Efficient electrocardiogram generation based on cardiac electric vector simulation model.

Area of Science:

• Biomedical Engineering
• Computational Electrophysiology

Background:

• Traditional electrophysiological models for ECG generation are computationally inefficient and lack fidelity.
• Accurate ECG data is crucial for computer-aided diagnosis of myocardial infarction (MI).

Purpose of the Study:

• To introduce a novel Cardiac Electric Vector Simulation Model (CEVSM) for efficient and high-fidelity ECG generation.
• To utilize CEVSM for data augmentation to improve myocardial infarction (MI) diagnosis.
• To demonstrate the application of life system simulations in training medical big models.

Main Methods:

• Development of the Cardiac Electric Vector Simulation Model (CEVSM).
• Implementation of the self-adapting regression transformation matrix method (SRTM) for enhanced simulation fidelity and consistency.
• Application of CEVSM-generated ECG data for augmenting datasets for MI diagnosis.

Main Results:

• CEVSM significantly reduces computation time compared to traditional models.
• The SRTM method achieves high fidelity and consistency with gold standards in ECG simulations.
• Data augmentation using CEVSM-generated data enhances MI localization accuracy.

Conclusions:

• CEVSM offers an efficient and reliable method for generating ECG samples, suitable for data augmentation.
• The model advances the development of intelligent diagnostic systems for MI.
• Life system simulations show promise for training medical big models.