Related Experiment Video
Updated: Jun 20, 2025
Establishing a Competing Risk Regression Nomogram Model for Survival Data
Published on: October 23, 2020
Development of a novel dynamic nomogram for predicting overall survival in anaplastic thyroid cancer patients with
Liuhuan Wang1, Yanghua Rao1, Pengxing Lai1
1The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, China.
Background:
Anaplastic thyroid cancer (ATC) is highly invasive, prone to distant metastasis (DM), and has a very poor prognosis. This study aims to construct an accurate survival prediction model for ATC patients with DM, providing reference for comprehensive assessment and treatment planning.
Methods:
We extracted data of ATC patients with DM diagnosed between 2004 and 2019 from the SEER database, randomly dividing them into a training set and a validation set in a ratio of 7:3. Univariate and multivariate Cox regression analyses were sequentially performed on the training set to identify independent prognostic factors for overall survival (OS) and construct nomograms for 3-month, 6-month, and 8-month OS for ATC patients with DM based on all identified independent prognostic factors. Receiver operating characteristic (ROC) curve analysis, decision curve analysis (DCA) curve analysis, and calibration curves were separately plotted on the training and validation sets to demonstrate the model's performance. Furthermore, patients were stratified into high- and low-risk groups based on their risk scores, and the Kaplan-Meier (KM) survival curves were used to illustrate the survival differences between the two groups.
Results:
A total of 322 patients were included in this study. Univariate and multivariate Cox regression analyses identified five independent prognostic factors for OS in ATC patients with DM: surgery, tumor size, age, chemotherapy, and radiotherapy. Nomograms for 3-month, 6-month, and 8-month OS were established based on these factors. The training set AUC values (3-month AUC: 0.767, 6-month AUC: 0.789, 8-month AUC: 0.795) and validation set AUC values (3-month AUC: 0.753, 6-month AUC: 0.798, 8-month AUC: 0.806) as well as the calibration curves demonstrated excellent applicability and accuracy of the model. Additionally, the DCA curves indicated substantial clinical net benefit of the model. The KM curves also confirmed the model's excellent stratification ability for patient OS.
Conclusion:
The nomogram developed in this study accurately predicts OS for ATC patients with DM. It can assist clinicians in formulating appropriate treatment strategies for these patients.
