Related Experiment Video
Updated: Sep 12, 2025
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
Prognosis risk stratification in patients with cervical adenocarcinoma after surgery: Development and validation of
1Department of Radiology, Hunan Cancer Hospital, The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, Hunan, China.
Aims:
Currently, there is a lack of prognostic assessment tools for cervical adenocarcinoma (CAC). To develop a prognostic tool for patients with CAC after surgery, we innovatively integrated radiomic features from contrast-enhanced computed tomography (CECT) images, clinicopathologic variables, and DNA methylation data.
Materials And Methods:
We retrospectively collected the clinical and imaging data of patients with CAC. Pre-, post-, and fusion radiomic models were constructed using a support-vector-machine classifier. Clinical, radiomic features, and DNA methylation data were integrated to develop the combined model. Model performance for the prediction of progression-free survival was evaluated using Harrell' concordance index (C-index). Kaplan-Meier curves were used to show the survival difference between high- and low-risk groups stratified by the models.
Results:
A total of 127 CAC patients (training cohort, n=86; validation cohort, n=41) were included. In the validation cohort, the clinical model based on chemoradiotherapy and invasion depth achieved a C-index of 0.811 (95%CI: 0.784-0.838). The pre-contrast, post-contrast, and fusion radiomic models yielded a C-index of 0.745 (95%CI: 0.688-0.802), 0.723 (95%CI: 0.668-0.778), 0.757 (95%CI: 0.708-0.806), respectively. The combined model based on chemoradiotherapy, ZNF582, and post-contrast radiomic features obtained the highest C-index of 0.872 (95%CI: 0.835-0.909). The Kaplan-Meier curves display that the high-risk patients had significantly shorter PFS compared to the low-risk patients (all P<0.05).
Conclusions:
The combined model can be used as a prognosis stratification tool for patients with CAC, which can facilitate disease monitoring and clinical decision-making.
