Clinical and Virological Profiles Associated with CINTEC® PLUS Positivity: A Data-Driven Clustering and Modeling Study

<b>Background/Objectives</b>: The diagnostic performance of CINtec^® PLUS can be influenced by numerous patient characteristics and risk factors. The aim of this retrospective study was to evaluate and model the risk factors associated with CINtec^® PLUS test positivity in patients undergoing cervical cancer screening and to assess their predictive performance for the prediction of cervical intraepithelial neoplasia (CIN) 2/3 using an unsupervised machine learning-based model. <b>Methods</b>: Medical data of 134 patients with human papillomavirus (HPV) infection who underwent CINtec^® PLUS testing were used to model the impact of risk factors on dual-stain cytology positivity and to evaluate the predictive performance for CIN2/3. <b>Results</b>: The gradient boosting classifier for the prediction of CINtec^® PLUS positivity using clinical risk factors had a precision of 75%, an overall accuracy of 0.62, and an area under the curve (AUC) value of 0.77. Body mass index and age were the most important variables in this model. HSIL, ASC-US, and other high-risk HPV strains increased the likelihood of a positive outcome. Overall AUC values for a positive test alone were 0.74 and 0.69 for CIN2 and CIN3 prediction, respectively. For CIN2 prediction, the XGBoost model performed well, with 71% sensitivity, 85% specificity, and an AUC value of 0.90. However, the model had 96% sensitivity, 25% specificity, and 0.58 AUC for CIN3 prediction. <b>Conclusions</b>: Patient characteristics and risk factors can influence CINtec^® PLUS positivity rates and they need to be carefully considered before choosing a specific management.