Fig. 4

The performance of the optimal cutoff values determined by the T-cell model, NK cell model, and CD8 + T-cell model in predicting natural HPV clearance. We calculated the risk scores for predicting natural HPV clearance using the T-cell model, NK cell model, and CD8 + T-cell model (a-c) and plotted risk factor plots based on these risk scores. These plots include risk score ranking (top), HPV infection status (middle), and heatmaps of T-cell percentage, NK cell percentage, and CD8 + T-cell percentage (bottom). The optimal cutoff values determined by ROC analysis divided patients into high-risk and low-risk groups for natural HPV clearance. Kaplan‒Meier curves and log-rank tests were used to analyze the differences in natural HPV clearance between the high-risk and low-risk groups (d represents the T-cell model, e represents the NK cell model, f represents the CD8 + T-cell model). Time-dependent ROC curves were used to evaluate the accuracy of binary classification based on the optimal cutoff values in predicting HPV clearance (g represents T-cell model, h represents NK cell model, i represents CD8 + T-cell model). ROC, receiver operating characteristic; AUC, area under the curve; CI, confidence interval; HR, hazard ratio