Development and Validation of a Nomogram Model for the Risk of Cardiac Death in Patients Treated with Chemotherapy for Esophageal Cancer

The primary cause of mortality in esophageal cancer survivors is cardiac death. Early identification of cardiac mortality risk during chemotherapy for esophageal cancer is crucial for improving the prognosis. We developed and validated a nomogram model to identify patients with high cardiac mortality risk after chemotherapy for esophageal cancer for early screening and clinical decision-making. We randomly allocated 37,994 patients with chemotherapy-treated esophageal cancer into two groups using a 7:3 split ratio: model training (n = 26,598) and validation (n = 11,396). 5- and 10-year survival rates were used as endpoints for model training and validation. Decision curve analysis and the consistency index (C-index) were used to evaluate the model's net clinical advantage. Model performance was evaluated using receiver operating characteristic curves and computing the area under the curve (AUC). Kaplan-Meier survival analysis based on the prognostic index was performed. Patient risk was stratified according to the death probability. Age, surgery, sex, and year were most closely related to cardiac death and used to plot the nomograms. The C-index for the training and validation datasets were 0.669 and 0.698, respectively, indicating the nomogram's net clinical advantage in predicting cardiac death risk at 5 and 10 years. The 5- and 10-year AUCs were 0.753 and 0.772 for the training dataset and 0.778 and 0.789 for the validation dataset, respectively. The accuracy of the model in predicting cardiac death risk was moderate. This nomogram can identify patients at risk of cardiac death after chemotherapy for esophageal cancer at an early stage.

Automated summary

This study developed and validated a nomogram model to identify esophageal cancer patients at high risk of cardiac death after chemotherapy. The model's accuracy in predicting cardiac death risk was moderate, and it can be used for early screening and clinical decision-making.