Related Experiment Video
Updated: Jul 6, 2025
Establishing a Competing Risk Regression Nomogram Model for Survival Data
Published on: October 23, 2020
Development and validation of a nomogram for predicting the risk of poor prognosis in patients with cerebral
Zhenfeng Chen1, Lixiang Zhang2, Rui Li3
1Department of Continuation Care Center, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230036, China.
Objective:
To identify factors related to poor prognosis in patients with cerebral infarction (CI) and to construct and validate a personalized prediction model based on these factors.
Methods:
A retrospective analysis was conducted on the clinical and follow-up data of 857 patients with CI who were diagnosed in the neurology department of a tertiary A hospital in Anhui Province, China from April 2020 to March 2022. Based on follow-up data and the Modified Rankin Scale (mRS) score one year after discharge, patients were divided into a good prognosis group (793 cases, mRS ≤2) and a poor prognosis group (64 cases, mRS >2). Multivariate logistic regression analysis was used to identify independent risk factors, which were then used to establish a nomogram model. The predictive performance of the model was evaluated using the area under the receiver operating characteristic curve (ROC, AUC), and the calibration curve was used to evaluate the calibration of the nomogram.
Results:
There was a statistically significant difference in the distribution of eight variables between the groups, including post-discharge use of biguanide hypoglycemic drugs, insulin, systolic blood pressure, exercise status, alcohol consumption, smoking status, age, and gender (P < 0.05). Multivariate logistic regression analysis suggested that gender, smoking after discharge, alcohol consumption, lack of exercise, and oral administration of biguanide hypoglycemic drugs are independent risk factors for poor prognosis in patients with CI (P < 0.05). The personalized poor prognosis nomogram constructed based on these five predictive factors showed good discriminative ability and predictive stability, with AUCs of 0.768 (95 % CI: 0.712-0.825) and 0.775 (95 % CI: 0.725-0.836) before and after internal validation, respectively. The calibration curve confirmed the accuracy and consistency of the nomogram (P = 0.956).
Conclusion:
Female gender, smoking, alcohol consumption, lack of exercise, and post-discharge use of biguanide hypoglycemic drugs are independent risk factors for poor prognosis in patients with CI. The constructed nomogram shows good predictive efficiency for post-discharge prognosis and can help in clinical decision-making.
