Multi-center-validated machine learning model for cervical cancer based on human papillomavirus genotyping…

AI / informaticsInternational journal of gynecological cancer : official journal of the International Gynecological Cancer Society· Jun 2026

Multi-center-validated machine learning model for cervical cancer based on human papillomavirus genotyping results.

Ziren Chen, Yihui Zeng, Lingxiao Luo … Qing Cong

Read paper

PathologyAI / informaticsDiagnosisQ1IF 3.5

Artificial Intelligence-guided screening could cut colposcopy referrals 14.3% while keeping 96.8% sensitivity

Multi-center-validated machine learning model for cervical cancer based on human papillomavirus genotyping results.

Ziren Chen … Qing Cong

International journal of gynecological cancer · Jun 2026

Background

Cervical cancer remains a leading cause of gynecologic cancer-related mortality worldwide, with human papillomavirus (human papillomavirus) testing being a key screening tool.

Purpose

This study aimed to develop and validate a machine learning model to predict cervical intra-epithelial neoplasia grade (CIN) 2 or worse (CIN2+) using human papillomavirus genotyping, cytology results, and patient age.

Methods

A retrospective analysis was conducted using data from 52,063 patients (61,022 clinical records) from the Obstetrics and Gynecology Hospital of Fudan University, Shanghai, collected between October 2017 and June 2023.

n = 52,063 patients

Results

14.3%

Artificial Intelligence screening lowers colposcopy referrals while catching nearly all CIN2+ cases

n = 52,063 patients

More results

Among the models, CatBoost achieved the highest area under the curve (0.917) in internal validation, with an accuracy of 86% and sensitivity of 78% for CIN2+.

More results

External validation confirmed robust performance: 89% accuracy (Obstetrics and Gynecology Hospital of Fudan University), and 78% (Xiamen Maternal and Child Health Hospital), and 80% (Jinan Maternal and Child Health Hospital).

A user-friendly tool (www.cervixcare.cn) was developed to provide individualized CIN2+ risk scores based on input variables.

“

Conclusion

This multi-center-validated model enables precise risk stratification by accounting for human papillomavirus genotype-specific pathogenicity, improving clinical decision-making for cervical cancer screening and management.

Multi-center-validated machine learning model for cervical cancer based on human papillomavirus genotyping results.

Multi-center-validated machine learning model for cervical cancer based on human papillomavirus genotyping results.

Related papers