RESUMO
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.
Assuntos
COVID-19 , Linfopenia , Neoplasias , Humanos , COVID-19/complicações , COVID-19/terapia , Estudos Retrospectivos , SARS-CoV-2 , Sobrevivência , Fatores de Risco , Neoplasias/complicações , Neoplasias/epidemiologia , OxigênioRESUMO
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.
RESUMO
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.
RESUMO
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.