Dataset Information

Predictive modeling of morbidity and mortality in COVID-19 hospitalized patients and its clinical implications.

ABSTRACT: Clinical activity of 3740 de-identified COVID-19 positive patients treated at NYU Langone Health (NYULH) were collected between January and August 2020. XGBoost model trained on clinical data from the final 24 hours excelled at predicting mortality (AUC=0.92, specificity=86% and sensitivity=85%). Respiration rate was the most important feature, followed by SpO2 and age 75+. Performance of this model to predict the deceased outcome extended 5 days prior with AUC=0.81, specificity=70%, sensitivity=75%. When only using clinical data from the first 24 hours, AUCs of 0.79, 0.80, and 0.77 were obtained for deceased, ventilated, or ICU admitted, respectively. Although respiration rate and SpO2 levels offered the highest feature importance, other canonical markers including diabetic history, age and temperature offered minimal gain. When lab values were incorporated, prediction of mortality benefited the most from blood urea nitrogen (BUN) and lactate dehydrogenase (LDH). Features predictive of morbidity included LDH, calcium, glucose, and C-reactive protein (CRP). Together this work summarizes efforts to systematically examine the importance of a wide range of features across different endpoint outcomes and at different hospitalization time points.

SUBMITTER: Wang JM

PROVIDER: S-EPMC7724684 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe COVID-19 pandemic began in early 2021 and placed significant strains on health care systems worldwide. There remains a compelling need to analyze factors that are predictive for patients at elevated risk of morbidity and mortality.ObjectiveThe goal of this retrospective study of patients who tested positive with COVID-19 and were treated at NYU (New York University) Langone Health was to identify clinical markers predictive of disease severity in order to assist in clinical decision triage and to provide additional biological insights into disease progression.MethodsThe clinical activity of 3740 patients at NYU Langone Hospital was obtained between January and August 2020; patient data were deidentified. Models were trained on clinical data during different parts of their hospital stay to predict three clinical outcomes: deceased, ventilated, or admitted to the intensive care unit (ICU).ResultsThe XGBoost (eXtreme Gradient Boosting) model that was trained on clinical data from the final 24 hours excelled at predicting mortality (area under the curve [AUC]=0.92; specificity=86%; and sensitivity=85%). Respiration rate was the most important feature, followed by SpO2 (peripheral oxygen saturation) and being aged 75 years and over. Performance of this model to predict the deceased outcome extended 5 days prior, with AUC=0.81, specificity=70%, and sensitivity=75%. When only using clinical data from the first 24 hours, AUCs of 0.79, 0.80, and 0.77 were obtained for deceased, ventilated, or ICU-admitted outcomes, respectively. Although respiration rate and SpO2 levels offered the highest feature importance, other canonical markers, including diabetic history, age, and temperature, offered minimal gain. When lab values were incorporated, prediction of mortality benefited the most from blood urea nitrogen and lactate dehydrogenase (LDH). Features that were predictive of morbidity included LDH, calcium, glucose, and C-reactive protein.ConclusionsTogether, this work summarizes efforts to systematically examine the importance of a wide range of features across different endpoint outcomes and at different hospitalization time points.

Project description:BackgroundThe novel coronavirus SARS-CoV-2 and its associated disease, COVID-19, have caused worldwide disruption, leading countries to take drastic measures to address the progression of the disease. As SARS-CoV-2 continues to spread, hospitals are struggling to allocate resources to patients who are most at risk. In this context, it has become important to develop models that can accurately predict the severity of infection of hospitalized patients to help guide triage, planning, and resource allocation.ObjectiveThe aim of this study was to develop accurate models to predict the mortality of hospitalized patients with COVID-19 using basic demographics and easily obtainable laboratory data.MethodsWe performed a retrospective study of 375 hospitalized patients with COVID-19 in Wuhan, China. The patients were randomly split into derivation and validation cohorts. Regularized logistic regression and support vector machine classifiers were trained on the derivation cohort, and accuracy metrics (F1 scores) were computed on the validation cohort. Two types of models were developed: the first type used laboratory findings from the entire length of the patient's hospital stay, and the second type used laboratory findings that were obtained no later than 12 hours after admission. The models were further validated on a multicenter external cohort of 542 patients.ResultsOf the 375 patients with COVID-19, 174 (46.4%) died of the infection. The study cohort was composed of 224/375 men (59.7%) and 151/375 women (40.3%), with a mean age of 58.83 years (SD 16.46). The models developed using data from throughout the patients' length of stay demonstrated accuracies as high as 97%, whereas the models with admission laboratory variables possessed accuracies of up to 93%. The latter models predicted patient outcomes an average of 11.5 days in advance. Key variables such as lactate dehydrogenase, high-sensitivity C-reactive protein, and percentage of lymphocytes in the blood were indicated by the models. In line with previous studies, age was also found to be an important variable in predicting mortality. In particular, the mean age of patients who survived COVID-19 infection (50.23 years, SD 15.02) was significantly lower than the mean age of patients who died of the infection (68.75 years, SD 11.83; P<.001).ConclusionsMachine learning models can be successfully employed to accurately predict outcomes of patients with COVID-19. Our models achieved high accuracies and could predict outcomes more than one week in advance; this promising result suggests that these models can be highly useful for resource allocation in hospitals.

Project description:Background The scope of pericardial involvement in COVID-19 infection is unknown. We aimed to evaluate the prevalence, associates, and clinical impact of pericardial involvement in hospitalized patients with COVID-19. Methods and Results Consecutive patients with COVID-19 underwent clinical and echocardiographic examination, irrespective of clinical indication, within 48 hours as part of a prospective predefined protocol. Protocol included clinical symptoms and signs suggestive of pericarditis, calculation of modified early warning score, ECG and echocardiographic assessment for pericardial effusion, left and right ventricular systolic and diastolic function, and hemodynamics. We identified predictors of mortality and assessed the adjunctive value of pericardial effusion on top of clinical and echocardiographic parameters. The study included 530 patients. Pericardial effusion was found in 75 (14%), but only 17 patients (3.2%) fulfilled the criteria for acute pericarditis. Pericardial effusion was independently associated with modified early warning score, brain natriuretic peptide, and right ventricular function. It was associated with excess mortality (hazard ratio [HR], 2.44; P=0.0005) in nonadjusted analysis. In multivariate analysis adjusted for modified early warning score and echocardiographic and hemodynamic parameters, it was marginally associated with mortality (HR, 1.86; P=0.06) and improvement in the model fit (P=0.07). Combined assessment for pericardial effusion with modified early warning score, left ventricular ejection fraction, and tricuspid annular plane systolic excursion was an independent predictor of outcome (HR, 1.86; P=0.02) and improved model fit (P=0.02). Conclusions In hospitalized patients with COVID-19, pericardial effusion is prevalent, but rarely attributable to acute pericarditis. It is associated with myocardial dysfunction and mortality. A limited echocardiographic examination, including left ventricular ejection fraction, tricuspid annular plane systolic excursion, and assessment for pericardial effusion, can contribute to outcome prediction.

Dataset Information

Predictive modeling of morbidity and mortality in COVID-19 hospitalized patients and its clinical implications.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets