Maodan Huang,1 Xiaohong Chen,1 Xin Lin,1 Yuxiang Yang,1 Lu Liu,2 Youzhong Zhang,3 Ronglong Wang,1 Wei Chen4 

1Department of Obstetrics and Gynecology, Zhangzhou Affiliated Hospital of Fujian Medical University, Zhangzhou, 363000, People’s Republic of China; 2Department of Obstetrics and Gynecology, The Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, 250033, People’s Republic of China; 3Department of Obstetrics and Gynecology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, 250012, People’s Republic of China; 4School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai’an, 271016, People’s Republic of China

Correspondence: Ronglong Wang, Department of Obstetrics and Gynecology, Zhangzhou Affiliated Hospital of Fujian Medical University, Zhangzhou, 363000, People’s Republic of China, Email earthfire1999@163.com Wei Chen, School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai’an, 271016, People’s Republic of China, Email chenwei9320@sdfmu.edu.cn

Objective: The implementation of comprehensive microinvasive cervical cancer (MIC) risk assessment in high-grade squamous intraepithelial lesion (HSIL) patients undergoing loop electrosurgical excision procedure (LEEP) is critical to optimize treatment strategies and improve patient outcomes.
Methods: From March 2017 to January 2024, a total of 3066 eligible patients with HSIL were retrospectively enrolled from two hospitals and assigned into one training cohort (n = 2084), one internal validation cohort (579) and one external testing cohort (n = 403). Four feature selection methods (Random Forest, Lasso regression, Boruta algorithm, and Extreme Gradient Boosting) were employed to identify key predictive factors from the training cohort. Then, four machine learning models were developed and evaluated using comprehensive metrics. The optimal model was visualized through interpretable techniques and operationalized as a web-based clinical decision support system for real-world implementation.
Results: Six clinical predictive variables were identified, including surgical margins, endocervical curettage (ECC), TCT status, HPV status, Transformation Zone (TZ) type and Age. The optimal model demonstrated good predictive performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.822 (95% CI: 0.793– 0.852) in the internal validation cohort and 0.802 (95% CI: 0.730– 0.874) in the external validation cohort.
Conclusion: The machine learning-based model can accurately assess the risk of MIC during the treatment of HSIL with LEEP, potentially aiding in the selection of appropriate treatment and surveillance strategies in clinical practice.

Keywords: high-grade squamous intraepithelial lesions, microinvasive cervical cancer, interpretable machine learning, visualization, prediction model