Related Experiment Video
Updated: Jun 18, 2025
Establishing a Competing Risk Regression Nomogram Model for Survival Data
Published on: October 23, 2020
Nomogram for Predicting the Risk of Short Sleep Duration in Myocardial Infarction Survivors
1First School of Clinical Medicine, Shanxi Medical University, 030000 Taiyuan, Shanxi, China.
Background:
Research on post-infarction insomnia, particularly short sleep duration following myocardial infarction (MI), remains limited. Currently, there are no existing guidelines or risk prediction models to assist physicians in managing or preventing short sleep duration or insomnia following MI. This study aims to develop a nomogram for predicting the risk of short sleep duration after MI.
Methods:
We conducted a retrospective study on 1434 MI survivors aged 20 and above, utilizing data from the National Health and Nutrition Examination Survey (NHANES) database spanning from 2007 to 2018. Among them, 710 patients were assigned to the training group, while 707 patients were allocated to the testing group. We utilized logistic regression, least absolute shrinkage and selection operator (LASSO) regression, and the elastic network for variable selection. The stability and accuracy of the prediction model were assessed using receiver operator characteristics (ROCs) and calibration curves.
Results:
We included five variables in the nomogram: age, poverty income ratio (PIR), body mass index (BMI), race, and depression. The ROC curves yielded values of 0.636 for the training group and 0.657 for the testing group, demonstrating the model's good prediction accuracy and robustness through a calibration curve test.
Conclusions:
Our nomogram can effectively predict the likelihood of short sleep duration in MI survivors, providing valuable support for clinicians in preventing and managing post-MI short sleep duration.
