Diagnostic performance of machine learning in systemic infection following percutaneous nephrolithotomy and identification of associated risk factors

Pengju Li; Yiming Tang; Qinsong Zeng; Chengqiang Mo; Nur Ali; Baohua Bai; Song Ji; Yubing Zhang; Junhang Luo; Hui Liang; Rongpei Wu

doi:10.1016/j.heliyon.2024.e30956

Diagnostic performance of machine learning in systemic infection following percutaneous nephrolithotomy and identification of associated risk factors

Heliyon. 2024 May 9;10(10):e30956. doi: 10.1016/j.heliyon.2024.e30956. eCollection 2024 May 30.

Authors

Pengju Li¹, Yiming Tang², Qinsong Zeng¹, Chengqiang Mo¹, Nur Ali¹, Baohua Bai¹, Song Ji¹, Yubing Zhang¹, Junhang Luo^{1

3}, Hui Liang⁴, Rongpei Wu¹

Affiliations

¹ Department of Urology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, PR China.
² Department of Urology, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, PR China.
³ Institute of Precision Medicine, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, PR China.
⁴ Department of Urology, Affiliated Longhua People's Hospital, Southern Medical University, Shenzhen, PR China.

Abstract

Objective: This study aims to investigate the predictive performance of machine learning in predicting the occurrence of systemic inflammatory response syndrome (SIRS) and urosepsis after percutaneous nephrolithotomy (PCNL).

Methods: A retrospective analysis was conducted on patients who underwent PCNL treatment between January 2016 and July 2022. Machine learning techniques were employed to establish and select the best predictive model for postoperative systemic infection. The feasibility of using relevant risk factors as predictive markers was explored through interpretability with Machine Learning.

Results: A total of 1067 PCNL patients were included in this study, with 111 (10.4 %) patients developing SIRS and 49 (4.5 %) patients developing urosepsis. In the validation set, the risk model based on the GBM protocol demonstrated a predictive power of 0.871 for SIRS and 0.854 for urosepsis. Preoperative and postoperative platelet changes were identified as the most significant predictors. Both thrombocytopenia and thrombocytosis were found to be risk factors for SIRS or urosepsis after PCNL. Furthermore, it was observed that when the change in platelet count before and after PCNL surgery exceeded 30*109/L (whether an increase or decrease), the risk of developing SIRS or urosepsis significantly increased.

Conclusion: Machine learning can be effectively utilized for predicting the occurrence of SIRS or urosepsis after PCNL. The changes in platelet count before and after PCNL surgery serve as important predictors.

Keywords: Machine learning; PCNL; SIRS; Urosepsis.