Incremental HMM training applied to ECG signal analysis

• Published in: Computers in biology and medicine Vol. 38; no. 6; pp. 659 - 667
• Main Authors: Andreão, Rodrigo V, Muller, Sandra M.T, Boudy, Jérôme, Dorizzi, Bernadette, Bastos-Filho, Teodiano F, Sarcinelli-Filho, Mário
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2008; Elsevier Limited; Elsevier
• Subjects: Algorithms; Databases, Factual; ECG analysis; ECG segmentation; Electrocardiography - statistics & numerical data; Engineering Sciences; HMM adaptation; Humans; Incremental training; Internal Medicine; Ischemia - diagnosis; Likelihood Functions; Markov Chains; Other; Signal and Image processing; Signal Processing, Computer-Assisted; Incremental training; HMM adaptation; ECG analysis; ECG segmentation; HMM adptation
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2008.03.006

Abstract This work discusses the implementation of incremental hidden Markov model (HMM) training methods for electrocardiogram (ECG) analysis. The HMMs are used to model the ECG signal as a sequence of connected elementary waveforms. Moreover, an adaptation process is implemented to adapt the HMMs to the ECG signal of a particular individual. The adaptation training strategy is based on incremental versions of the expectation–maximization, segmental k-means and Bayesian approaches. Performance of the training methods was assessed through experiments considering the QT and ST–T databases. The results obtained show that the incremental training improves beat segmentation and ischemia detection performance with the advantage of low computational effort.