Prediction Model of Postoperative Severe Hypocalcemia in Patients with Secondary Hyperparathyroidism Based on Logistic Regression and XGBoost Algorithm

Objective. A predictive model was established based on logistic regression and XGBoost algorithm to investigate the factors related to postoperative hypocalcemia in patients with secondary hyperparathyroidism (SHPT). Methods. A total of 60 SHPT patients who underwent parathyroidectomy (PTX) in our hospital were retrospectively enrolled. All patients were randomly divided into a training set ( $n=42$ ) and a test set ( $n=18$ ). The clinical data of the patients were analyzed, including gender, age, dialysis time, body mass, and several preoperative biochemical indicators. The multivariate logistic regression and XGBoost algorithm models were used to analyze the independent risk factors for severe postoperative hypocalcemia (SH). The forecasting efficiency of the two prediction models is analyzed. Results. Multivariate logistic regression analysis showed that body mass ( $\text{OR}=1.203$ , $P=0.032$ ), age ( $\text{OR}=1.214$ , $P=0.035$ ), preoperative PTH ( $\text{OR}=1.026$ , $P=0.043$ ), preoperative Ca ( $\text{OR}=1.062$ , $P=0.025$ ), and preoperative ALP ( $\text{OR}=1.031$ , $P=0.027$ ) were positively correlated with postoperative SH. The top three important features of XGBoost algorithm prediction model were preoperative Ca, preoperative PTH, and preoperative ALP. The area under the curve of the logistic regression and XGBoost algorithm model in the test set was 0.734 (95% CI: 0.595~0.872) and 0.827 (95% CI: 0.722~0.932), respectively. Conclusion. The predictive models based on the logistic regression and XGBoost algorithm model can predict the occurrence of postoperative SH.