Lu Liu,1 Jing Li,2 Xu Qiao,3 Wei Chen,4 Youzhong Zhang,5 Ping Zhang1 

1Department of Obstetrics and Gynecology, The Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, 250012, People’s Republic of China; 2Department of Obstetrics and Gynecology, Yidu Central Hospital of Weifang, Weifang, People’s Republic of China; 3School of Control Science and Engineering, Shandong University, Jinan, 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; 5Department of Obstetrics and Gynecology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, 250012, People’s Republic of China

Correspondence: Ping Zhang, Department of Obstetrics and Gynecology, The Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, 250012, People’s Republic of China, Email zp17660082377@163.com Youzhong Zhang, Department of Obstetrics and Gynecology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, 250012, People’s Republic of China, Email zhangyouzhong@sdu.edu.cn

Purpose: This study aimed to identify reliable risk factors for the development of Vaginal intraepithelial neoplasia (VaIN) within two years after the conization for high-grade squamous intraepithelial lesions (HSIL). We developed a prediction model to predict the risk of VaIN based on preoperative and follow-up data.
Methods: We collected 5358 patients who underwent conization for HSIL, of whom 99 developed VaIN within two years after conization. We selected 495 patients as the control group by randomly pairing them 1:5, and were randomly divided into development and validation cohorts at a ratio 7:3. Random Forest (RF), Lasso, and Extreme Gradient Boosting (XGBoost) were employed to identify the most influential variables in the model development dataset. The optimal variables selected through this process were then used for model construction. Subsequently, four machine learning models were developed, and their performance was evaluated using metrics including sensitivity, specificity, accuracy, area under the curve (AUC), and the F1 score. To enhance interpretability, the prediction process was visualized using Shapley Additive Explanations (SHAP). Finally, the model was deployed as a web-based clinical decision support system for practical clinical applications.
Results: Five key clinical predictive variables were identified: age, transformation zone (TZ) type, presence of VaIN before conization, follow-up cytology after conization, and follow-up HPV after conization. The optimal model demonstrated strong predictive performance, achieving AUC of 0.910 (95% CI: 0.854– 0.966) in the internal validation cohort and 0.905 (95% CI: 0.859– 0.951) in the external validation cohort.
Conclusion: We established a practical and accurate prediction model deployed in the network application to predict the occurrence of VaIN within two years after conization in patients with HSIL. This tool can facilitate targeted clinical decision-making for clinicians.

Keywords: conization after HSIL, VaIN, practical model, machine learning