A New Model for the Prediction of Intramyocardial Hemorrhage in ST-Segment Elevation Myocardial Infarction Patients After Emergency Percutaneous Coronary Intervention.

Background: Intramyocardial hemorrhage (IMH) after emergency percutaneous coronary intervention (PCI) in ST-segment elevation myocardial infarction (STEMI) patients is a significant predictor of major adverse cardiovascular events. However, current research lacks a simple and visual predictive model for IMH occurrence.

Aims: Our study aims to construct a Nomogram model to predict IMH occurrence.

Methods: Patients with STEMI who underwent PCI at Yichang Central People's Hospital from August 2023 to September 2024 and had CMR 2-10 days post-PCI were included. They were divided into IMH and Non-IMH groups. Risk factors for IMH were identified using Random Forest, single-factor, and multifactor Logistic regression analyses. The constructed nomogram prediction model was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and clinical decision analysis (DCA) curves. Bootstrap resampling was used for internal validation.

Results: IMH occurred in 43 patients (Non-IMH:53). Ischemic time, preoperative CK-MB level, and preoperative Myo level were identified as independent risk factors for IMH, while RCA occlusion was a protective factor. A nomogram model based on these four variables was established to predict the risk of IMH occurrence. The model's ROC curve had an area under the curve (AUC) of 0.865, indicating excellent discriminative ability; the calibration curve had a good fit (p = 0.16); the DCA curve showed high clinical applicability. After internal validation, the AUC of the ROC curve was 0.873 (95% CI:0.754-0.921).

Conclusion: The Nomogram model constructed based on four clinical risk factors has good predictive value and clinical applicability, providing an effective reference for predicting the risk of IMH occurrence in STEMI patients after PCI.