A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.

The detection of heart disease using a stethoscope requires significant skill and time, making it expensive and impractical for widespread screening in low-resource environments. Machine learning analysis of heart sound recordings can improve upon the accessibility and accuracy of diagnoses, but exi...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrew McDonald, Mark J F Gales, Anurag Agarwal
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-11-01
Series:PLOS Digital Health
Online Access:https://doi.org/10.1371/journal.pdig.0000436
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850219664449208320
author Andrew McDonald
Mark J F Gales
Anurag Agarwal
author_facet Andrew McDonald
Mark J F Gales
Anurag Agarwal
author_sort Andrew McDonald
collection DOAJ
description The detection of heart disease using a stethoscope requires significant skill and time, making it expensive and impractical for widespread screening in low-resource environments. Machine learning analysis of heart sound recordings can improve upon the accessibility and accuracy of diagnoses, but existing approaches require further validation on larger and more representative clinical datasets. For many previous algorithms, segmenting the signal into its individual sound components is a key first step. However, segmentation algorithms often struggle to find S1 or S2 sounds in the presence of strong murmurs or noise that significantly alter or mask the expected sound. Segmentation errors then propagate to the subsequent disease classifier steps. We propose a novel recurrent neural network and hidden semi-Markov model (HSMM) algorithm that can both segment the signal and detect a heart murmur, removing the need for a two-stage algorithm. This algorithm formed the 'CUED_Acoustics' entry to the 2022 George B. Moody PhysioNet challenge, where it won the first prize in both the challenge tasks. The algorithm's performance exceeded that of many end-to-end deep learning approaches that struggled to generalise to new test data. As our approach both segments the heart sound and detects a murmur, it can provide interpretable predictions for a clinician. The model also estimates the signal quality of the recording, which may be useful for a screening environment where non-experts are using a stethoscope. These properties make the algorithm a promising tool for screening of abnormal heart murmurs.
format Article
id doaj-art-511d49db92c44e9c84afe45165238583
institution OA Journals
issn 2767-3170
language English
publishDate 2024-11-01
publisher Public Library of Science (PLoS)
record_format Article
series PLOS Digital Health
spelling doaj-art-511d49db92c44e9c84afe451652385832025-08-20T02:07:19ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702024-11-01311e000043610.1371/journal.pdig.0000436A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.Andrew McDonaldMark J F GalesAnurag AgarwalThe detection of heart disease using a stethoscope requires significant skill and time, making it expensive and impractical for widespread screening in low-resource environments. Machine learning analysis of heart sound recordings can improve upon the accessibility and accuracy of diagnoses, but existing approaches require further validation on larger and more representative clinical datasets. For many previous algorithms, segmenting the signal into its individual sound components is a key first step. However, segmentation algorithms often struggle to find S1 or S2 sounds in the presence of strong murmurs or noise that significantly alter or mask the expected sound. Segmentation errors then propagate to the subsequent disease classifier steps. We propose a novel recurrent neural network and hidden semi-Markov model (HSMM) algorithm that can both segment the signal and detect a heart murmur, removing the need for a two-stage algorithm. This algorithm formed the 'CUED_Acoustics' entry to the 2022 George B. Moody PhysioNet challenge, where it won the first prize in both the challenge tasks. The algorithm's performance exceeded that of many end-to-end deep learning approaches that struggled to generalise to new test data. As our approach both segments the heart sound and detects a murmur, it can provide interpretable predictions for a clinician. The model also estimates the signal quality of the recording, which may be useful for a screening environment where non-experts are using a stethoscope. These properties make the algorithm a promising tool for screening of abnormal heart murmurs.https://doi.org/10.1371/journal.pdig.0000436
spellingShingle Andrew McDonald
Mark J F Gales
Anurag Agarwal
A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.
PLOS Digital Health
title A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.
title_full A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.
title_fullStr A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.
title_full_unstemmed A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.
title_short A recurrent neural network and parallel hidden Markov model algorithm to segment and detect heart murmurs in phonocardiograms.
title_sort recurrent neural network and parallel hidden markov model algorithm to segment and detect heart murmurs in phonocardiograms
url https://doi.org/10.1371/journal.pdig.0000436
work_keys_str_mv AT andrewmcdonald arecurrentneuralnetworkandparallelhiddenmarkovmodelalgorithmtosegmentanddetectheartmurmursinphonocardiograms
AT markjfgales arecurrentneuralnetworkandparallelhiddenmarkovmodelalgorithmtosegmentanddetectheartmurmursinphonocardiograms
AT anuragagarwal arecurrentneuralnetworkandparallelhiddenmarkovmodelalgorithmtosegmentanddetectheartmurmursinphonocardiograms
AT andrewmcdonald recurrentneuralnetworkandparallelhiddenmarkovmodelalgorithmtosegmentanddetectheartmurmursinphonocardiograms
AT markjfgales recurrentneuralnetworkandparallelhiddenmarkovmodelalgorithmtosegmentanddetectheartmurmursinphonocardiograms
AT anuragagarwal recurrentneuralnetworkandparallelhiddenmarkovmodelalgorithmtosegmentanddetectheartmurmursinphonocardiograms