L’appariement des données ECG à base des séries chronologiques

Abstract

The electrocardiogram (ECG) is one of the most commonly used diagnostic tools in medicine and healthcare, facilitating the diagnosis of a large number of cardiac di seases in combination with clinical, biological or echocardiographic data. The ECG trace is seen as a series of time-related values, which can be modeled by time series. Deep learning methods have achieved promising results on predictive healthcare tasks using ECG signals. The aim of this work is to propose a time series modeled ECG data matching ap proach by using deep learning techniques. For this purpose, we have proposed an RNN-LSTM recurrent neural network model. This model has been evaluated and the results are very satisfactory. We performed deep visualization of complex 12-lead ECG data stored in InfluxDB using the Grafana Framework.