Development of a machine learning-based prediction model for systemic inflammatory response syndrome after percutaneous nephrolithotomy and comparison with nomogram model

Abstract

Abstract The objective of this study was to develop and compare the performance of nomogram model and machine learning models for predicting the possibility of systemic inflammatory response syndrome (SIRS) following percutaneous nephrolithotomy (PCNL). We retrospectively reviewed the clinical data of 337 patients who received PCNL between May 2020 and June 2022. Eighty percent of the data were used as the training set, and the remaining data were used as the testing set. The nomogram and machine learning (ML) models were created using the training set and were validated using the testing set. Based on the areas under the receiver operating characteristic curve (AUC) and the calibration curve, we evaluated the predictive ability of the nomogram. The predictive performance of six machine learning models was determined by the AUC and accuracy. Multivariate logistic regression analysis revealed four independent risk factors associated with SIRS, including preoperative monocyte, serum fibrinogen, serum prealbumin, and preoperative SII. The above independent related factors were used as variables to construct the nomogram model. Among the six machine learning algorithms, the support vector machine (SVM) delivered the best performance with accuracy of 0.926, AUC of 0.952 [95% Confidence Interval (CI): 0.906–0.999], while the nomogram showed an AUC of 0.818. Compared with the nomogram model, the SVM model can provide more reliable prognostic information about the possibility of SIRS after PCNL, which can assist surgeons in clinical decision-making.