Extraction of Respiratory Information from ECG and Application on the
Apnea Detection

Janbakhshi, Parvaneh | 2016

3208 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 48673 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Shamsollahi, Mohammad Bagher
  7. Abstract:
  8. Respiration signal is one of the biological information required to monitor patient respiratory activities. Noninvasive respiratory monitoring is an extensive field of research, which has seen widespread interest for several years. It is well known that the respiratory activity influences electrocardiographic measurements (ECG) in various ways. Therefore, different signal processing techniques have been developed for extracting this respiratory information from the ECG, namely ECG derived respiratory (EDR). Potential advantages of such techniques are their low cost, high convenience and the ability to simultaneously monitor cardiac and respiratory activity. One of the aims of this thesis is to propose an EDR extraction method using one-lead ECG. The proposed method is supposed to result in a good time patterns and frequency information agreement between extracted EDR and reference respiration signal. In this research, respiration effects on ECG have been modeled in two ways: additive and multiplicative based models. After model selection using a proposed criterion, Gaussian process (GP) and phase space reconstruction area (PSR_Area) methods are introduced for EDR extraction for additive and multiplicative models respectively. The extracted EDRs using GP and PSR_Area for their selected appropriate models, have correlations of 70.6%, 72.7% with reference respiration respectively. Compared with the recent EDR methods, these results yield improvement.Respiration signals can be used in diagnosis of respiration related disorders, e.g. sleep apnea. Sleep apnea is commonly defined as the cessation of breathing during sleep. Since apnea detection provided in sleep study centers is a complex and expensive procedure, providing a reliable diagnostic measure of apnea based solely on measurement of the ECG is of benefit. EDR signals, which are expected to be alternatives to other respiration signals, may be useful in apnea detection. Hence, the other aim of this work is to evaluate EDR extracted features in apnea detection. Results have demonstrated that automatic minute by minute apnea detection using PSR_Area extracted EDR can be achievable with sensitivity, specificity, and accuracy of over 90%
  9. Keywords:
  10. Gaussian process ; Electrocardiogram ; Apnea ; Electrocardiography ; Respiration Signal ; Electrocardiogram Derived Respiration (EDR) Signal ; Apnea Detection

 Digital Object List


...see more