Development and validation of a simple-to-use nomogram for predicting minimal change disease based on quantification of color Doppler sonography data from a region of interest.

Abstract

To establish a simple-to-use nomogram based on quantification of color Doppler sonography data from a region of interest (ROI) to diagnose minimal change disease (MCD) promptly and non-invasively, and to evaluate the prediction capability of the nomogram. We recruited 564 patients with pathology-proven renal disease who were admitted to our hospital from July 2020 to July 2021 (388 patients in the training dataset and 176 patients in the validation dataset), and their color Doppler sonography data were acquired from a ROI and underwent ipsilateral renal biopsy. The collected clinical features and ultrasonic features were imported into Rstuido and statistically significant features were selected by stepwise regression using the forward-backward method. Multivariate Logistic regression analysis was combined with clinical analysis to obtain the final modeling features. General and dynamic nomogram models were constructed with the selected features, depending on whether they were MCD or not. Bootstrapping and internal validation were used for internal and external validation of the nomogram, respectively. The performance of the nomogram was assessed by C-index, calibration curve, and receiver operating characteristic (ROC) curve. Age and VI were independent factors in predicting MCD. The value of Age (Best cut-off value: 33.5years) combined with VI (Best cut-off value: 40.50 points) in the diagnosis of MCD was significantly higher than that of single diagnosis (AUC 0.901, 95% CI 0.863-0.938). The C-index of the nomogram constructed with age and VI in the training and validation datasets was 0.915 [95% confidence interval (CI) 0.874-0.956 and 0.875 95% CI 0.783-0.967], respectively. Calibration curves were fitted well. The sensitivity, specificity, and accuracy were 76.1%, 95.6%, and 78.3%, respectively, in the training dataset, and 74.1%, 94.4%, and 76.1% in the validation dataset, respectively. The nomogram constructed with age and VI showed a satisfactory degree of differentiation and accuracy, which is of great significance for early, non-invasively, and individually analysis of the risk of MCD.