Multicenter Validated Machine Learning Model for Cervical Cancer Based on HPV Genotyping Results

<h2>Abstract</h2><h3>Objective</h3> Cervical cancer remains a leading cause of gynecological cancer-related mortality globally, with human papillomavirus (HPV) testing being a key screening tool. However, current guidelines often categorize high-risk HPV (hrHPV) types broadly, overlooking their varying oncogenic potentials. This study aimed to develop and validate a machine learning model to predict cervical intraepithelial neoplasia grade 2 or worse (CIN2+) using HPV genotyping, cytology results, and patient age. <h3>Methods</h3> A retrospective analysis was conducted using data from 52,063 patients (61,022 clinical records) from the Obstetrics and Gynecology Hospital of Fudan University (OGHFU), Shanghai, collected between October 2017 and June 2023. Clinical data included HPV genotyping, cytology results, and histopathological diagnoses. Six machine learning algorithms (logistic regression, decision tree, random forest, Support Vector Machine-Radial Basis Function, XGBoost, and CatBoost) were compared, with performance evaluated using AUC, accuracy, sensitivity, and F1-score. The optimal model was validated using a temporal cohort from OGHFU and external cohorts from Xiamen Maternal and Child Health Hospital and Jinan Maternal and Child Health Hospital. <h3>Results</h3> Among the models, CatBoost achieved the highest AUC (0.917) in internal validation, with an accuracy of 86% and sensitivity of 78% for CIN2+. External validation confirmed robust performance: 89% accuracy (OGHFU), 78% (XMFYBJ), and 80% (JNFYBJ). Simulation analysis indicated that the AI-guided strategy could reduce colposcopy referrals by 14.3% while maintaining 96.8% sensitivity and an exceptional Negative Predictive Value of 99.18%. A user-friendly tool (www.cervixcare.cn) was developed to provide individualized CIN2+ risk scores based on input variables. <h3>Conclusion</h3> This multicenter-validated model enables precise risk stratification by accounting for HPV genotype-specific pathogenicity, improving clinical decision-making for cervical cancer screening and management.