Dataset Information

COVID-19 mortality risk assessment: An international multi-center study.

ABSTRACT: Timely identification of COVID-19 patients at high risk of mortality can significantly improve patient management and resource allocation within hospitals. This study seeks to develop and validate a data-driven personalized mortality risk calculator for hospitalized COVID-19 patients. De-identified data was obtained for 3,927 COVID-19 positive patients from six independent centers, comprising 33 different hospitals. Demographic, clinical, and laboratory variables were collected at hospital admission. The COVID-19 Mortality Risk (CMR) tool was developed using the XGBoost algorithm to predict mortality. Its discrimination performance was subsequently evaluated on three validation cohorts. The derivation cohort of 3,062 patients has an observed mortality rate of 26.84%. Increased age, decreased oxygen saturation (≤ 93%), elevated levels of C-reactive protein (≥ 130 mg/L), blood urea nitrogen (≥ 18 mg/dL), and blood creatinine (≥ 1.2 mg/dL) were identified as primary risk factors, validating clinical findings. The model obtains out-of-sample AUCs of 0.90 (95% CI, 0.87-0.94) on the derivation cohort. In the validation cohorts, the model obtains AUCs of 0.92 (95% CI, 0.88-0.95) on Seville patients, 0.87 (95% CI, 0.84-0.91) on Hellenic COVID-19 Study Group patients, and 0.81 (95% CI, 0.76-0.85) on Hartford Hospital patients. The CMR tool is available as an online application at covidanalytics.io/mortality_calculator and is currently in clinical use. The CMR model leverages machine learning to generate accurate mortality predictions using commonly available clinical features. This is the first risk score trained and validated on a cohort of COVID-19 patients from Europe and the United States.

SUBMITTER: Bertsimas D

PROVIDER: S-EPMC7725386 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

COVID-19 mortality risk assessment: An international multi-center study.

Bertsimas Dimitris D Lukin Galit G Mingardi Luca L Nohadani Omid O Orfanoudaki Agni A Stellato Bartolomeo B Wiberg Holly H Gonzalez-Garcia Sara S Parra-Calderón Carlos Luis CL Robinson Kenneth K Schneider Michelle M Stein Barry B Estirado Alberto A A Beccara Lia L Canino Rosario R Dal Bello Martina M Pezzetti Federica F Pan Angelo A

PloS one 20201209 12

Timely identification of COVID-19 patients at high risk of mortality can significantly improve patient management and resource allocation within hospitals. This study seeks to develop and validate a data-driven personalized mortality risk calculator for hospitalized COVID-19 patients. De-identified data was obtained for 3,927 COVID-19 positive patients from six independent centers, comprising 33 different hospitals. Demographic, clinical, and laboratory variables were collected at hospital admis ...[more]

PMID: 33296405

Similar Datasets

Project description:BackgroundCoronavirus disease 2019 (COVID-19) mortality has waned significantly over time; however, factors contributing towards this reduction largely remain unidentified. The purpose of this study was to evaluate the trend in mortality at our large tertiary academic health system and factors contributing to this trend.MethodsThis is a retrospective cohort study of intensive care unit (ICU) patients diagnosed with COVID-19 between March and August 2020 admitted across 14 hospitals in the Philadelphia area. Collected data included demographics, comorbidities, admission risk of mortality score, laboratory values, medical interventions, survival outcomes, hospital and ICU length of stay (LOS) and discharge disposition. Chi-square (χ2) test, Fisher exact test, Cochran-Mantel-Haenszel method, multinomial logistic regression models, independent sample t-test, Mann-Whitney U test and one-way analysis of variance (ANOVA) were used.ResultsA total of 1,204 patients were included. Overall mortality was 39%. Mortality declined significantly from 46% in March to 14% in August 2020 (P < 0.05). The most common underlying comorbidities were hypertension (60.2%), diabetes mellitus (44.7%), dyslipidemia (31.6%) and congestive heart failure (14.7%). Hydroxychloroquine (HCQ) use was more commonly associated with the patients who died, while the use of remdesivir, tocilizumab, steroids and duration of these medications were not significantly different. Peak values of ferritin, lactate dehydrogenase (LDH), C-reactive protein (CRP) and D-dimer levels were significantly higher in patients who died (P < 0.05). The mean hospital LOS was significantly longer in the patients who survived compared to the patients who died (18 vs. 12, P < 0.05).ConclusionsThe mortality of patients admitted to our ICU system significantly decreased over time. Factors that may have contributed to this may be the result of a better understanding of COVID-19 pathophysiology and treatments. Further research is needed to elucidate the factors contributing to a reduction in the mortality rate for this patient population.

Project description:BackgroundThe extent of lung involvement in coronavirus disease 2019 (COVID-19) pneumonia, quantified on computed tomography (CT), is an established biomarker for prognosis and guides clinical decision-making. The clinical standard is semi-quantitative scoring of lung involvement by an experienced reader. We aim to compare the performance of automated deep-learning- and threshold-based methods to the manual semi-quantitative lung scoring. Further, we aim to investigate an optimal threshold for quantification of involved lung in COVID pneumonia chest CT, using a multi-center dataset.MethodsIn total 250 patients were included, 50 consecutive patients with RT-PCR confirmed COVID-19 from our local institutional database, and another 200 patients from four international datasets (n=50 each). Lung involvement was scored semi-quantitatively by three experienced radiologists according to the established chest CT score (CCS) ranging from 0-25. Inter-rater reliability was reported by the intraclass correlation coefficient (ICC). Deep-learning-based segmentation of ground-glass and consolidation was obtained by CT Pulmo Auto Results prototype plugin on IntelliSpace Discovery (Philips Healthcare, The Netherlands). Threshold-based segmentation of involved lung was implemented using an open-source tool for whole-lung segmentation under the presence of severe pathologies (R231CovidWeb, Hofmanninger et al., 2020) and consecutive quantitative assessment of lung attenuation. The best threshold was investigated by training and testing a linear regression of deep-learning and threshold-based results in a five-fold cross validation strategy.ResultsMedian CCS among 250 evaluated patients was 10 [6-15]. Inter-rater reliability of the CCS was excellent [ICC 0.97 (0.97-0.98)]. Best attenuation threshold for identification of involved lung was -522 HU. While the relationship of deep-learning- and threshold-based quantification was linear and strong (r2 deep-learning vs. threshold=0.84), both automated quantification methods translated to the semi-quantitative CCS in a non-linear fashion, with an increasing slope towards higher CCS (r2 deep-learning vs. CCS= 0.80, r2 threshold vs. CCS=0.63).ConclusionsThe manual semi-quantitative CCS underestimates the extent of COVID pneumonia in higher score ranges, which limits its clinical usefulness in cases of severe disease. Clinical implementation of fully automated methods, such as deep-learning or threshold-based approaches (best threshold in our multi-center dataset: -522 HU), might save time of trained personnel, abolish inter-reader variability, and allow for truly quantitative, linear assessment of COVID lung involvement.

Dataset Information

COVID-19 mortality risk assessment: An international multi-center study.

Publications

COVID-19 mortality risk assessment: An international multi-center study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets