Nomogram Predicting the Likelihood of Parametrial Involvement in Early-Stage Cervical Cancer: Avoiding Unjustified Radical Hysterectomies.

Background: We aimed to establish a tool predicting parametrial involvement (PI) in patients with early-stage cervical cancer and select a sub-group of patients who would most benefit from a less radical surgery. Methods: We retrospectively reviewed patients from two prospective multicentric databases-SENTICOL I and II-from 2005 to 2012. Patients with early-stage cervical cancer (FIGO 2018 IA with lympho-vascular involvement to IIA1), undergoing radical surgery (hysterectomy or trachelectomy) with bilateral sentinel lymph node (SLN) mapping with no metastatic node or PI on pre-operative imaging, were included. Results: In total, 5.2% patients (11/211) presented a histologic PI. After univariate analysis, SLN status, lympho-vascular space invasion, deep stromal invasion and tumor size were significantly associated with PI and were included in our nomogram. Our predictive model had an AUC of 0.92 (IC95% = 0.86-0.98) and presented a good calibration. A low risk group, defined according to the optimal sensitivity and specificity, presented a predicted probability of PI of 2%. Conclusion: Patients could benefit from a two-step approach. Final surgery (i.e. radical surgery and/or lymphadenectomy) would depend on the SLN status and the probability PI calculated after an initial conization with bilateral SLN mapping.