Coupled hidden Markov model for automatic ECG and PCG segmentation

Jorge Oliveira; Catarina Sousa; Miguel T. Coimbra

ICASSP 2017accepted0 citations

Coupled hidden Markov model for automatic ECG and PCG segmentation

Jorge Oliveira, Catarina Sousa, Miguel T. Coimbra

Abstract

Automatic and simultaneous electrocardiogram (ECG) and phonocardiogram (PCG) segmentation is a good example of current challenges when designing multi-channel decision support systems for healthcare. In this paper, we implemented and tested a Montazeri coupled hidden Markov model (CHMM), where two HMM's cooperate to recreate the “true” state sequence. To evaluate its performance, we tested different settings (two fully connected and two partially connected channels) on a real dataset annotated by an expert. The fully connected model achieved 71% of positive predictability (P + ) on the ECG channel and 67% of P + on the PCG channel. The partially connected model achieved 90% of P + on the ECG channel and 80% of P + in the PCG channel. These results validate the potential of our approach for real world multichannel application systems.

BibTeX

@inproceedings{icassp2017_coupledhiddenmar,
  title = {Coupled hidden Markov model for automatic ECG and PCG segmentation},
  author = {Jorge Oliveira and Catarina Sousa and Miguel T. Coimbra},
  booktitle = {ICASSP 2017},
  year = {2017}
}