TY - JOUR

T1 - 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

AU - Lee, Rebecca J.

AU - Wysocki, Oskar

AU - Zhou, Cong

AU - Shotton, Rohan

AU - Tivey, Ann

AU - Lever, Louise

AU - Woodcock, Joshua

AU - Albiges, Laurence

AU - Angelakas, Angelos

AU - Arnold, Dirk

AU - Aung, Theingi

AU - Banfill, Kathryn

AU - Baxter, Mark

AU - Barlesi, Fabrice

AU - Bayle, Arnaud

AU - Besse, Benjamin

AU - Bhogal, Talvinder

AU - Boyce, Hayley

AU - Britton, Fiona

AU - Calles, Antonio

AU - Castelo-Branco, Luis

AU - Copson, Ellen

AU - Croitoru, Adina E.

AU - Dani, Sourbha S.

AU - Dickens, Elena

AU - Eastlake, Leonie

AU - Fitzpatrick, Paul

AU - Foulon, Stephanie

AU - Frederiksen, Henrik

AU - Frost, Hannah

AU - Ganatra, Sarju

AU - Gennatas, Spyridon

AU - Glenthøj, Andreas

AU - Gomes, Fabio

AU - Graham, Donna M.

AU - Hague, Christina

AU - Harrington, Kevin

AU - Harrison, Michelle

AU - Horsley, Laura

AU - Hoskins, Richard

AU - Huddar, Prerana

AU - Hudson, Zoe

AU - Jakobsen, Lasse H.

AU - Joharatnam-Hogan, Nalinie

AU - Khan, Sam

AU - Khan, Umair T.

AU - Khan, Khurum

AU - Massard, Christophe

AU - Maynard, Alec

AU - McKenzie, Hayley

AU - Michielin, Olivier

AU - Mosenthal, Anne C.

AU - Obispo, Berta

AU - Patel, Rushin

AU - Pentheroudakis, George

AU - Peters, Solange

AU - Rieger-Christ, Kimberly

AU - Robinson, Timothy

AU - Rogado, Jacobo

AU - Romano, Emanuela

AU - Rowe, Michael

AU - Sekacheva, Marina

AU - Sheehan, Roseleen

AU - Stevenson, Julie

AU - Stockdale, Alexander

AU - Thomas, Anne

AU - Turtle, Lance

AU - Viñal, David

AU - Weaver, Jamie

AU - Williams, Sophie

AU - Wilson, Caroline

AU - Palmieri, Carlo

AU - Landers, Donal

AU - Cooksley, Timothy

AU - Dive, Caroline

AU - Freitas, André

AU - Armstrong, Anne C.

N1 - Publisher Copyright: © American Society of Clinical Oncology.

PY - 2022

Y1 - 2022

N2 - PURPOSEPatients 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).METHODSPatients 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 (O2) 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.RESULTSThe 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.CONCLUSIONCORONET, a decision support tool validated in health care systems worldwide, can aid admission decisions and predict COVID-19 severity in patients with cancer.

AB - PURPOSEPatients 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).METHODSPatients 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 (O2) 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.RESULTSThe 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.CONCLUSIONCORONET, a decision support tool validated in health care systems worldwide, can aid admission decisions and predict COVID-19 severity in patients with cancer.

U2 - 10.1200/CCI.21.00177

DO - 10.1200/CCI.21.00177

M3 - Journal article

C2 - 35609228

AN - SCOPUS:85130652633

VL - 6

JO - JCO clinical cancer informatics

JF - JCO clinical cancer informatics

SN - 2473-4276

M1 - e2100177

ER -