International multicenter study comparing COVID-19 in patients with cancer to patients without cancer: Impact of risk factors and treatment modalities on survivorship.

Background: In this international multicenter study, we aimed to determine the independent risk factors associated with increased 30 day mortality and the impact of cancer and novel treatment modalities in a large group of patients with and without cancer with COVID-19 from multiple countries. Methods: We retrospectively collected de-identified data on a cohort of patients with and without cancer diagnosed with COVID-19 between January and November 2020 from 16 international centers. Results: We analyzed 3966 COVID-19 confirmed patients, 1115 with cancer and 2851 without cancer patients. Patients with cancer were more likely to be pancytopenic and have a smoking history, pulmonary disorders, hypertension, diabetes mellitus, and corticosteroid use in the preceding 2 wk (p≤0.01). In addition, they were more likely to present with higher inflammatory biomarkers (D-dimer, ferritin, and procalcitonin) but were less likely to present with clinical symptoms (p≤0.01). By country-adjusted multivariable logistic regression analyses, cancer was not found to be an independent risk factor for 30 day mortality (p=0.18), whereas lymphopenia was independently associated with increased mortality in all patients and in patients with cancer. Older age (≥65y) was the strongest predictor of 30 day mortality in all patients (OR = 4.47, p<0.0001). Remdesivir was the only therapeutic agent independently associated with decreased 30 day mortality (OR = 0.64, p=0.036). Among patients on low-flow oxygen at admission, patients who received remdesivir had a lower 30 day mortality rate than those who did not (5.9 vs 17.6%; p=0.03). Conclusions: Increased 30 day all-cause mortality from COVID-19 was not independently associated with cancer but was independently associated with lymphopenia often observed in hematolgic malignancy. Remdesivir, particularly in patients with cancer receiving low-flow oxygen, can reduce 30 day all-cause mortality. Funding: National Cancer Institute and National Institutes of Health.

International Multicenter Study Comparing Cancer to Non-Cancer Patients with COVID-19: Impact of Risk Factors and Treatment Modalities on Survivorship.

Background: In this international multicenter study we aimed to determine the independent risk factors associated with increased 30-day mortality and the impact of novel treatment modalities in a large group of cancer and non-cancer patients with COVID-19 from multiple countries. Methods: We retrospectively collected de-identified data on a cohort of cancer and non-cancer patients diagnosed with COVID-19 between January and November 2020, from 16 international centers. Results: We analyzed 3966 COVID-19 confirmed patients, 1115 cancer and 2851 non-cancer patients. Cancer patients were more likely to be pancytopenic, and have a smoking history, pulmonary disorders, hypertension, diabetes mellitus, and corticosteroid use in the preceding two weeks (p≤0.01). In addition, they were more likely to present with higher inflammatory biomarkers (D-dimer, ferritin and procalcitonin), but were less likely to present with clinical symptoms (p≤0.01). By multivariable logistic regression analysis, cancer was an independent risk factor for 30-day mortality (OR 1.46; 95% CI 1.03 to 2.07; p=0.035). Older age (≥65 years) was the strongest predictor of 30-day mortality in all patients (OR 4.55; 95% CI 3.34 to6.20; p< 0.0001). Remdesivir was the only therapeutic agent independently associated with decreased 30-day mortality (OR 0.58; CI 0.39-0.88; p=0.009). Among patients on low-flow oxygen at admission, patients who received remdesivir had a lower 30-day mortality rate than those who did not (5.9% vs 17.6%; p=0.03). Conclusions: Cancer is an independent risk factor for increased 30-day all-cause mortality from COVID-19. Remdesivir, particularly in patients receiving low-flow oxygen, can reduce 30-day all-cause mortality. Condensed Abstract: In this large multicenter worldwide study of 4015 patients with COVID-19 that included 1115 patients with cancer, we found that cancer is an independent risk factor for increased 30-day all-cause mortality. Remdesivir is a promising treatment modality to reduce 30-day all-cause mortality.

International Multicenter Study Comparing Cancer to Non-Cancer Patients with COVID-19: Impact of Risk Factors and Treatment Modalities on Survivorship

BackgroundIn this international multicenter study we aimed to determine the independent risk factors associated with increased 30-day mortality and the impact of novel treatment modalities in a large group of cancer and non-cancer patients with COVID-19 from multiple countries. MethodsWe retrospectively collected de-identified data on a cohort of cancer and non-cancer patients diagnosed with COVID-19 between January and November 2020, from 16 international centers. ResultsWe analyzed 3966 COVID-19 confirmed patients, 1115 cancer and 2851 non-cancer patients. Cancer patients were more likely to be pancytopenic, and have a smoking history, pulmonary disorders, hypertension, diabetes mellitus, and corticosteroid use in the preceding two weeks (p[≤]0.01). In addition, they were more likely to present with higher inflammatory biomarkers (D-dimer, ferritin and procalcitonin), but were less likely to present with clinical symptoms (p[≤]0.01). By multivariable logistic regression analysis, cancer was an independent risk factor for 30-day mortality (OR 1.46; 95% CI 1.03 to 2.07; p=0.035). Older age ([≥]65 years) was the strongest predictor of 30-day mortality in all patients (OR 4.55; 95% CI 3.34 to6.20; p< 0.0001). Remdesivir was the only therapeutic agent independently associated with decreased 30-day mortality (OR 0.58; CI 0.39-0.88; p=0.009). Among patients on low-flow oxygen at admission, patients who received remdesivir had a lower 30-day mortality rate than those who did not (5.9% vs 17.6%; p=0.03). ConclusionsCancer is an independent risk factor for increased 30-day all-cause mortality from COVID-19. Remdesivir, particularly in patients receiving low-flow oxygen, can reduce 30-day all-cause mortality. Condensed AbstractIn this large multicenter worldwide study of 4015 patients with COVID-19 that included 1115 patients with cancer, we found that cancer is an independent risk factor for increased 30-day all-cause mortality. Remdesivir is a promising treatment modality to reduce 30-day all-cause mortality.

CovRNN - A recurrent neural network model for predicting outcomes of COVID-19 patients: model development and validation using EHR data

BackgroundPredicting outcomes of COVID-19 patients at an early stage is critical for optimized clinical care and resource management, especially during a pandemic. Although multiple machine learning models have been proposed to address this issue, based on the need for extensive data pre-processing and feature engineering, these models have not been validated or implemented outside of the original study site. MethodsIn this study, we propose CovRNN, recurrent neural network (RNN)-based models to predict COVID-19 patients outcomes, using their available electronic health record (EHR) data on admission, without the need for specific feature selection or missing data imputation. CovRNN is designed to predict three outcomes: in-hospital mortality, need for mechanical ventilation, and long length of stay (LOS >7 days). Predictions are made for time-to-event risk scores (survival prediction) and all-time risk scores (binary prediction). Our models were trained and validated using heterogeneous and de-identified data of 247,960 COVID-19 patients from 87 healthcare systems, derived from the Cerner(R) Real-World Dataset (CRWD). External validation was performed using three test sets (approximately 53,000 patients). Further, the transferability of CovRNN was validated using 36,140 de-identified patients data derived from the Optum(R) de-identified COVID-19 Electronic Health Record v. 1015 dataset (2007-2020). FindingsCovRNN shows higher performance than do traditional models. It achieved an area under the receiving operating characteristic (AUROC) of 93% for mortality and mechanical ventilation predictions on the CRWD test set (vs. 91{middle dot}5% and 90% for light gradient boost machine (LGBM) and logistic regression (LR), respectively) and 86.5% for prediction of LOS > 7 days (vs. 81{middle dot}7% and 80% for LGBM and LR, respectively). For survival prediction, CovRNN achieved a C-index of 86% for mortality and 92{middle dot}6% for mechanical ventilation. External validation confirmed AUROCs in similar ranges. InterpretationTrained on a large heterogeneous real-world dataset, our CovRNN model showed high prediction accuracy, good calibration, and transferability through consistently good performance on multiple external datasets. Our results demonstrate the feasibility of a COVID-19 predictive model that delivers high accuracy without the need for complex feature engineering.