Establishment and validation of a prediction model for nonrecovery of left ventricular ejection fraction in acute...

Area of Science:

• Cardiology
• Clinical Research
• Predictive Modeling

Background:

• Acute myocardial infarction (AMI) with reduced left ventricular ejection fraction (LVEF) post-percutaneous coronary intervention (PCI) presents a significant clinical challenge.
• Identifying factors influencing LVEF recovery is crucial for patient management and prognosis.

Purpose of the Study:

• To investigate risk factors associated with the nonrecovery of LVEF in AMI patients treated with PCI.
• To establish and validate a predictive risk model for LVEF nonrecovery.

Main Methods:

• A predictive model was developed using least absolute shrinkage and selection operator (LASSO) regression.
• Patients were enrolled in model establishment and validation cohorts from a high-volume PCI center (December 2018 - December 2021).

Main Results:

• Cardiac troponin I, myoglobin, left ventricular end-diastolic dimension, multivessel disease, and no-reflow were significant predictors of LVEF recovery failure.
• The prediction model demonstrated moderate predictive ability (AUC 0.703 and 0.665) with good calibration and clinical utility.

Conclusions:

• A validated risk prediction model can effectively assess the likelihood of LVEF nonrecovery in AMI patients undergoing PCI.
• The model facilitates early identification of high-risk individuals, enabling timely intervention.