Loading...

Early Detection of Cardiac Arrhythmia Based on Bayesian Methods from ECG Data

Montazeri Ghahjaverestan, Nasim | 2015

888 Viewed
  1. Type of Document: Ph.D. Dissertation
  2. Language: English
  3. Document No: 47642 (05)
  4. University: Sharif University of Technology, University of Rennes 1, France
  5. Department: Electrical Engineering
  6. Advisor(s): Shamsollahi, Mohammad Bagher; Hernandez, Alfredo
  7. Abstract:
  8. Apnea Bradycardia (AB) episodes (breathing pauses associated with a significant fall in heart rate) are the most common disease in preterm infants. Consequences associated with apnea-bradycardia episodes involve a compromise in oxygenation and tissue perfusion, a poor neuromotor prognosis at childhood and a predisposing factor to sudden-death syndrome in preterm newborns. It is therefore important that these episodes are recognized (early detected or predicted if possible), to start an appropriate treatment and to prevent the associated risks. In this thesis, we propose two Bayesian Network (BN) approaches (Markovian and Switching Kalman Filter) for the early detection of apnea bradycardia events on preterm infants, using different features extracted from electrocardiographic (ECG) recordings.Concerning the Markovian approach, we propose new frameworks for two generalizations of the classical Hidden Markov Model (HMM). The first framework, Coupled Hidden Markov Model (CHMM), is accomplished by assigning a Markov chain (channel) to each dimension of observation and establishing a coupling among channels. The second framework, Coupled Hidden semi Markov Model (CHSMM), combines the characteristics of Hidden semi Markov Model (HSMM) with the above-mentioned coupling concept. For each framework,we present appropriate recursions in order to use modified Forward-Backward (FB) algorithms to solve the learning and inference problems. The proposed learning algorithm is based on Maximum Likelihood (ML) criteria. Moreover, we propose two new switching Kalman Filter (SKF) based algorithms, called wave-based and R-based, to present an index for bradycardia detection from ECG. The wave-based algorithm is established based on McSarry’s dynamical model for ECG beat generation which is used in an Extended Kalman filter algorithm in order to detect subtle changes in ECG sample by sample. We also propose a new SKF algorithm to model normal beats and those with bradycardia by two different AR processes.We evaluate the performance of the proposed Markovian methods to detect event of interest using both simulated and real databases. In the case of simulated data, the performance of the proposed algorithms is evaluated in classification and detection procedures, in terms of confusion tables, sensitivity, specificity and time delay for detection task. The real signal database contains three feature time series extracted from raw ECG signals, acquired from preterm infants suffering from bradycardia. The proposed algorithms are evaluated in terms of the same metrics as in detection task of simulated data, which illustrate their ability in early detection of bradycardia episodes. The real ECG database is also applied in order to establish and assess the two Switching algorithms. The best results of AB detection precision are achieved by CHSMM (94.87% sensitivity and 96.52% specificity) and the lowest time delay is obtained by using CHMM (0.73 s). Among methods in Switching approach, wavebased shows superior performance by 94.74% sensitivity, 94.17% specificity and 0.35 s time
    delay
  9. Keywords:
  10. Electrocardiogram ; State Space ; Coupled Hidden Markov Model ; Switching Kalman Filter ; Heart Diseases ; Early Detection ; Arrhythmia Recognition ; Couple Hidden Semi Markov Model

 Digital Object List

 Bookmark

No TOC