Artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus

An electrocardiogram analysis method, comprising:

• receiving electrocardiogram (ECG) data, and the electrocardiogram data being single-lead or multi-lead time sequence data;
• converting a data format of the ECG data into a preset standard data format by resampling, and performing a first filtering processing on converted ECG data in the preset standard data format;
• performing heart beat detection processing on the ECG data processed by the first filtering processing to identify multiple pieces of heart beat data included in the ECG data, each of which is corresponding to a heart beat cycle, including amplitude data and starting-ending time data of corresponding P wave, QRS complex and T wave;
• performing interference identification on the heart beat data according to a trained interference identification two classification model to determine whether there is an interference noise in the heart beat data with a probability value for judging the interference noise;
• according to lead parameters of the heart beat data and the heart beat data, combining and generating heart beat time sequence data based on results of the interference identification and time rules;
• and generating heart beat analysis data according to the heart beat time sequence data;
• analyzing and evaluating a signal quality of the heart beat analysis data, and obtaining signal quality evaluation index of the heart beat analysis data;
• performing feature extraction and analysis of an amplitude and time characterization data on the heart beat analysis data according to a trained heart beat classification model, to obtain primary classification information of the heart beat analysis data;
• inputting the heart beat analysis data of particular heart beats in results of the primary classification information into a trained ST segment and T wave change model for identification, and determining ST segment and T wave evaluation information;
• performing secondary classification processing on the heart beat analysis data according to ECG basic rule reference data and the ST segment and T wave evaluation information under the primary classification information to finally obtain heart beat classification information;
• and
• generating ECG event data from the heart beat analysis data according to the heart beat classification information and the ECG basic rule reference data;
• screening the ECG event data according to the signal quality evaluation index to obtain corresponding report conclusion data and report table item data;
• generating report graphic data according to typical data segments in each kind of the ECG event data;
• and outputting the report table item data, the report graphic data and the report conclusion data.