Risk factors for surgical site infection after percutaneous endoscopic lumbar discectomy

Abstract

The objective of this study was to investigate the risk factors associated with surgical site infection (SSI) after percutaneous endoscopic lumbar discectomy (PELD) in patients with lumbar disc herniation (LDH). A retrospective analysis was performed on a cohort of 335 patients who underwent PELD between January 2016 and January 2023. Data were derived from the Hospital Information System (HIS), and a comprehensive statistical assessment was performed using IBM SPSS Statistics version 25.0. Both univariate and multivariate logistic regression analyses assessed a range of risk determinants, such as age, body mass index (BMI), comorbidities, laboratory test parameters and surgery-related variables. The incidence of SSI after PELD was 2.7% (9/335). Univariate analysis highlighted BMI, diabetes mellitus, long-term corticosteroid consumption, surgical time and cerebrospinal fluid leakage as significant predictors of SSI. Multivariate logistic regression identified BMI, diabetes mellitus, long-term corticosteroid consumption, surgical time and cerebrospinal fluid leakage as significant risk factors for SSI after PELD. High BMI, diabetes mellitus, long-term corticosteroid consumption, long surgical time and postoperative cerebrospinal fluid leakage are predisposing factors for SSI in patients undergoing PELD. Precise interventions focused on such risk components, including careful preoperative assessment and strategic postoperative care, are essential to reduce the incidence of SSI and improve surgical efficacy.

Chronic kidney disease prediction using boosting techniques based on clinical parameters

by Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Saurav Mallik, Zhongming Zhao

Chronic kidney disease (CKD) has become a major global health crisis, causing millions of yearly deaths. Predicting the possibility of a person being affected by the disease will allow timely diagnosis and precautionary measures leading to preventive strategies for health. Machine learning techniques have been popularly applied in various disease diagnoses and predictions. Ensemble learning approaches have become useful for predicting many complex diseases. In this paper, we utilise the boosting method, one of the popular ensemble learnings, to achieve a higher prediction accuracy for CKD. Five boosting algorithms are employed: XGBoost, CatBoost, LightGBM, AdaBoost, and gradient boosting. We experimented with the CKD data set from the UCI machine learning repository. Various preprocessing steps are employed to achieve better prediction performance, along with suitable hyperparameter tuning and feature selection. We assessed the degree of importance of each feature in the dataset leading to CKD. The performance of each model was evaluated with accuracy, precision, recall, F1-score, Area under the curve-receiving operator characteristic (AUC-ROC), and runtime. AdaBoost was found to have the overall best performance among the five algorithms, scoring the highest in almost all the performance measures. It attained 100% and 98.47% accuracy for training and testing sets. This model also exhibited better precision, recall, and AUC-ROC curve performance.