Development of models for cervical cancer screening: construction in a cross-sectional population and validation in two screening cohorts in China

Abstract

Background Current methods for cervical cancer screening result in an increased number of referrals and unnecessary diagnostic procedures. This study aimed to develop and evaluate a more accurate model for cervical cancer screening. Methods Multiple predictors including age, cytology, high-risk human papillomavirus (hrHPV) DNA/mRNA, E6 oncoprotein, HPV genotyping, and p16/Ki-67 were used for model construction in a cross-sectional population including women with normal cervix (N = 1085), cervical intraepithelial neoplasia (CIN, N = 279), and cervical cancer (N = 551) to predict CIN2+ or CIN3+. A base model using age, cytology, and hrHPV was calculated, and extended versions with additional biomarkers were considered. External validations in two screening cohorts with 3-year follow-up were further conducted (NCohort-I = 3179, NCohort-II = 3082). Results The base model increased the area under the curve (AUC, 0.91, 95% confidence interval [CI] = 0.88–0.93) and reduced colposcopy referral rates (42.76%, 95% CI = 38.67–46.92) compared to hrHPV and cytology co-testing in the cross-sectional population (AUC 0.80, 95% CI = 0.79–0.82, referrals rates 61.62, 95% CI = 59.4–63.8) to predict CIN2+. The AUC further improved when HPV genotyping and/or E6 oncoprotein were included in the base model. External validation in two screening cohorts further demonstrated that our models had better clinical performances than routine screening methods, yielded AUCs of 0.92 (95% CI = 0.91–0.93) and 0.94 (95% CI = 0.91–0.97) to predict CIN2+ and referrals rates of 17.55% (95% CI = 16.24–18.92) and 7.40% (95% CI = 6.50–8.38) in screening cohort I and II, respectively. Similar results were observed for CIN3+ prediction. Conclusions Compared to routine screening methods, our model using current cervical screening indicators can improve the clinical performance and reduce referral rates.

Using online search activity for earlier detection of gynaecological malignancy

“…The best performing online search-based model in users who engaged in health searches had an AUC of 0.82. This is comparable to other established cancer screening programs in place to detect cervical (HPV, AUC 0.87) and Breast (Mammography AUC 0.88) cancer 36,37 . An online search-based model would work continuously, assessing an individual's risk of disease in real-time.…”

“…Further research in behavioural psychology is needed to understand how best to manage these issues before it could be feasibly integrated into a pathway of care. This is the first study to demonstrate the potential role of online search data in facilitating the earlier detection of gynaecological cancer with a performance that is comparable (AUC 0.82) to established disease screening programs 36,37 . We have also established the feasibility and acceptability of utilising online search data for health screening, highlighting its potential application in other diseases.…”

Mathematical Modelling of Cervical Precancerous Lesion Grade Risk Scores: Linear Regression Analysis of Cellular Protein Biomarkers and Human Papillomavirus E6/E7 RNA Staining Patterns

“…In the first cohort, 42 cases were diagnosed as CIN 2+, with thirty-seven cases predicted to progress and five cases to not progress. In the second cohort, 28 cases were diagnosed as CIN 2+, with 11 cases predicted to progress and 17 cases to not progress [ 66 ]. Although this is a starting point for research using machine learning, our study demonstrates that machine–learning–based algorithms using input data from the expression levels of multiple biomarkers have potential for diagnosing and predicting disease progression [ 67 , 68 ] and consequently for solving health problems currently considered unsolvable, such as cancer.…”

Developing a predictive nomogram for colposcopists: a retrospective, multicenter study of cervical precancer identification in China

“…Clinical prediction models have been explored to predict cervical lesions, but few have been constructed for HSIL + predictions. Wu et al [ 24 ] created and validated a logistic regression model for support vector machine (SVM) learning based on a multicenter cohort study of cervical cancer screening in China. Likewise, Karakitsos et al [ 25 ] developed machine learning methods based on cytology, HPV status, E6/E7 mRNA test, and p16 immunostaining to build an algorithm to facilitate the classification of cervical intraepithelial neoplasia grade 2 or worse (CIN2+).…”