Projecting COVID-19 disease severity in cancer patients using purposefully-designed machine learning
Open Access
- 4 May 2021
- journal article
- research article
- Published by Springer Science and Business Media LLC in BMC Infectious Diseases
- Vol. 21 (1), 1-8
- https://doi.org/10.1186/s12879-021-06038-2
Abstract
Accurately predicting outcomes for cancer patients with COVID-19 has been clinically challenging. Numerous clinical variables have been retrospectively associated with disease severity, but the predictive value of these variables, and how multiple variables interact to increase risk, remains unclear. We used machine learning algorithms to predict COVID-19 severity in 348 cancer patients at Memorial Sloan Kettering Cancer Center in New York City. Using only clinical variables collected on or before a patient’s COVID-19 positive date (time zero), we sought to classify patients into one of three possible future outcomes: Severe-early (the patient required high levels of oxygen support within 3 days of being tested positive for COVID-19), Severe-late (the patient required high levels of oxygen after 3 days), and Non-severe (the patient never required oxygen support). Our algorithm classified patients into these classes with an area under the receiver operating characteristic curve (AUROC) ranging from 70 to 85%, significantly outperforming prior methods and univariate analyses. Critically, classification accuracy is highest when using a potpourri of clinical variables — including basic patient information, pre-existing diagnoses, laboratory and radiological work, and underlying cancer type — suggesting that COVID-19 in cancer patients comes with numerous, combinatorial risk factors. Overall, we provide a computational tool that can identify high-risk patients early in their disease progression, which could aid in clinical decision-making and selecting treatment options.This publication has 24 references indexed in Scilit:
- Clinical Characteristics of Coronavirus Disease 2019 in ChinaThe New England Journal of Medicine, 2020
- Clinical Characteristics of 138 Hospitalized Patients With 2019 Novel Coronavirus–Infected Pneumonia in Wuhan, ChinaJAMA, 2020
- Clinical Features of 69 Cases With Coronavirus Disease 2019 in Wuhan, ChinaClinical Infectious Diseases, 2020
- Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort studyThe Lancet, 2020
- Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan, ChinaIntensive Care Medicine, 2020
- Clinical course and outcomes of critically ill patients with SARS-CoV-2 pneumonia in Wuhan, China: a single-centered, retrospective, observational studyThe Lancet Respiratory Medicine, 2020
- Abnormal coagulation parameters are associated with poor prognosis in patients with novel coronavirus pneumoniaJournal of Thrombosis and Haemostasis, 2020
- Clinical features of patients infected with 2019 novel coronavirus in Wuhan, ChinaThe Lancet, 2020
- Active LearningSynthesis Lectures on Artificial Intelligence and Machine Learning, 2012
- Random ForestsMachine Learning, 2001