Design and Optimization Strategy of a CNN Aided Pre-hospital Diagnosis System for Myocardial Infarction

Myocardial Infarction (MI), commonly known as a heart attack, is a prevalent acute cardiovascular disease and one of the deadliest types of cardiovascular diseases in China. Electrocardiogram (ECG) serves as the primary tool for analysis and diagnosis, recording the heart’s electrical activity to detect abnormal patterns. ECG exhibits nonlinear and unstable characteristics, with its noise being random. Therefore, the extraction and identification of ECG features related to MI are crucial for intelligent assisted diagnosis of heart attacks. In this paper, a MI assisted pre-hospital diagnosis system based on CNN (Convolution Neural Network, CNN) is designed, to assist healthcare professionals in improving the accuracy and efficiency of MI diagnosis. The MI assisted diagnosis system, based on the CNN MI intelligent diagnostic model, is established with the goal of intelligent identification of MI in the context of computer-aided diagnosis systems. It aims to address key issues such as automatic feature extraction and analysis diagnosis, focusing on ECG research and exploring MI intelligent identification methods based on CNN. This system is dedicated to providing assistance and support for clinical diagnosis by healthcare professionals, enhancing diagnostic accuracy and efficiency to ensure early diagnosis and timely treatment of MI. Additionally, in cases of sudden cardiac emergencies among ECG users, the system is capable of providing timely assistance and treatment plans, offering critical support to ECG users in need.