METHOD AND DEVICE FOR AUTOMATICALLY DETERMINING ST SEGMENT OF ELECTROCARDIOGRAM SIGNAL BASED ON ARTIFICIAL INTELLIGENCE TECHNOLOGY

摘要

Provided are an electrocardiosignal ST section automatic determination method and apparatus based on artificial intelligence technology. For a filtered human body electrocardiosignal, in conjunction with wavelet filtering and triangular area methods, key feature points of the electrocardiosignal are respectively extracted, comprising locating an S wave and a T wave, and the accurate recognition of initial point and slope features of an ST section is realized; subsequently, the use of a baseline removal method based on mean value filtering is put forward, and an extracted baseline sequence is subtracted to obtain a new electrocardiosignal; then, the ST section and each baseline section are extracted for the electrocardiosignal, a heart rate and the slope of each baseline section are calculated, and a standard baseline is selected comprehensively; and finally, an abnormal change in the ST section is recognized according to the standard baseline to obtain a qualitative and quantitative determination result regarding whether the ST section is lifted, lowered or normal. The method solves the problems of a baseline error being caused by a baseline shift, the selection of a standard baseline being inaccurate, and the number of abnormal heartbeats having a great difference, indirectly improves the ST section abnormal change determination accuracy, is simple for calculation and can be easily implemented.