Performance of an open-source heart sound segmentation algorithm on eight independent databases
Heart sound segmentation is a prerequisite step for the automatic analysis of heart sound signals, facilitating the subsequent identification and classification of pathological events. Recently, hidden Markov model-based algorithms have received increased interest due to their robustness in processi...
Saved in:
| Published in: | Physiological measurement Vol. 38; no. 8; p. 1730 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
England
01.08.2017
|
| Subjects: | |
| ISSN: | 1361-6579, 1361-6579 |
| Online Access: | Get more information |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Heart sound segmentation is a prerequisite step for the automatic analysis of heart sound signals, facilitating the subsequent identification and classification of pathological events. Recently, hidden Markov model-based algorithms have received increased interest due to their robustness in processing noisy recordings. In this study we aim to evaluate the performance of the recently published logistic regression based hidden semi-Markov model (HSMM) heart sound segmentation method, by using a wider variety of independently acquired data of varying quality.
Firstly, we constructed a systematic evaluation scheme based on a new collection of heart sound databases, which we assembled for the PhysioNet/CinC Challenge 2016. This collection includes a total of more than 120 000 s of heart sounds recorded from 1297 subjects (including both healthy subjects and cardiovascular patients) and comprises eight independent heart sound databases sourced from multiple independent research groups around the world. Then, the HSMM-based segmentation method was evaluated using the assembled eight databases. The common evaluation metrics of sensitivity, specificity, accuracy, as well as the [Formula: see text] measure were used. In addition, the effect of varying the tolerance window for determining a correct segmentation was evaluated.
The results confirm the high accuracy of the HSMM-based algorithm on a separate test dataset comprised of 102 306 heart sounds. An average [Formula: see text] score of 98.5% for segmenting S1 and systole intervals and 97.2% for segmenting S2 and diastole intervals were observed. The [Formula: see text] score was shown to increases with an increases in the tolerance window size, as expected.
The high segmentation accuracy of the HSMM-based algorithm on a large database confirmed the algorithm's effectiveness. The described evaluation framework, combined with the largest collection of open access heart sound data, provides essential resources for evaluators who need to test their algorithms with realistic data and share reproducible results. |
|---|---|
| AbstractList | Heart sound segmentation is a prerequisite step for the automatic analysis of heart sound signals, facilitating the subsequent identification and classification of pathological events. Recently, hidden Markov model-based algorithms have received increased interest due to their robustness in processing noisy recordings. In this study we aim to evaluate the performance of the recently published logistic regression based hidden semi-Markov model (HSMM) heart sound segmentation method, by using a wider variety of independently acquired data of varying quality.OBJECTIVEHeart sound segmentation is a prerequisite step for the automatic analysis of heart sound signals, facilitating the subsequent identification and classification of pathological events. Recently, hidden Markov model-based algorithms have received increased interest due to their robustness in processing noisy recordings. In this study we aim to evaluate the performance of the recently published logistic regression based hidden semi-Markov model (HSMM) heart sound segmentation method, by using a wider variety of independently acquired data of varying quality.Firstly, we constructed a systematic evaluation scheme based on a new collection of heart sound databases, which we assembled for the PhysioNet/CinC Challenge 2016. This collection includes a total of more than 120 000 s of heart sounds recorded from 1297 subjects (including both healthy subjects and cardiovascular patients) and comprises eight independent heart sound databases sourced from multiple independent research groups around the world. Then, the HSMM-based segmentation method was evaluated using the assembled eight databases. The common evaluation metrics of sensitivity, specificity, accuracy, as well as the [Formula: see text] measure were used. In addition, the effect of varying the tolerance window for determining a correct segmentation was evaluated.APPROACHFirstly, we constructed a systematic evaluation scheme based on a new collection of heart sound databases, which we assembled for the PhysioNet/CinC Challenge 2016. This collection includes a total of more than 120 000 s of heart sounds recorded from 1297 subjects (including both healthy subjects and cardiovascular patients) and comprises eight independent heart sound databases sourced from multiple independent research groups around the world. Then, the HSMM-based segmentation method was evaluated using the assembled eight databases. The common evaluation metrics of sensitivity, specificity, accuracy, as well as the [Formula: see text] measure were used. In addition, the effect of varying the tolerance window for determining a correct segmentation was evaluated.The results confirm the high accuracy of the HSMM-based algorithm on a separate test dataset comprised of 102 306 heart sounds. An average [Formula: see text] score of 98.5% for segmenting S1 and systole intervals and 97.2% for segmenting S2 and diastole intervals were observed. The [Formula: see text] score was shown to increases with an increases in the tolerance window size, as expected.MAIN RESULTSThe results confirm the high accuracy of the HSMM-based algorithm on a separate test dataset comprised of 102 306 heart sounds. An average [Formula: see text] score of 98.5% for segmenting S1 and systole intervals and 97.2% for segmenting S2 and diastole intervals were observed. The [Formula: see text] score was shown to increases with an increases in the tolerance window size, as expected.The high segmentation accuracy of the HSMM-based algorithm on a large database confirmed the algorithm's effectiveness. The described evaluation framework, combined with the largest collection of open access heart sound data, provides essential resources for evaluators who need to test their algorithms with realistic data and share reproducible results.SIGNIFICANCEThe high segmentation accuracy of the HSMM-based algorithm on a large database confirmed the algorithm's effectiveness. The described evaluation framework, combined with the largest collection of open access heart sound data, provides essential resources for evaluators who need to test their algorithms with realistic data and share reproducible results. Heart sound segmentation is a prerequisite step for the automatic analysis of heart sound signals, facilitating the subsequent identification and classification of pathological events. Recently, hidden Markov model-based algorithms have received increased interest due to their robustness in processing noisy recordings. In this study we aim to evaluate the performance of the recently published logistic regression based hidden semi-Markov model (HSMM) heart sound segmentation method, by using a wider variety of independently acquired data of varying quality. Firstly, we constructed a systematic evaluation scheme based on a new collection of heart sound databases, which we assembled for the PhysioNet/CinC Challenge 2016. This collection includes a total of more than 120 000 s of heart sounds recorded from 1297 subjects (including both healthy subjects and cardiovascular patients) and comprises eight independent heart sound databases sourced from multiple independent research groups around the world. Then, the HSMM-based segmentation method was evaluated using the assembled eight databases. The common evaluation metrics of sensitivity, specificity, accuracy, as well as the [Formula: see text] measure were used. In addition, the effect of varying the tolerance window for determining a correct segmentation was evaluated. The results confirm the high accuracy of the HSMM-based algorithm on a separate test dataset comprised of 102 306 heart sounds. An average [Formula: see text] score of 98.5% for segmenting S1 and systole intervals and 97.2% for segmenting S2 and diastole intervals were observed. The [Formula: see text] score was shown to increases with an increases in the tolerance window size, as expected. The high segmentation accuracy of the HSMM-based algorithm on a large database confirmed the algorithm's effectiveness. The described evaluation framework, combined with the largest collection of open access heart sound data, provides essential resources for evaluators who need to test their algorithms with realistic data and share reproducible results. |
| Author | Clifford, Gari D Liu, Chengyu Springer, David |
| Author_xml | – sequence: 1 givenname: Chengyu surname: Liu fullname: Liu, Chengyu organization: Department of Biomedical Informatics, Emory University, Atlanta, United States of America – sequence: 2 givenname: David surname: Springer fullname: Springer, David – sequence: 3 givenname: Gari D surname: Clifford fullname: Clifford, Gari D |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/28762336$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkLtPwzAQhy1URGlhZ0IeWUJtJ_FjRBUvqRIMMEd-XNqgxC62O_DfY4mCmO6-n747nW6BZj54QOiKkltKpFzRmtOKt0KttOag-hN0_hfN_vVztEjpgxBKJWvP0JxJwVld83PUvULsQ5y0t4BDj7XHYQ--SuEQS7IDHTMu4B1OsJ3AZ52H4LEetyEOeTfhAjBsdxkP3kEZdcXBTmdtdIJ0gU57PSa4PNYlen-4f1s_VZuXx-f13aay5YxcKSGgIdbyvjeECS2Uk7VtmTaNNbSFgrKpnaTMGaE0qZWRyjYc2oYYVXO2RDc_e_cxfB4g5W4akoVx1B7CIXVUsZYJRlta1OujejATuG4fh0nHr-73KewbeUpnPQ |
| CitedBy_id | crossref_primary_10_1016_j_bspc_2019_101560 crossref_primary_10_3390_s22010181 crossref_primary_10_1016_j_mtcomm_2024_110223 crossref_primary_10_1016_j_bspc_2020_102208 crossref_primary_10_1186_s12938_021_00925_0 crossref_primary_10_1109_JBHI_2019_2894222 crossref_primary_10_3390_app10144791 crossref_primary_10_1016_j_compbiomed_2025_109712 crossref_primary_10_3390_mi10120885 crossref_primary_10_1007_s10916_019_1415_1 crossref_primary_10_1016_j_bspc_2021_102474 crossref_primary_10_1007_s13534_025_00482_8 crossref_primary_10_1002_smm2_1130 crossref_primary_10_1155_2020_5846191 crossref_primary_10_3390_bios11040127 crossref_primary_10_3390_electronics11060938 crossref_primary_10_1007_s10470_021_01867_2 crossref_primary_10_1007_s00034_025_03000_4 crossref_primary_10_1016_j_compbiomed_2025_110623 crossref_primary_10_1007_s13246_020_00851_w crossref_primary_10_1177_09544062221091773 crossref_primary_10_1007_s13246_022_01112_8 crossref_primary_10_1038_s41598_019_42826_2 crossref_primary_10_1063_1_5110203 crossref_primary_10_1016_j_compeleceng_2021_107521 crossref_primary_10_1109_JSTSP_2019_2908723 crossref_primary_10_1016_j_cmpb_2023_107777 crossref_primary_10_1186_s12859_021_04032_8 crossref_primary_10_3390_e23060667 crossref_primary_10_1080_0954898X_2023_2270040 crossref_primary_10_1063_5_0083764 crossref_primary_10_1088_2057_1976_ac9da6 crossref_primary_10_1016_j_bspc_2024_106882 crossref_primary_10_1109_TBME_2018_2843258 crossref_primary_10_1109_TBME_2020_3010241 crossref_primary_10_1109_TIM_2021_3109389 crossref_primary_10_3390_diagnostics11122349 crossref_primary_10_1109_JBHI_2023_3270978 crossref_primary_10_1111_coin_12244 crossref_primary_10_2478_ijssis_2024_0012 crossref_primary_10_3390_app10175842 crossref_primary_10_1109_TBME_2021_3060718 crossref_primary_10_1109_ACCESS_2018_2889437 crossref_primary_10_3390_s25175263 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1088/1361-6579/aa6e9f |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine Engineering Physics |
| EISSN | 1361-6579 |
| ExternalDocumentID | 28762336 |
| Genre | Journal Article |
| GroupedDBID | --- -~X 123 1JI 4.4 53G 5B3 5VS 5ZH 7.M 7.Q AAGCD AAJIO AAJKP AALHV AATNI ABCXL ABHWH ABJNI ABQJV ABVAM ACAFW ACGFS ACHIP AEFHF AENEX AFYNE AKPSB ALMA_UNASSIGNED_HOLDINGS AOAED ASPBG ATQHT AVWKF AZFZN CBCFC CEBXE CGR CJUJL CRLBU CS3 CUY CVF DU5 EBS ECM EDWGO EIF EJD EMSAF EPQRW EQZZN F5P IHE IJHAN IOP IZVLO KOT LAP M45 N5L N9A NPM NT- NT. P2P PJBAE R4D RIN RNS RO9 ROL RPA SY9 W28 XPP ZMT 7X8 ADEQX AEINN |
| ID | FETCH-LOGICAL-c336t-977e40cc6ffb027a79d83c52ab4cb15e9d8843d812db79a039b89c46e540b9362 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 49 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000406847900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1361-6579 |
| IngestDate | Thu Sep 04 17:43:39 EDT 2025 Thu Apr 03 07:11:43 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c336t-977e40cc6ffb027a79d83c52ab4cb15e9d8843d812db79a039b89c46e540b9362 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 28762336 |
| PQID | 1925272151 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_1925272151 pubmed_primary_28762336 |
| PublicationCentury | 2000 |
| PublicationDate | 2017-Aug-01 20170801 |
| PublicationDateYYYYMMDD | 2017-08-01 |
| PublicationDate_xml | – month: 08 year: 2017 text: 2017-Aug-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England |
| PublicationTitle | Physiological measurement |
| PublicationTitleAlternate | Physiol Meas |
| PublicationYear | 2017 |
| SSID | ssj0011825 |
| Score | 2.4368541 |
| Snippet | Heart sound segmentation is a prerequisite step for the automatic analysis of heart sound signals, facilitating the subsequent identification and... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 1730 |
| SubjectTerms | Algorithms Databases, Factual Electrocardiography Heart Sounds Markov Chains Phonocardiography Signal Processing, Computer-Assisted |
| Title | Performance of an open-source heart sound segmentation algorithm on eight independent databases |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/28762336 https://www.proquest.com/docview/1925272151 |
| Volume | 38 |
| WOSCitedRecordID | wos000406847900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFD6oU9EHL_M2b0TwtWxt0qZ5EhGHLxt7UNhbSdJ0Dlw7bfX3e9Jmmy-C4EshhZRDLuf7es5JPoBb5fPU1_aiW-QOHot84wlutEeFVAjwmmZC12ITfDiMx2MxcgG30pVVLnxi7ajTQtsYeReZSBhwC1B383fPqkbZ7KqT0FiHFkUqY0u6-HiVRUDuHDbnrnxb4iFcmhI3Vnf5ritlZET2O8Gsgaa__18TD2DPUUxy36yJQ1gzeRt2f1w82IbtgUupt2GrrgHV5REko9UhAlJkRObEamt5TXyfWOnripRWhomUZjJzh5ZyIt8maEX1OiPYqCOtZLoU162IrUG1WFkew0v_8fnhyXP6C56mNKpw0rhhPa2jLFP49yq5SGOqw0AqppUfGmzGjKZIEVLFhexRoWKhWWSQBSqByHgCG3mRmzMgAYszPzah5Rv4yVBQTU2asgyhUfY068DNYkgTXN82aSFzU3yWyWpQO3DazEsyby7iSALrytHU8z_0voCdwCJyXbt3Ca0Md7e5gk39VU3Lj-t64eBzOBp8A7HizTM |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Performance+of+an+open-source+heart+sound+segmentation+algorithm+on+eight+independent+databases&rft.jtitle=Physiological+measurement&rft.au=Liu%2C+Chengyu&rft.au=Springer%2C+David&rft.au=Clifford%2C+Gari+D&rft.date=2017-08-01&rft.eissn=1361-6579&rft.volume=38&rft.issue=8&rft.spage=1730&rft_id=info:doi/10.1088%2F1361-6579%2Faa6e9f&rft_id=info%3Apmid%2F28762336&rft_id=info%3Apmid%2F28762336&rft.externalDocID=28762336 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1361-6579&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1361-6579&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1361-6579&client=summon |