Background: Exposure to high altitude increases the risk of myocardial ischemia (MI) and subsequent cardiovascular death. Nomogram is a graphical regression model, but there are no reports on using nomogram to predict myocardial ischemia under high altitude exposure. Our goal was to establish prediction models based on pre-high-altitude physical exposure examination data and identify key risk factors. Methods: We prospectively enrolled a total of 2,855 healthy individuals who underwent physical examination at the 920th Hospital of Joint Logistics Support Force and were scheduled to undergo high-altitude (3000–3500 m) training within six months. These participants were randomly divided into a training cohort (75%) and a validation cohort (25%). In the training set, single-factor analysis of variance and Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis were used to select variables, and two nomograms were established based on clinical features (CF) and clinical features + blood tests (CF + BT), respectively. The performance of the nomograms was evaluated using the area under the receiver operating characteristic curve (ROC), the concordance index (C-index), and calibration curves. Results: The C-index for the prediction models CF and CF + BT were 0.652 and 0.804, respectively. In the training cohort, the AUC for prediction models CF and CF + BT were 0.61 and 0.80, respectively. In the validation cohort, the AUC for prediction models CF and CF + BT were 0.61 and 0.81, respectively. Conclusion: We have successfully established two nomogram models to predict myocardial ischemia under high-altitude exposure and identified some risk factors.
Read full abstract