Development and validation of nomogram to predict severe illness requiring intensive care follow up in hospitalized COVID-19 cases

Abstract

Background Early identification of severe COVID-19 patients who will need intensive care unit (ICU) follow-up and providing rapid, aggressive supportive care may reduce mortality and provide optimal use of medical resources. We aimed to develop and validate a nomogram to predict severe COVID-19 cases that would need ICU follow-up based on available and accessible patient values. Methods Patients hospitalized with laboratory-confirmed COVID-19 between March 15, 2020, and June 15, 2020, were enrolled in this retrospective study with 35 variables obtained upon admission considered. Univariate and multivariable logistic regression models were constructed to select potential predictive parameters using 1000 bootstrap samples. Afterward, a nomogram was developed with 5 variables selected from multivariable analysis. The nomogram model was evaluated by Area Under the Curve (AUC) and bias-corrected Harrell's C-index with 95% confidence interval, Hosmer–Lemeshow Goodness-of-fit test, and calibration curve analysis. Results Out of a total of 1022 patients, 686 cases without missing data were used to construct the nomogram. Of the 686, 104 needed ICU follow-up. The final model includes oxygen saturation, CRP, PCT, LDH, troponin as independent factors for the prediction of need for ICU admission. The model has good predictive power with an AUC of 0.93 (0.902–0.950) and a bias-corrected Harrell's C-index of 0.91 (0.899–0.947). Hosmer–Lemeshow test p-value was 0.826 and the model is well-calibrated (p = 0.1703). Conclusion We developed a simple, accessible, easy-to-use nomogram with good distinctive power for severe illness requiring ICU follow-up. Clinicians can easily predict the course of COVID-19 and decide the procedure and facility of further follow-up by using clinical and laboratory values of patients available upon admission.

Predictive Risk Factors at Admission and a “Burning Point” During Hospitalization Serve as Sequential Alerts for Critical Illness in Patients With COVID-19

“…A higher SOFA score at admission was associated with increased odds of in-hospital death for patients with COVID-19 ( 15 ). Previous studies ( 11 , 15 , 26 – 28 ) showed that NLR, D-dimer, LDH, BUN, troponin, CRP, and PCT were risk predictors for the fatal outcome related to COVID-19. INR was reportedly higher in deceased patients than in convalescent patients with COVID-19 ( 29 ).…”

Novel Biomarker-Based Score (Sad-60) for Predicting Mortality in Patients with Covid-19 Pneumonia: A Multicenter Retrospective Cohort of 1013 Patients

“…They developed a novel score with the combination of these seven predictors in addition to age. In the study of Guner et al , 15.2% of COVID-19 patients (n = 104/686) transferred to the ICU [ 29 ]. In their final model, the independent predictors of the need for ICU transfer were SpO2, CRP, procalcitonin, lactate dehidyrogenase and troponin.…”

“…In their final model, the independent predictors of the need for ICU transfer were SpO2, CRP, procalcitonin, lactate dehidyrogenase and troponin. Guner et al reported a good predictive value in the ROC analysis (AUC = 0.93; CI = 0.90–0.95) [ 29 ]. Bayram et al [ 30 ] developed a novel score named CAPA , which allows for the prediction of mortality and ICU admission in patients with COVID-19.…”

Predictors of the Outcomes Following the Tocilizumab Treatment for Severe COVID-19

“…Many predictive models have been created in the context of COVID-19 pneumonia predicting disease severity, progression, or risk of intensive care admission [19][20][21][22]. Mussini et al also tried to identify and model the predictors for tocilizumab failure.…”