心電圖疾病特徵分析

The Analysis of Electrocardiogram Feature in Disease

周逸雯(Yi-Wen Chou)

指導教授 ： 謝瑞建

元智大學/資訊學院/資訊管理學系/碩士(2009年)

摘要

摘 要
心臟疾病為歷年國人十大死因之一，因此診斷心臟疾病的方法扮演了重要角色。心電圖記載了心臟生理電氣活動紀錄，具有方便取得、非侵入性及蘊藏豐富的心臟生理訊號等特性，可推測病患的心臟狀況及可能罹患的疾病，提供臨床醫師作為進一步診斷使用。
本研究是利用隱藏式馬可夫模型(Hidden Markov Model)的特性，以心臟疾病的心肌梗塞為例，將已診斷為心肌梗塞的案例輸入，透過訓練產生幾個疾病模型，再從這幾個模型中，選出最能代表心肌梗塞的病症模型，這樣我們就得到了心肌梗塞疾病的辨識模型；以類似的方法，我們可將其他心臟疾病的病症案例投入訓練，再產生其他心臟疾病的辨識模型，這樣我們就可自行開發一套心臟疾病自動診斷分析系統。
目的：本研究以隱藏式馬可夫模型，將心肌梗塞疾病心電圖訊號資料，做模型訓練，可得到心肌梗塞疾病模型，進而可發展一套國人自製的心電圖疾病自動診斷分析系統。
方法：先將蒐集到的心肌梗塞XML-ECG檔案輸入做為訓練資料，經過訊號移除及導程選擇等處理，製作成隱藏式馬可夫模型要訓練的資料檔，就可進行病症模型訓練，產生心肌梗塞疾病模型。
結果：經過隱藏式馬可夫模型訓練產出的八種疾病模型，再將訓練資料匯入以最大近似估計法評估，發現二個高斯數和十二個狀態數訓練出的模型的近似估計值資料最大，機率值愈大表示愈能代表該群病症資料的分佈，故可得二個高斯數和十二個狀態數訓練出的疾病模型，做為心肌梗塞疾病的辨識模型。
結論：由心肌梗塞產出的二個高斯數和十二個狀態數訓練出的疾病模型可知，未來研究可繼續其他的心臟疾病模型訓練，依序依此方式進行，就可得到一套判斷心臟疾病的自動診斷分析機制。
關鍵字：隱藏式馬可夫模型，12導程心電圖，心肌梗塞

關鍵字

隱藏式馬可夫模型；12導程心電圖；心肌梗塞

並列摘要

Abstract
Heart attack is one of the major diseases leading to death based on recent reports. Therefore, it is crucial to develop a computer-assisted algorithm to improve conventional diagnoses of heart diseases. 12-lead ECG is a frequently-used diagnostic tool with the advantages of non-invasive measurement and convenient acquisition.
Objective : The major objective of this study is to develop a hidden markov model (HMM) that can recognize the ECG features of 12-lead ECG. The HMM model then can be used to identify myocardial infarction that is a life-threaten disease and commonly-seen in clinical practice.
Method : The 12-lead ECGs confirmed as myocardial infarction were acquired from clinically-used Philips XML-ECG. The waveforms in collected XML-ECG files were extracted and then processed to get clean ECG waveform data. The waveform data in various leads were used to build a HMM model. The HMM model using mixed Gaussian functions to model waveform pattern in time domain.
Result : By using Maximum Likelihood Estimation in the process of HMM training, the optimal HMM model representing anterior myocardial infarction was evaluated. Results indicated that anterior myocardial infarction can be represented by two Gaussian mixture and twelve states in HMM.
Conclusion : In sum, a computer-assisted myocardial infarction detector can be facilitated with the use of HMM.
Keywords: Hidden Markov Model, 12-lead ECG, Myocardial Infarction

並列關鍵字

Hidden Markov Model； 12-lead ECG； Myocardial Infarction

參考文獻

[2] Kei-ichiro, Hiroshi Nakajima, Takeshi Toyoshima, “Real-time Discrimination of Ventricular Tachyarrhythmia with Fourier-Transform Neural Network”, Biomedical Engineering, IEEE Transactions on Volume 46, NO 2, Feb. 1999 P179-185

[3] Cuiwei Li. Chongxun Zheng, Changfeng Tai, “Detection of ECG characteristic points using wavelet transforms”, Biomedical Engineering, IEEE Transactions on Volume 42, Issue 1, Jan. 1995 P21-28

[4] D. Coast, R. Stern, G. Cano, S. Briller, “An Approach to Cardiac Arrhythmia Analysis Using Hidden Markov Models”, Biomedical Engineering, IEEE Transactions on Volume 37, no 9, Sep. 1990 P826-836

[6] Frida Sandberg, Martin Stridh, Member, IEEE, Leif Sornmo, Senior Member, IEEE, “Frequency Tracking of Atrial Fibrillation Using Hidden Markov Models”, IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 55,NO. 2.FEBRUARY 2008

[7] Carlos S. Lima, Manuel J. Cardoso, “Cardiac Arrhythmia Detection by Parameters Sharing and MMIE Training of Hidden Markov Models”, Proceedings of th 29th Annual international Conference of the IEEE EMBS, 2007