694 Cervical cancer application (CER-CAP): a new App for estimation of the lymph nodal risk invasion in patients with early-stage cervical cancer

Abstract

<h3>Introduction/Background*</h3> Lymph node status is a major prognostic factor in early-stage cervical cancer. According to the International Federation of Gynecology and Obstetrics (FIGO) 2018 classification, the presence of metastatic lymph node involvement, including the presence of macrometastasis (MAC) or micrometastasis (MIC), is classified as stage IIIC. The recommended treatment is a combination of chemoradiation without complete surgery. Assigning initial staging of patients is therefore essential for the therapeutic management. <h3>Methodology</h3> We performed a secondary analysis of data from two prospective multicenter trials assessing the role of the sentinel node in the surgical management of cervical cancer (SENTICOL 1 and 2 pooled together in the training dataset). The histological risk factors were included in a multivariate logistic regression model in order to determine the most suitable prediction model. An internal validation of the chosen prediction model was then carried out by a cross validation of the ‘leave one out cross validation’ type. The prediction model implemented into an interactive online application of the ’Shinyapp’ type. Finally, an external validation was performed with a retrospective cohort of L’Hôtel-Dieu de Québec in Canada. <h3>Result(s)*</h3> Three hundred twenty-one patients participating in Senticol 1 and 2 were included in our training analysis. Among these patients, 280 did not present lymph node invasion (87.2%), 13 presented ITC (4%), 11 presented MIC (3.4%) and 17 MAC (5.3%). Tumor size, presence of lymph-vascular space invasion and stromal invasion were included in the prediction model. The Receiver Operating Characteristic (ROC) Curve from this model had an area under the curve (AUC) of 0.79 (95% CI [0.69 – 0.90]). The AUC ROC curve from the cross validation was 0.63. The external validation on the Canadian cohort confirmed a good discrimination of the model with AUC ROC of 0.83. <h3>Conclusion*</h3> This study is the first study of a prediction score for lymph node involvement in early-stage cervical cancer that includes internal and external validation of a prediction score for lymph node involvement in early-stage cervical cancer. The web application is a simple, practical, and modern method of using this prediction score in clinical management. Link of the CER-CAP: https://thomas-gaillard.shinyapps.io/senticol_n_pred/?_ga=2.9061948.842752796.1621805282-1130361826.1585828032