Development and validation of a nomogram for the early prediction of acute kidney injury in hospitalized COVID-19 patients

Abstract

Introduction: Acute kidney injury (AKI) is a prevalent complication of coronavirus disease 2019 (COVID-19) and is closely linked with a poorer prognosis. The aim of this study was to develop and validate an easy-to-use and accurate early prediction model for AKI in hospitalized COVID-19 patients.

Methods: Data from 480 COVID-19-positive patients (336 in the training set and 144 in the validation set) were obtained from the public database of the Cancer Imaging Archive (TCIA). The least absolute shrinkage and selection operator (LASSO) regression method and multivariate logistic regression were used to screen potential predictive factors to construct the prediction nomogram. Receiver operating curves (ROC), calibration curves, as well as decision curve analysis (DCA) were adopted to assess the effectiveness of the nomogram. The prognostic value of the nomogram was also examined.

Results: A predictive nomogram for AKI was developed based on arterial oxygen saturation, procalcitonin, C-reactive protein, glomerular filtration rate, and the history of coronary artery disease. In the training set, the nomogram produced an AUC of 0.831 (95% confidence interval [CI]: 0.774-0.889) with a sensitivity of 85.2% and a specificity of 69.9%. In the validation set, the nomogram produced an AUC of 0.810 (95% CI: 0.737-0.871) with a sensitivity of 77.4% and a specificity of 78.8%. The calibration curve shows that the nomogram exhibited excellent calibration and fit in both the training and validation sets. DCA suggested that the nomogram has promising clinical effectiveness. In addition, the median length of stay (m-LS) for patients in the high-risk group for AKI (risk score ≥ 0.122) was 14.0 days (95% CI: 11.3-16.7 days), which was significantly longer than 8.0 days (95% CI: 7.1-8.9 days) for patients in the low-risk group (risk score <0.122) (hazard ratio (HR): 1.98, 95% CI: 1.55-2.53, p < 0.001). Moreover, the mortality rate was also significantly higher in the high-risk group than that in the low-risk group (20.6 vs. 2.9%, odd ratio (OR):8.61, 95%CI: 3.45-21.52).

Conclusions: The newly constructed nomogram model could accurately identify potential COVID-19 patients who may experience AKI during hospitalization at the very beginning of their admission and may be useful for informing clinical prognosis.

Keywords: COVID-19; acute kidney injury; length of stay; mortality; nomogram.

Figure 1

The flowchart of the study procedure. Abbreviations: LASSO, least absolute shrinkage and selection operator; ROC, receiver operating characteristic; DCA, decision curve analysis.

Figure 2

Feature selection using the least absolute shrinkage and selection operator (LASSO) Cox regression model. (A) LASSO coefficient profiles of the 41 features. (A) coefficient profile plot was produced against the log (λ) sequence. (B) Selection of tuning parameter (λ) in the LASSO regression using 10-fold cross-validation via minimum criteria. At the optimal values log (λ), where features are selected, two dotted vertical lines were drawn at the optimal scores by minimum criteria and 1-s.e. criteria.

Figure 3

Results of multivariate logistic regression analysis in the training set. Factors with p-values < 0.1 were screened for constructing the nomogram model. Abbreviations: CAD, coronary artery disease; SaO2, artery oxygen saturation; ALT, alanine aminotransferase; PCT, procalcitonin; CRP, C-reactive protein; GFR, SCR, serum creatinine; GFR, glomerular filtration rate.

Figure 4

The nomogram was developed in the training set. It included five factors: glomerular filtration rate (GFR), artery oxygen saturation (SaO2), procalcitonin (PCT), C-reactive protein (CRP), and history of coronary artery disease (CAD). The nomogram plot provides a visual way to predict the risk of AKI for COVID-19 patients.

Figure 5

Validation of the discrimination power of the nomogram in the training and validation sets. (A,D) ROC curve analysis of the nomogram in the training and validation sets (AUC, 0.831 and 0.810, respectively); (B,E) Calibration plot of the nomogram in the training and validation sets, The black dashed diagonal line indicates the perfect prediction of the ideal model. The solid black line represents the performance of the nomogram, and the closer the fit to the diagonal line, the more accurate the prediction. The gray dashed line represents the performance of the model trained after bootstrapping validation (1,000 bootstrap resamples), which corrects the overfitting situation; (C,F) DCA analysis of the nomogram in the training and validation sets. The y-axis represents the net benefit, the x-axis represents the threshold probability. The red line represents the nomogram, and the blue and orange lines represent the all-patient treatment scenario and the no-patient treatment scenario, respectively. Abbreviations: ROC, receiver operating characteristic; AUC, area under the curve; DCA, decision curve analysis.

Figure 6

Kaplan-Meier curves for the length of stay of high-risk patients and low-risk patients based on the optimal segmentation threshold obtained from the ROC analysis in the training set (A) and the validation set (B). Abbreviations: m-LS: median length of stay.