Stduy On Myocardial Ischemia Detection Based On T-wave Area Curve(TWAC)

In recent years,coronary heart disease has become one of the main diseases that endanger human health,with a high mortality and disability rate.Myocardial ischemia(MI)is the main symptom in the development of coronary heart disease.Continuous and severe myocardial ischemia will lead to myocardial infarction.Coronary angiography is considered the gold standard for the diagnosis of coronary heart disease.However,the standard 12-lead electrocardiogram(ECG)has always been the most commonly used method in the diagnosis of clinical heart disease.It contains a wealth of physiological and pathological information and is economical.A convenient and non-invasive detection tool,except that the electrocardiogram is very accurate in diagnosing arrhythmia,the sensitivity and specificity of other cardiac diseases(such as myocardial ischemia)are not high.The clinical manifestations of myocardial ischemia are mainly the changes of ST-T segment of ECG,that is,ST segment and T wave.The diagnosis of myocardial ischemia by ECG mainly depends on the characteristics of ST-T segment.However,there are many factors affecting ST segment changes,such as axis shift,heart rate,electrode effects,body position changes,etc.,leading to inaccurate detection of feature points,relying on ST segment shift to detect myocardial ischemia has a large false detection rate and missed detection rate.T wave represents the repolarization process of the ventricle.During myocardial ischemia,myocardial repolarization is delayed,resulting in changes in T wave morphology,such as biphasic type,inverted type or high type.In view of this characteristic of T wave,this paper proposes a method for diagnosing myocardial ischemia based on the T wave area curve.The main work of this paper is given as follow:First of all,we use parabolic fitting method to locate the peaks of QRS complexes,and then compares three algorithms for locating T-wave offset:wavelet transform method,cumulative integrated area method,and TRA algorithm.The performance of this algorithm for the detection of T-wave endpoints is verified using QT database.It is concluded that the cumulative integrated area method has higher sensitivity and positive predictiveness,and is simple to calculate.It is robust to acquisition noise,baseline drift,and T-wave morphological changes.Secondly,we analyze the limitations of the cumulative integral area method in detecting T-wave characteristic points,that is,the fixed RR ^'interval parameter is used to determine the T-wave characteristic point search interval,and there is a certain false detection rate.Aiming at this problem,this paper uses k-means clustering algorithm to set the search boundary,and uses grid search strategy to optimize parameters.Experiments conducted in the QT database show that the improved algorithm has better performance.Finally,after accurately positioning the onset and offset of the T wave,the variation curves of the T wave area of different leads with the cardiac cycle are calculated.Based on the characteristic that the T wave morphology changes specifically during myocardial ischemia,a novel method for detecting myocardial ischemia——T-Wave Area Curve(TWAC).This method is completely based on the standard 12-lead ECG,so it is non-invasive,economical and convenient.Through observation and analysis of a large amount of data,it was found that:There exist significant correlation between the morphology of TWAC and myocardial ischemia.The TWAC morphology of normal people is smooth and gentle,while the TWAC morphology of patients with coronary stenosis is mostly jagged,and the curve becomes more severe with more severe stenosis;The sensitivity and specificity of detecting myocardial ischemia are higher than those of static electrocardiogram and treadmill exercise electrocardiogram.We selected 364 sample data to verify the effectiveness of TWAC,including sample data of 148 patients with MI and 52 normal people in the PTB database,and 122 suspected myocardial defects collected in the Second Affiliated Hospital of Zhejiang University.Sample data from blood patients and 42 healthy medical examiners.The experimental results show that the overall sensitivity of TWAC to the diagnosis of myocardial ischemia is 84.3%,the specificity is 83.5%,and the accuracy is 84.0%.Therefore,this method has important guiding significance for the detection and treatment of myocardial ischemia,and it can also be used as an evaluation method for the treatment effect of myocardial ischemia patients.