Dataset Information

Development of a Prediction Model for COVID-19 Acute Respiratory Distress Syndrome in Patients With Rheumatic Diseases: Results From the Global Rheumatology Alliance Registry.

ABSTRACT:

Objective

Some patients with rheumatic diseases might be at higher risk for coronavirus disease 2019 (COVID-19) acute respiratory distress syndrome (ARDS). We aimed to develop a prediction model for COVID-19 ARDS in this population and to create a simple risk score calculator for use in clinical settings.

Methods

Data were derived from the COVID-19 Global Rheumatology Alliance Registry from March 24, 2020, to May 12, 2021. Seven machine learning classifiers were trained on ARDS outcomes using 83 variables obtained at COVID-19 diagnosis. Predictive performance was assessed in a US test set and was validated in patients from four countries with independent registries using area under the curve (AUC), accuracy, sensitivity, and specificity. A simple risk score calculator was developed using a regression model incorporating the most influential predictors from the best performing classifier.

Results

The study included 8633 patients from 74 countries, of whom 523 (6%) had ARDS. Gradient boosting had the highest mean AUC (0.78; 95% confidence interval [CI]: 0.67-0.88) and was considered the top performing classifier. Ten predictors were identified as key risk factors and were included in a regression model. The regression model that predicted ARDS with 71% (95% CI: 61%-83%) sensitivity in the test set, and with sensitivities ranging from 61% to 80% in countries with independent registries, was used to develop the risk score calculator.

Conclusion

We were able to predict ARDS with good sensitivity using information readily available at COVID-19 diagnosis. The proposed risk score calculator has the potential to guide risk stratification for treatments, such as monoclonal antibodies, that have potential to reduce COVID-19 disease progression.

SUBMITTER: Izadi Z

PROVIDER: S-EPMC9350083 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of a Prediction Model for COVID-19 Acute Respiratory Distress Syndrome in Patients With Rheumatic Diseases: Results From the Global Rheumatology Alliance Registry.

Izadi Zara Z Gianfrancesco Milena A MA Aguirre Alfredo A Strangfeld Anja A Mateus Elsa F EF Hyrich Kimme L KL Gossec Laure L Carmona Loreto L Lawson-Tovey Saskia S Kearsley-Fleet Lianne L Schaefer Martin M Seet Andrea M AM Schmajuk Gabriela G Jacobsohn Lindsay L Katz Patricia P Rush Stephanie S Al-Emadi Samar S Sparks Jeffrey A JA Hsu Tiffany Y-T TY Patel Naomi J NJ Wise Leanna L Gilbert Emily E Duarte-García Alí A Valenzuela-Almada Maria O MO Ugarte-Gil Manuel F MF Ribeiro Sandra Lúcia Euzébio SLE de Oliveira Marinho Adriana A de Azevedo Valadares Lilian David LD Giuseppe Daniela Di DD Hasseli Rebecca R Richter Jutta G JG Pfeil Alexander A Schmeiser Tim T Isnardi Carolina A CA Reyes Torres Alvaro A AA Alle Gelsomina G Saurit Verónica V Zanetti Anna A Carrara Greta G Labreuche Julien J Barnetche Thomas T Herasse Muriel M Plassart Samira S Santos Maria José MJ Rodrigues Ana Maria AM Robinson Philip C PC Machado Pedro M PM Sirotich Emily E Liew Jean W JW Hausmann Jonathan S JS Sufka Paul P Grainger Rebecca R Bhana Suleman S Costello Wendy W Wallace Zachary S ZS Yazdany Jinoos J

ACR open rheumatology 20220722 10

<h4>Objective</h4>Some patients with rheumatic diseases might be at higher risk for coronavirus disease 2019 (COVID-19) acute respiratory distress syndrome (ARDS). We aimed to develop a prediction model for COVID-19 ARDS in this population and to create a simple risk score calculator for use in clinical settings.<h4>Methods</h4>Data were derived from the COVID-19 Global Rheumatology Alliance Registry from March 24, 2020, to May 12, 2021. Seven machine learning classifiers were trained on ARDS ou ...[more]

PMID: 35869686

Similar Datasets

Project description:IntroductionTo describe clinical characteristics of patients in Japan with coronavirus disease 19 (COVID-19) and pre-existing rheumatic disease and examine the possible risk factors associated with severe COVID-19.MethodsAdults with rheumatic disease and a COVID-19 diagnosis who were registered in the COVID-19 Global Rheumatology Alliance (C19-GRA) physician-reported registry from Japan between 15 May 2020 and 12 May 2021 were included. Multivariable logistic regression models were used to assess factors associated with severe COVID-19 progression, defined as death or requiring oxygen inhalation.ResultsIn total, 222 patients were included in the study. Rheumatoid arthritis (48.2%), gout (14.4%), and systemic lupus erythematosus (8.1%) were the most common types of rheumatic disease, 55.1% of patients were in remission and 66.2% had comorbid disease. Most patients were hospitalised (86.9%) for COVID-19, 43.3% received oxygen, and 9.0% died. Older age (≥ 65 years), corticosteroid use, comorbid diabetes, and lung diseases are associated with higher risk for severe COVID-19 progression (odds ratio (OR) 3.52 [95% confidence interval (CI) 1.69-7.33], OR 2.68 [95% CI 1.23-5.83], OR 3.56 [95% CI 1.42-8.88], and OR 2.59 [95% CI 1.10-6.09], respectively).ConclusionsThis study described clinical characteristics of COVID-19 patients with rheumatic diseases in Japan. Several possible risk factors for severe COVID-19 progression were suggested. Key points • Clinical characteristics of 222 adult patients in Japan with coronavirus disease 19 (COVID-19) and pre-existing rheumatic diseases were described. • Most patients were hospitalised (86.9%) for COVID-19 in Japan, 43.3% received oxygen, and 9.0% died. • The COVID-19 characteristics of patients with rheumatic diseases did not show any obvious different pattern from those of the general population in Japan. • In this study, older age (≥ 65 years), corticosteroid use, comorbid diabetes, and lung diseases are associated with higher risk for severe COVID-19 progression.

Project description:ObjectiveRacial/ethnic minorities experience more severe outcomes of coronavirus disease 2019 (COVID-19) in the general US population. This study was undertaken to examine the association between race/ethnicity and COVID-19 hospitalization, ventilation status, and mortality in people with rheumatic disease.MethodsUS patients with rheumatic disease and COVID-19 were entered into the COVID-19 Global Rheumatology Alliance physician registry between March 24, 2020 and August 26, 2020 were included. Race/ethnicity was defined as White, African American, Latinx, Asian, or other/mixed race. Outcome measures included hospitalization, requirement for ventilatory support, and death. Multivariable regression models were used to estimate odds ratios (ORs) and 95% confidence intervals (95% CIs) adjusted for age, sex, smoking status, rheumatic disease diagnosis, comorbidities, medication use prior to infection, and rheumatic disease activity.ResultsA total of 1,324 patients were included, of whom 36% were hospitalized and 6% died; 26% of hospitalized patients required mechanical ventilation. In multivariable models, African American patients (OR 2.74 [95% CI 1.90-3.95]), Latinx patients (OR 1.71 [95% CI 1.18-2.49]), and Asian patients (OR 2.69 [95% CI 1.16-6.24]) had higher odds of hospitalization compared to White patients. Latinx patients also had 3-fold increased odds of requiring ventilatory support (OR 3.25 [95% CI 1.75-6.05]). No differences in mortality based on race/ethnicity were found, though power to detect associations may have been limited.ConclusionSimilar to findings in the general US population, racial/ethnic minorities with rheumatic disease and COVID-19 had increased odds of hospitalization and ventilatory support. These results illustrate significant health disparities related to COVID-19 in people with rheumatic diseases. The rheumatology community should proactively address the needs of patients currently experiencing inequitable health outcomes during the pandemic.

Dataset Information

Development of a Prediction Model for COVID-19 Acute Respiratory Distress Syndrome in Patients With Rheumatic Diseases: Results From the Global Rheumatology Alliance Registry.

Objective

Methods

Results

Conclusion

Publications

Development of a Prediction Model for COVID-19 Acute Respiratory Distress Syndrome in Patients With Rheumatic Diseases: Results From the Global Rheumatology Alliance Registry.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets