利用形態學特徵偵測心肌缺血的發生

Detection of myocardial ischemia episode using morphological features

徐佑(Hsu,Yu)

指導教授 ： 余松年

國立中正大學/工學院/電機工程學系/碩士(2012年)

摘要

本篇論文提出一個利用型態學特徵來辨識正常心搏(Normal beat)與心肌缺血心搏(Myocardial Ischemia beat)的心搏辨識系統。一般來說，心肌缺血都是藉由觀察心電圖波形中ST段(ST segment)的變化，當ST段的下降量超過一定的電壓時，則心肌缺血發生。
本系統所使用的型態學特徵，除了原始心搏波形能擷取到的ST段變化量，其餘的就是將擷取下來的心搏波形經過小波轉換，擷取最能夠明顯反應ST段變化的次頻帶，利用此次頻帶重建訊號並擷取特徵。而實驗的方式有三種，第一種採用混合所有檔案的心搏，使用10-fold cross-validation的方式做驗證。第二種為一筆檔案的心搏當測試資料，剩餘為訓練資料的leave-one-out方式，評估此系統是否能排除個體的差異性。最後一種為判斷持續性心肌缺血的發生，當心肌缺血持續30秒，我們才認為一個心肌缺血事件(Myocardial ischemia episode)成立。
第一種實驗方式的結果，在經過支持向量機(SVM)且為平衡的資料量(balance data)，辨識率達96.08%，而第二種實驗方式結果，辨識率仍有92.48%，第三種能判斷出心肌缺血事件的正確率有96.67%。

關鍵字

心電圖 ； ST段 ； 心肌缺血 ； 小波轉換

並列摘要

In this thesis, we propose to use morphological features to differentiate myocardial ischemia beats from normal beats. In general, myocardial ischemia causes alterations in electrocardiographic (ECG) signal such as deviation in the ST segment. When the ST segment deviates more than a certain voltage, the beat would be diagnosing as myocardial ischemia.
Some of the morphological features are extracted from the ST segment of the raw signal and some from the signal which is processed by wavelet transform . The wavelet transform decompose the ECG signal into several subband components, and we select one subband which is sensitive to the most changes in ST segment. There are three schemes to validate our experiment results. The first scheme mixes all file and uses 10-fold cross-validation. The second scheme uses leave-one-out cross-validation to test individual difference of each record. The last one is to detect the Myocardial Ischemia episode directly. If myocardial ischemia continues for 30 seconds, the episode is defined. All of schemes use support vector machine (SVM) classifier.
The result of the first scheme shows on accuracy of 96.15%. The accuracy of the second scheme is 92.48%.The third scheme achieves a detection rate of 96.67% in myocardial ischemic episode detection.

並列關鍵字

Electrocardiogram ； ST segment ； myocardial ischemia ； wavelet transform

參考文獻

[2] J. F. Scholl, J. R. Agre, L.P. Clare, and M. C. Gill, “Low-power impulse signal classifier using the Haar wavelet transform,” presented at Proc. SPIE, 1999.

[4] P. Exarchos,P.Costas,D.I.Fotiadis” An Association Rule Mining-Based Methodology for Automated Detection of Ischemic ECG Beats” IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 53, NO. 8, AUGUST 2006.

[5] K.Shiva, T.Mohammad, A.S.Mahdi ” Probabilistic Neural Network Oriented Classification Methodology for Ischemic Beat Detection Using Multi Resolution Wavelet Analysis” Proceedings of the 17th Iranian Conference of Biomedical Engineering (ICBME2010),pp.1-4 2010.

[6] K. Daskalov, I. A. Dotsinsky, and I. I. Christov, “Developments in ECG acquisition, preprocessing, parameter measurement, and recording,”

IEEE Eng. Med. Biol., vol. 17, no. 2, pp. 50–58, Mar./Apr. 1998.