Design Of ECG Automatic Diagnosis System

The research of ECG automatic diagnosis has been focus in the last years. If the research can be put into practice and its performance is reliable,it will be a great fruit in both medical field and artificial intelligence field. The system can detect QRS wave correctly,use the features of ECG and experience of specialists to diagnose,provide diagnosis advice to the doctor,and query the information of both patient and ECG. The following work has been performed in this research: The ECG preprocessing and characteristic point detection are studied. The ECG preprocessing emphasis is put in the elimination of power line interference. The characteristic point detection includes the P,QRS and T wave detecting and the onset and offset point determination. Based on location of wave crest,a real-time R-Wave precise detection algorithm is used to detect QRS wave. The expert knowledge and the rule of deducing are managed through database manage engine. The method makes the analyses of expert knowledge more easily. In addition,the system also contains the information of the patients and ECG data. These parts make the system modifying and debugging more easily. Based on the idea of expert system,a deducing and diagnosis system for ECG is made. According to the features of ECG,through queering the expert knowledge and the rule of deducing,the advice of diagnosis is made. Just because there are some uncertain factors in the signal sampling and expert knowledge,MYCIN model is referenced in the system. To use the information saved in the database conveniently,the inquiry system is made in the paper.