Development and Validation of Prediction Models for the Prognosis of Clear Cell Adenocarcinoma of the Cervix: A Population‐Based Cohort Study
ABSTRACT
Aims
Clear cell adenocarcinoma of the cervix (CCAC) is a rare and aggressive malignancy with poor prognosis. This study aimed to develop and validate nomograms and risk‐stratification scores for predicting overall survival (OS) and cancer‐specific survival (CSS) in CCAC patients.
Methods
Data from 429 CCAC patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database (2000–2019). Patients were randomly assigned to training and validation sets. Cox regression analysis identified five independent prognostic factors for OS and CSS, which were used to construct nomograms for predicting 1‐, 3‐, and 5‐year OS and CSS. The models were evaluated using receiver operating characteristic (AUC) analysis, calibration curves, and decision curve analysis (DCA). The clinical utility of the nomograms was compared with the 2018 FIGO Stage System using C‐index, NRI, and IDI. Patients were stratified into low‐ and high‐risk groups based on predicted risk scores, and Kaplan–Meier survival analysis was performed.
Results
Multivariate Cox regression identified age at diagnosis, tumor size, and surgery as independent prognostic factors for both OS and CSS, while chemotherapy and radiotherapy were specifically associated with OS and CSS. The C‐index for OS and CSS in the training set was 0.83 and 0.84, respectively. The AUC for 1‐, 3‐, and 5‐year OS and CSS in the training set was 0.95, 0.95, and 0.88, respectively, with similar results in the validation set. Calibration curves showed good agreement between predicted and actual outcomes. DCA, NRI, and IDI analyses indicated that the nomogram outperformed the 2018 FIGO Stage System. Survival analysis revealed that high‐risk patients had worse prognosis compared to low‐risk patients.
Conclusion
This study developed and validated nomograms for predicting OS and CSS in CCAC patients using SEER data. These models offer a more accurate prognostic tool, enhancing clinical decision‐making and enabling individualized treatment planning.