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.

Factors associated with freqeuncy and severity of COVID-19 in patients with axial spondyloarthritis

“…In a prospective study with 103 COVID-19 patients who had a diagnosis with AS (54%) and RA (46%), hospitalized patients had a higher ratio of advanced age, HT, COPD, and GC use, but anti-cytokine therapy was associated with worse COVID-19 outcomes [23]. Some predictive factors of acute respiratory distress syndrome (ARDS) in patients with rheumatic diseases such as age, daily glucocorticoid dose, pulmonary hypertension, interstitial lung disease, CKD, rituximab, DM, HT, active rheumatic disease, and morbid obesity were at exclusion criteria or absent in our study population so it may be the reason why we didn't encounter the ARDS [24]. Obesity, male sex, HT, DM, and CKD are associated with poor prognosis in COVID-19.…”

“…In patients with severe SaRS-CoV-2 infection, the serum level of TNF-α is elevated, which causes cytokine storm and lung injury [27,28]; potential beneficial effects of TNF-α blocking may be a result of this mechanism. Systemic GC and rituximab (RTX) use have harmful effects on COVID-19 in patients with IRD, but GC is not widely used, and RTX is not licensed for axSpa [16,17,21,23,24,29]. Thus, the treatment of axSpa is safe in general during the pandemic.…”

Critical evaluation of established risk prediction models for acute respiratory distress syndrome in adult patients: A systematic review and meta‐analysis

“…40 Ding et al used a LASSO binary logistic regression. 38 Of the included studies, missing data were handled by multiple imputation in two studies, 30,34 single imputation in three studies, 26,37,40 median imputation in two studies, 26,40 patients with missing data were excluded from model development in eight studies, 28,32,33,38,[42][43][44][45] missing data treated as an absent disease state or a standard variable in two studies, 24,25 a category for missing values was created in two studies. 23,35 In addition, methods for dealing with missing data were not reported in five studies.…”

“…25 Nine studies reported model calibration graphically using calibration plots. 27,35,38,39,[41][42][43]45,47 In total, 16 studies reported both discrimination and calibration measures.…”

Acute and postacute COVID-19 outcomes for patients with rheumatoid arthritis: lessons learned and emerging directions 3 years into the pandemic

“…The COVID-19 Global Rheumatology Alliance (GRA) also performed important early studies using voluntarily reported data from physicians. These included risk factors for hospitalization and mortality [ 11 , 12 ▪ , 13 ] due to COVID-19 that such as specific medications [ 14 ], comorbidities, disease activity, race/ethnicity [ 15 ], and area-level/societal factors [ 16 ▪ ]. A meta-analysis and systematic review performed by the GRA showed that patients with SARDs had higher risk of COVID-19 infection [odds ratio (OR) 1.53, 95% confidence interval (CI) 1.16–2.01] and mortality (OR 1.74, 95% CI 1.08–2.80) compared with the general population [ 17 ▪▪ ].…”