OBJECTIVES: To develop risk prediction models for postoperative hypothermia after transurethral holmium laser enucleation of the prostate (HoLEP) using machine learning algorithms. METHODS: We retrospectively analyzed the clinical data of 403 patients from our center (283 patients in the training set and 120in the internal validation set) and 120 patients from Weifang People's Hospital (as the external validation set). The risk prediction models were built using logistic regression, decision tree and support vector machine (SVM), and model performance was evaluated in terms of accuracy, recall, precision, F1 score and AUC. RESULTS: Operation duration, prostate weight, intraoperative irrigation volume, and being underweight were identified as the predictors of postoperative hypothermia following HoLEP. Among the 3 algorithms, SVM showed the best precision rate and accuracy in all the 3 data sets and the best area under the ROC (AUC) in the training set and validation set, followed by logistic regression, which had a similar AUC in the two data sets. SVM outperformed logistic regression and decision tree models in the validation set in precision, accuracy, recall, F1 score, and AUC, and performed well in the external validation set with better precision rate and accuracy than logistic regression and decision tree models but slightly lower recall rate, F1 index, and AUC value than the decision tree model. SVM outperformed logistic regression and decision tree models in precision, accuracy, F1 score, and AUC in the training set, but had slightly lower recall rate than the decision tree. CONCLUSIONS Among the 3 models, SVM has the best performance and generalizability for predicting post-HoLEP hypothermia risk to provide support for clinical decisions.
Humans ; Male ; Retrospective Studies ; Machine Learning ; Transurethral Resection of Prostate/adverse effects* ; Hypothermia/etiology* ; Prostatic Hyperplasia/surgery* ; Algorithms ; Lasers, Solid-State ; Risk Assessment ; Postoperative Complications ; Decision Trees ; Logistic Models ; Aged ; Middle Aged ; Support Vector Machine

OBJECTIVES: Postoperative hypothermia is a common clinical complication with a high incidence rate, potentially adversely affecting postoperative recovery. Transurethral holmium laser enucleation of the prostate (HoLEP) is a minimally invasive procedure for benign prostatic hyperplasia (BPH). Offering advantages such as minimal bleeding, broad indications, and rapid postoperative recovery. However, research on risk factors for postoperative hypothermia following HoLEP remains limited, and predictive models for guiding clinical practice are lacking. This study aims to develop a predictive model for assessing the risk of postoperative hypothermia in HoLEP patients and to identify relevant risk factors. METHODS: Clinical data from patients who underwent HoLEP at affiliated Hospital of Shandong Second Medical University were retrospectively collected. Patients were categorized into a hypothermia group and a non-hypothermia group based on whether postoperative hypothermia occurred. Preoperative, intraoperative, and postoperative indicators were compared between the 2 groups. Least absolute shrinkage and selection operator (LASSO) regression combined with logistic regression analysis was used to analyze clinical data. A predictive model for assessing the risk of postoperative hypothermia after HoLEP was constructed and internally validated using bootstrap resampling. RESULTS: A total of 403 patients were included in the analysis, among whom 85 patients developed postoperative hypothermia, with an incidence rate of 21.1%. Logistic regression analysis identified operative duration (OR=1.009, 95% CI 1.003 to 1.015), underweight status (OR=9.881, 95% CI 4.038 to 24.910), and prostate weight (OR=1.021, 95% CI 1.012 to 1.030) as independent risk factors for postoperative hypothermia, and these variables were incorporated into the nomogram model. Internal validation showed strong discriminative ability of the nomogram, with an area under the receiver operating characteristic curve (AUC) of 0.755 (95% CI 0.686 to 0.820) and a C-index of 0.832 (95% CI 0.787 to 0.865). The calibration curve demonstrated good consistency between predicted and observed outcomes. Decision curve analysis showed that the nomogram provided greater clinical utility when the risk threshold for postoperative hypothermia was between 8% and 97%. CONCLUSIONS This study developed a nomogram model for predicting the risk of postoperative hypothermia in HoLEP patients, providing clinicians with a simple and effective predictive tool for individualized risk assessment and preoperative decision-making.
Humans ; Male ; Nomograms ; Prostatic Hyperplasia/surgery* ; Lasers, Solid-State/adverse effects* ; Risk Factors ; Retrospective Studies ; Transurethral Resection of Prostate/methods* ; Postoperative Complications/epidemiology* ; Hypothermia/epidemiology* ; Middle Aged ; Aged

Objective To investigate the effects of combination of propofol and whole-body hypoxic preconditioning on lung ischemia-reperfusion(I/R)injury in rats and the mechansim involved.Methods Ninety male SD rats weighing 250-320 g,were randomly divided into 5 groups(n=18 each): sham operation group(group S),lung I/R group(group I/R),propofol preconditioning group(group P),whole-body hypoxic preconditioning group(group WBHP),and combination of propofol and whole-body hypoxic preconditioning group(group PW).The animals were anesthetized with intraperitoneal 3% pentobarbital 30 mg/kg,tracheostomized and mechanically ventilated.Lung I/R injury was produced by occlusion of hilum of the left lung for 45 min followed by reperfusion.Propofol was continuously infused iv at 30 mg·kg-1·h-1 30 min before ischemia in group P.In group WBHP,5 times of WBHP were performed before ischemia.In group PW,propofol was infused iv at 30 mg· kg-1·h- 1 and 5 times of WBHP were performed 30 min before ischemia.Six rats from each group were killed at 30 min,1 h,and 4 h of reperfusion(T1-3).The lungs were then removed for determination of the contents of TNF-α,IL-1,IL6 and MDA,and activities of SOD.The W/D lung weight ratio was calculated.Results Compared with group S,the contents of TNF-α,IL-1,IL-6 and MDA and W/D ratio were significantly increased at T1-3,and SOD activity was significantly decreased at T1-3 in the other four groups(P＜0.05).The contents of TNF-α,IL-1,IL-6 and MDA and W/D ratio were significantly lower at T1-3 ,and SOD activity was significantly higher at T1-3 in group P,WBHP and PW than in group I/R(P ＜ 0.05).The contents of TNF-α and IL-6 and W/D ratio at T2,3 and contents of IL-1 and MDA at T3 were significantly lower,and SOD activity was significantly higher at T2,3 in group PW than in group P and WBHP(P＜0.05).There was no significant difference in the parameters metioned above between group P and WBHP(P＞0.05).Conclusion The combination of propofol and WBHP can protect the lungs from I/R injury,the efficacy is better than that of either of them alone,and it may be related to the enhancement in the inhibiton of inflammatory reaction and improvement in the antioxidant effect.