Wearable individual electrocardiogram detection method

Abstract

The invention belongs to the technical field of electrocardiogram detection, and particularly relates to a wearable patient individual electrocardiogram detection method. According to the method, based on a multi-stream multi-scale convolutional neural networks (MM-CNN) model and a multi-lead comprehensive judgment algorithm, detection classifying is performed on an individual electrocardiogram (ECG). The invention proposes an MM-CNN-based single-lead classified detection algorithm to promote the clinical practice of ECG diagnosis; an algorithm that ECG signals of a few minutes are obtained from a specific patient to train a general model into a patient-specific model is proposed; the general model and the patient-specific model have a same network system, so that the efficiency of ECG detection is increased; the invention proposes the multi-lead comprehensive judgment algorithm to permanently classify the ECG signals from the specific patient, thus improving the robustness; and the method has high accuracy and high real-time performance, and is suitable for real-time detection of wearable equipment.

Description

Technical field [0001] The invention belongs to the technical field of ECG detection, and specifically relates to a wearable patient's individual ECG detection method. Background technique [0002] In 2013, the smart wearable device industry began to take off in China, and the current wearable device market seems to be saturated. In recent years, the wearable device market has been sluggish, because wearable devices are mainly used for medical and health testing, but the accuracy of the detection is not enough, such as the detection of ECG signals. Although Holter or other electrocardiographs can easily capture long-term real-time ECG signals, how to mine the information to further diagnose heart disease is still somewhat challenging. The electrocardiogram varies greatly between different patients, and this difference depends largely on the patient's physical condition. Because of the variation of the ECG waveform shape between different patients, the features extracted from th...

AI Technical Summary

Problems solved by technology

Because of the variation in ECG waveform morphology between different patients, the features extracted from the ECG signal should well represent the characteristics of the corresponding patients, which cannot be met by previous methods.

Images