstrated superior performance over Lasso with lower mean squared error (0.801 v 0.807) and was selected for development. During validation (n = 282 patients), the performance of CORONET varied depending on the country cohort. CORONET cutoffs for admission and mortality of 1.0 and 2.3 were established. The CORONET decision support tool recommended admission for 95% of patients eventually requiring oxygen and 97% of those who died (94% and 98% in validation, respectively). The specificity for mortality prediction was 92% and 83% in derivation and validation, respectively. Shapley Additive Explanations revealed that National Early Warning Score 2, C-reactive protein, and albumin were the most important features contributing to COVID-19 severity prediction in patients with cancer at time of hospital presentation. Conclusion: CORONET, a decision support tool validated in health care systems worldwide, can aid admission decisions and predict COVID-19 severity in patients with cancer.",
keywords = "Adolescent, Adult, Aged, Aged, 80 and over, COVID-19/complications, Child, Child, Preschool, Female, Hospitals, Humans, Male, Middle Aged, Neoplasms/complications, Oxygen, SARS-CoV-2, Young Adult",
author = "Lee, {Rebecca J.} and Oskar Wysocki and Cong Zhou and Rohan Shotton and Ann Tivey and Louise Lever and Joshua Woodcock and Laurence Albiges and Angelos Angelakas and Dirk Arnold and Theingi Aung and Kathryn Banfill and Mark Baxter and Fabrice Barlesi and Arnaud Bayle and Benjamin Besse and Talvinder Bhogal and Hayley Boyce and Fiona Britton and Antonio Calles and Luis Castelo-Branco and Ellen Copson and Croitoru, {Adina E.} and Dani, {Sourbha S.} and Elena Dickens and Leonie Eastlake and Paul Fitzpatrick and Stephanie Foulon and Henrik Frederiksen and Hannah Frost and Sarju Ganatra and Spyridon Gennatas and Andreas Glenth{\o}j and Fabio Gomes and Graham, {Donna M.} and Christina Hague and Kevin Harrington and Michelle Harrison and Laura Horsley and Richard Hoskins and Prerana Huddar and Zoe Hudson and Jakobsen, {Lasse H} and Nalinie Joharatnam-Hogan and Sam Khan and Khan, {Umair T.} and Khurum Khan and Christophe Massard and Alec Maynard and Caroline Wilson",
note = "Funding Information: R.J.L., T.R., and J.W. were supported by the National Institute for Health Research as Clinical Lecturers. T.B. was supported by the National Institute for Health Research as an academic clinical fellow. U.T.K. is an MRC Clinical Training Fellow based at the University of Liverpool supported by the North West England Medical Research Council Fellowship Scheme in Clinical Pharmacology and Therapeutics, which was funded by the Medical Research Council (Award Ref. MR/N025989/ 1), The Liverpool Experimental Cancer Medicine Centre for providing infrastructure support (Grant Reference: C18616/A25153), and The Clatterbridge Cancer charity (North West Cancer Research). C.D. was funded by CRUK Core funding to Manchester Institute (C5757/A27412) and was supported by the CRUK Manchester Centre Award (C5759/ A25254) and by the NIHR Manchester Biomedical Research Centre. C.Z. was funded by the CRUK Manchester Center Award (C5759/A25254), J.S. and P.F. were funded by the CRUK Accelerator Award (29374). This research was funded in part by the Wellcome Trust (205228/Z/16/Z). L.T. was also supported by the National Institute for Health Research Health Protection Research Unit (HPRU) in Emerging and Zoonotic Infections (NIHR200907) at the University of Liverpool in partnership with Public Health England (PHE), in collaboration with Liverpool School of Tropical Medicine and the University of Oxford. L.T. is based at University of Liverpool. M.S. was supported by the Ministry of Science and Higher Education of the Russian Federation within the framework of state support for the creation and development of World-Class Research Centers Digital biodesign and personalized healthcare. No. 075-15-2020-926. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR, and the Department of Health or Public Health England. Funding for COVID-19 work was provided by The Christie Charitable fund (1049751)",
year = "2022",
month = may,
day = "24",
doi = "10.1200/CCI.21.00177",
language = "English",
volume = "6",
journal = "JCO Clinical Cancer Informatics",
issn = "2473-4276",
publisher = "Lippincott Williams and Wilkins",
}