Exploring classical machine learning for identification of pathological lung auscultations
The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attemp...
Saved in:
| Published in: | Computers in biology and medicine Vol. 168; p. 107784 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
Elsevier Ltd
01.01.2024
Elsevier Limited |
| Subjects: | |
| ISSN: | 0010-4825, 1879-0534, 1879-0534 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.
•Digital stethoscopes enabled quality recordings of pulmonary sounds.•The study data contains sequential 6-channel auscultations of 45 subjects.•Various schemes for the use of these biomedical audio signals were tested.•Supervised machine learning methods outperformed unsupervised ones.•The random forest had 71.11% accuracy in the side-based detection task. |
|---|---|
| AbstractList | The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection. The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection. •Digital stethoscopes enabled quality recordings of pulmonary sounds.•The study data contains sequential 6-channel auscultations of 45 subjects.•Various schemes for the use of these biomedical audio signals were tested.•Supervised machine learning methods outperformed unsupervised ones.•The random forest had 71.11% accuracy in the side-based detection task. AbstractThe use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection. The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection. The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection. © Copyright 2024 Elsevier B.V., All rights reserved |
| ArticleNumber | 107784 |
| Author | Sadauskas, Saulius Razvadauskas, Haroldas Nowaczyk, Sławomir Buškus, Kazimieras Naudžiūnas, Albinas Vaičiukynas, Evaldas Arlauskas, Lukas |
| Author_xml | – sequence: 1 givenname: Haroldas orcidid: 0000-0002-5391-4004 surname: Razvadauskas fullname: Razvadauskas, Haroldas organization: Lithuanian University of Health Sciences, Kaunas, Lithuania – sequence: 2 givenname: Evaldas orcidid: 0000-0002-4769-4527 surname: Vaičiukynas fullname: Vaičiukynas, Evaldas email: evaldas.vaiciukynas@ktu.lt organization: Kaunas University of Technology, Kaunas, Lithuania – sequence: 3 givenname: Kazimieras surname: Buškus fullname: Buškus, Kazimieras organization: Kaunas University of Technology, Kaunas, Lithuania – sequence: 4 givenname: Lukas surname: Arlauskas fullname: Arlauskas, Lukas organization: Kaunas University of Technology, Kaunas, Lithuania – sequence: 5 givenname: Sławomir orcidid: 0000-0002-7796-5201 surname: Nowaczyk fullname: Nowaczyk, Sławomir organization: Halmstad University, Halmstad, Sweden – sequence: 6 givenname: Saulius orcidid: 0000-0001-6705-6154 surname: Sadauskas fullname: Sadauskas, Saulius organization: Lithuanian University of Health Sciences, Kaunas, Lithuania – sequence: 7 givenname: Albinas surname: Naudžiūnas fullname: Naudžiūnas, Albinas organization: Lithuanian University of Health Sciences, Kaunas, Lithuania |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38042100$$D View this record in MEDLINE/PubMed https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-53514$$DView record from Swedish Publication Index (Högskolan i Halmstad) |
| BookMark | eNqNkk1v1DAQhi1URLeFv4AicUFCWcaOs3EuiKqUD6kSBz4OXEa2Y-968capnQD99zjdbZEqIThZsp9535l5fUKO-tAbQgoKSwp09XK71GE3KBd2plsyYFW-bhrBH5AFFU1bQl3xI7IAoFBywepjcpLSFgA4VPCIHFcCOKMAC_Lt4tfgQ3T9utBepuS09MVO6o3rTeGNjP38ZEMsXGf60dkMjC70RbDFIMdN8GF9U-OnzMkp6cmPN0R6TB5a6ZN5cjhPyZe3F5_P35eXH999OD-7LDVv6Vhqqlaqk4LWjEvLqFJdRaFSXWO1NcpS1XDKGqW4roWFRlkQLVccLKtUQ0V1Sl7sddNPM0wKh-h2Ml5jkA7fuK9nGOIaNxusq5ryTD_f00MMV5NJI-5c0sZ72ZswJWSiXQlK84Yy-uweug1T7PMsyFoKDEDAbP_0QE0qx3Fnf7vjDLzaAzqGlKKxqN1-RWOUziMFnEPFLf4JFedQcR9qFhD3BG49_qP04G1yAD-ciai96-fAvptrk-7moZgYAn6af8z8YVgFlPF2bv713wWwC-7fPfwGDYfXGw |
| CitedBy_id | crossref_primary_10_1016_j_compbiomed_2024_108190 crossref_primary_10_1002_widm_70030 |
| Cites_doi | 10.1007/s00521-019-04547-5 10.1001/archinte.166.6.610 10.1093/ehjdh/ztab059 10.2147/MDER.S135882 10.1097/MD.0000000000024738 10.1016/j.chaos.2020.110071 10.11613/BM.2012.031 10.1371/journal.pone.0254134 10.1177/001316446002000104 10.3390/medicina55040094 10.1016/j.bbe.2021.12.004 10.1023/A:1010933404324 10.1023/A:1022648800760 10.1109/LRA.2022.3149576 10.4103/1817-1737.160831 10.1038/s41598-020-64405-6 10.1093/ehjdh/ztaa017 10.1371/journal.pone.0220606 10.1038/s41598-021-96724-7 10.1109/TKDE.2005.50 10.1177/0300060520945141 10.1007/s00431-019-03363-2 10.1001/jamacardio.2018.0001 10.3390/app11104544 10.1007/978-3-030-16399-0_13 10.1111/tct.13462 10.2139/ssrn.2765419 10.21437/Interspeech.2020-2879 10.1007/978-3-030-96293-7_32 10.1186/s12890-022-01896-1 10.3390/app12157623 10.1109/JBHI.2020.3020494 10.1109/JBHI.2021.3056916 10.1109/JSEN.2018.2870759 10.18637/jss.v033.i01 10.1109/JBHI.2020.3048006 10.3390/s22093165 10.1016/j.bspc.2021.103215 10.1109/JBHI.2021.3064237 10.1186/s12909-019-1708-6 10.1016/j.amjcard.2018.12.022 10.1145/1541880.1541882 10.1186/s12938-015-0056-y 10.1161/JAHA.120.019905 10.1109/JBHI.2022.3144314 10.1109/ACCESS.2021.3063129 10.1080/15412555.2020.1815182 10.1016/j.dsp.2012.12.009 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd Copyright © 2023 Elsevier Ltd. All rights reserved. 2023. Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd – notice: Copyright © 2023 Elsevier Ltd. All rights reserved. – notice: 2023. Elsevier Ltd |
| DBID | AAYXX CITATION NPM 8FD FR3 JQ2 K9. M7Z NAPCQ P64 7X8 ADTPV AOWAS D8Z |
| DOI | 10.1016/j.compbiomed.2023.107784 |
| DatabaseName | CrossRef PubMed Technology Research Database Engineering Research Database ProQuest Computer Science Collection ProQuest Health & Medical Complete (Alumni) Biochemistry Abstracts 1 Nursing & Allied Health Premium Biotechnology and BioEngineering Abstracts MEDLINE - Academic SwePub SwePub Articles SWEPUB Högskolan i Halmstad |
| DatabaseTitle | CrossRef PubMed Nursing & Allied Health Premium Technology Research Database ProQuest Computer Science Collection Biochemistry Abstracts 1 ProQuest Health & Medical Complete (Alumni) Engineering Research Database Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed Nursing & Allied Health Premium |
| 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 | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1879-0534 |
| EndPage | 107784 |
| ExternalDocumentID | oai_DiVA_org_hh_53514 38042100 10_1016_j_compbiomed_2023_107784 1_s2_0_S0010482523012490 S0010482523012490 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M --Z -~X .1- .55 .DC .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29F 4.4 457 4G. 53G 5GY 5VS 7-5 71M 77I 7RV 7X7 88E 8AO 8FE 8FG 8FH 8FI 8FJ 8G5 8P~ 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMZM ABOCM ABUWG ABWVN ABXDB ACDAQ ACGFS ACIEU ACIUM ACIWK ACLOT ACNNM ACPRK ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO AEBSH AEIPS AEKER AENEX AEUPX AEVXI AFJKZ AFKRA AFPUW AFRAH AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AHMBA AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOUOD APXCP ARAPS ASPBG AVWKF AXJTR AZFZN AZQEC BBNVY BENPR BGLVJ BHPHI BKEYQ BKOJK BLXMC BNPGV BPHCQ BVXVI CCPQU CS3 DU5 DWQXO EBS EFJIC EFKBS EFLBG EJD EMOBN EO8 EO9 EP2 EP3 EX3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN FYUFA G-2 G-Q GBLVA GBOLZ GNUQQ GUQSH HCIFZ HLZ HMCUK HMK HMO HVGLF HZ~ IHE J1W K6V K7- KOM LK8 LX9 M1P M29 M2O M41 M7P MO0 N9A NAPCQ O-L O9- OAUVE OZT P-8 P-9 P2P P62 PC. PHGZM PHGZT PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO Q38 R2- ROL RPZ RXW SAE SBC SCC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSV SSZ SV3 T5K TAE UAP UKHRP WOW WUQ X7M XPP Z5R ZGI ~G- ~HD 3V. AACTN AFCTW AFKWA AJOXV ALIPV AMFUW M0N RIG 9DU AAYXX AFFHD CITATION AGCQF AGRNS NPM 8FD FR3 JQ2 K9. M7Z P64 7X8 ADTPV AOWAS D8Z |
| ID | FETCH-LOGICAL-c491t-c1b6bda81524af21bbd3103bd7fcfebf1b74127bb4c58f07bf0894b40f23b7183 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001130207800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0010-4825 1879-0534 |
| IngestDate | Tue Nov 04 16:09:41 EST 2025 Thu Oct 02 10:52:05 EDT 2025 Tue Oct 07 06:28:38 EDT 2025 Mon Jul 21 05:56:09 EDT 2025 Tue Nov 18 22:24:23 EST 2025 Sat Nov 29 06:58:01 EST 2025 Tue Feb 25 20:11:33 EST 2025 Tue Oct 14 19:33:12 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Isolation forest Surfboard audio features extractor Digital health Random forest Auscultation Lung sounds |
| Language | English |
| License | Copyright © 2023 Elsevier Ltd. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c491t-c1b6bda81524af21bbd3103bd7fcfebf1b74127bb4c58f07bf0894b40f23b7183 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-7796-5201 0000-0002-4769-4527 0000-0001-6705-6154 0000-0002-5391-4004 |
| PMID | 38042100 |
| PQID | 2910200808 |
| PQPubID | 1226355 |
| PageCount | 1 |
| ParticipantIDs | swepub_primary_oai_DiVA_org_hh_53514 proquest_miscellaneous_2896811380 proquest_journals_2910200808 pubmed_primary_38042100 crossref_citationtrail_10_1016_j_compbiomed_2023_107784 crossref_primary_10_1016_j_compbiomed_2023_107784 elsevier_clinicalkeyesjournals_1_s2_0_S0010482523012490 elsevier_clinicalkey_doi_10_1016_j_compbiomed_2023_107784 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-01-01 |
| PublicationDateYYYYMMDD | 2024-01-01 |
| PublicationDate_xml | – month: 01 year: 2024 text: 2024-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Oxford |
| PublicationTitle | Computers in biology and medicine |
| PublicationTitleAlternate | Comput Biol Med |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd Elsevier Limited |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier Limited |
| References | Huang, Ling (b55) 2005; 17 Jani, Danford, Thompson, Schuster, Manlhiot, Kutty (b25) 2021; 2 Hsu, Huang, Huang, Huang, Cheng, Chen, Hsiao, Chen, Chen, Lai, Hsu, Lin, Tsai, Wu, Tseng, Tseng, Chen, Lai (b34) 2021; 16 Garvick, Gillette, Gao, Bates, Waynick, Crandall (b3) 2022; 19 Breiman (b46) 2001; 45 Cortes (b50) 2022 Pham, Phan, Palaniappan, Mertins, McLoughlin (b37) 2021; 25 Barbosa, Sousa, Morais-Almeida, Simões, Mendes (b18) 2020; 17 Sankararaman (b40) 2022; 71 Hafke-Dys, Brȩborowicz, Kleka, Kociński, Biniakowski (b6) 2019; 14 Kim, Hyon, Lee, Woo, Ha, Chung (b27) 2022; 22 Yadav, Singh, Dutta, Travieso (b30) 2019; 32 Liu, Ting, Zhou (b49) 2008 Chandola, Banerjee, Kumar (b54) 2009; 41 Huang, Meng, Zhang, Wu, Zhang, Zhang, Ye, Wei, Zhao, Jiang, Ji, Zhou, Zheng, Zhang, Xie, Hu, He, Chen, Wang, Cao, Xu, Lei, Jiang, Hu, Qin, Wang, He, Xiao, Zheng, Hu, Pan, Zhang, Cai (b21) 2020 Serbes, Sakar, Kahya, Aydin (b41) 2013; 23 Bernardi, Giudici, Leone, Zuolo, Furlotti, Carretta, Fabris (b10) 2019; 19 Cortes (b52) 2019 Leng, Tan, Chai, Wang, Ghista, Zhong (b24) 2015; 14 McHugh (b58) 2012 Fernando, Sridharan, Denman, Ghaemmaghami, Fookes (b39) 2022; 26 . Pereira, Gomes, Sa Couto, Costa, Reis, Mattos, Cruz-Correia, Coimbra (b2) 2017 (b4) 2022 Lv, Dong, Lei, Shi, Wang, Zhu, Wen, Zhang, Fu, Gu, Yuan, Guan, Xia, Zhao, Chen (b15) 2021; 2 Jeong, Kim, Kim, Kim, Lee (b33) 2021; 11 Zhu, Smith, Hauser (b22) 2022; 7 Brites, Silva, Barbosa, Rigo, Correia, Leithardt (b26) 2022 Hsu, Huang, Huang, Cheng, Chen, Hsiao, Chen, Lai (b61) 2022; 12 Rocha, Filos, Mendes, Vogiatzis, Perantoni, Kaimakamis, Natsiavas, Oliveira, Jácome, Marques, Paiva, Chouvarda, Carvalho, Maglaveras (b43) 2017 Silverman, Balk (b12) 2019; 123 Vukanovic-Criley, Criley, Warde, Boker, Guevara-Matheus, Churchill, Nelson, Criley (b9) 2006; 166 Jonathan Rubin, Rui Abreu, Anurag Ganguli, Saigopal Nelaturi, Ion Matei, Kumar Sricharan, Recognizing Abnormal Heart Sounds Using Deep Learning, in: Proceedings of the 2nd International Workshop on Knowledge Discovery in Healthcare Data (KHD@IJCAI), 2017, pp. 13–19, URL. Zhang, Wang, Zhou, Dong, Zhang, Zhang, Liu, Wu, Yuan, Tang, Dong, Lin, Chen, Tong, Zhao, Yin (b35) 2021; 9 Schapire (b60) 1990; 5 (b5) 2022 Sarkar, Madabhavi, Niranjan, Dogra (b44) 2015; 10 Horimasu, Ohshimo, Yamaguchi, Sakamoto, Masuda, Nakashima, Miyamoto, Iwamoto, Fujitaka, Hamada, Sadamori, Shime, Hattori (b36) 2021; 100 Arts, Lim, van de Ven, Heunks, Tuinman (b8) 2020; 10 Friedman, Hastie, Tibshirani (b48) 2010; 33 Cortes (b51) 2019 Grzywalski, Piecuch, Szajek, Brȩborowicz, Hafke-Dys, Kociński, Pastusiak, Belluzzo (b23) 2019; 178 Narula, Chandrashekhar, Braunwald (b1) 2018; 3 Haider, Behera (b42) 2022; 42 Cortes (b53) 2021 Swarup, Makaryus (b19) 2018; 11 Latif, Usman, Rana, Qadir (b29) 2018; 18 Steyerberg (b47) 2019 Kalinauskienė, Razvadauskas, Morse, Maxey, Naudžiūnas (b14) 2019; 55 Haskel, Itelman, Zilber, Barkai, Segal (b16) 2022; 22 Li, Zhang, Yang, Gao (b20) 2020; 48 Beger (b56) 2016 Rennoll, McLane, Emmanouilidou, West, Elhilali (b11) 2021; 25 Kim, Hyon, Jung, Lee, Yoo, Chung, Ha (b7) 2021; 11 Altan, Karasu (b17) 2020; 140 Cohen (b57) 1960; 20 Raphael Lenain, Jack Weston, Abhishek Shivkumar, Emil Fristed, Surfboard: Audio Feature Extraction for Modern Machine Learning, in: Proc. Interspeech 2020, 2020, pp. 2917–2921 McLane, Emmanouilidou, West, Elhilali (b13) 2021; 25 Müller, Illium, Ritz, Schmid (b59) 2021 Shuvo, Ali, Swapnil, Hasan, Bhuiyan (b38) 2021; 25 Chorba, Shapiro, Le, Maidens, Prince, Pham, Kanzawa, Barbosa, Currie, Brooks, White, Huskin, Paek, Geocaris, Elnathan, Ronquillo, Kim, Alam, Mahadevan, Fuller, Stalker, Bravo, Jean, Lee, Gjergjindreaj, Mihos, Forman, Venkatraman, McCarthy, Thomas (b31) 2021; 10 Shuvo, Ali, Swapnil, Al-Rakhami, Gumaei (b32) 2021; 9 Altan (10.1016/j.compbiomed.2023.107784_b17) 2020; 140 Friedman (10.1016/j.compbiomed.2023.107784_b48) 2010; 33 Cortes (10.1016/j.compbiomed.2023.107784_b51) 2019 Pham (10.1016/j.compbiomed.2023.107784_b37) 2021; 25 Chandola (10.1016/j.compbiomed.2023.107784_b54) 2009; 41 Fernando (10.1016/j.compbiomed.2023.107784_b39) 2022; 26 Narula (10.1016/j.compbiomed.2023.107784_b1) 2018; 3 Jani (10.1016/j.compbiomed.2023.107784_b25) 2021; 2 Arts (10.1016/j.compbiomed.2023.107784_b8) 2020; 10 Liu (10.1016/j.compbiomed.2023.107784_b49) 2008 Yadav (10.1016/j.compbiomed.2023.107784_b30) 2019; 32 McHugh (10.1016/j.compbiomed.2023.107784_b58) 2012 Jeong (10.1016/j.compbiomed.2023.107784_b33) 2021; 11 (10.1016/j.compbiomed.2023.107784_b4) 2022 Sarkar (10.1016/j.compbiomed.2023.107784_b44) 2015; 10 Leng (10.1016/j.compbiomed.2023.107784_b24) 2015; 14 Shuvo (10.1016/j.compbiomed.2023.107784_b38) 2021; 25 Kim (10.1016/j.compbiomed.2023.107784_b7) 2021; 11 Huang (10.1016/j.compbiomed.2023.107784_b21) 2020 Latif (10.1016/j.compbiomed.2023.107784_b29) 2018; 18 Cortes (10.1016/j.compbiomed.2023.107784_b52) 2019 Hafke-Dys (10.1016/j.compbiomed.2023.107784_b6) 2019; 14 McLane (10.1016/j.compbiomed.2023.107784_b13) 2021; 25 Kim (10.1016/j.compbiomed.2023.107784_b27) 2022; 22 Silverman (10.1016/j.compbiomed.2023.107784_b12) 2019; 123 Bernardi (10.1016/j.compbiomed.2023.107784_b10) 2019; 19 10.1016/j.compbiomed.2023.107784_b45 Beger (10.1016/j.compbiomed.2023.107784_b56) 2016 Vukanovic-Criley (10.1016/j.compbiomed.2023.107784_b9) 2006; 166 Sankararaman (10.1016/j.compbiomed.2023.107784_b40) 2022; 71 Haider (10.1016/j.compbiomed.2023.107784_b42) 2022; 42 Swarup (10.1016/j.compbiomed.2023.107784_b19) 2018; 11 Hsu (10.1016/j.compbiomed.2023.107784_b61) 2022; 12 Li (10.1016/j.compbiomed.2023.107784_b20) 2020; 48 Horimasu (10.1016/j.compbiomed.2023.107784_b36) 2021; 100 Cortes (10.1016/j.compbiomed.2023.107784_b50) 2022 Haskel (10.1016/j.compbiomed.2023.107784_b16) 2022; 22 Cohen (10.1016/j.compbiomed.2023.107784_b57) 1960; 20 Schapire (10.1016/j.compbiomed.2023.107784_b60) 1990; 5 Rocha (10.1016/j.compbiomed.2023.107784_b43) 2017 Grzywalski (10.1016/j.compbiomed.2023.107784_b23) 2019; 178 Zhu (10.1016/j.compbiomed.2023.107784_b22) 2022; 7 Rennoll (10.1016/j.compbiomed.2023.107784_b11) 2021; 25 Zhang (10.1016/j.compbiomed.2023.107784_b35) 2021; 9 (10.1016/j.compbiomed.2023.107784_b5) 2022 Lv (10.1016/j.compbiomed.2023.107784_b15) 2021; 2 Barbosa (10.1016/j.compbiomed.2023.107784_b18) 2020; 17 Müller (10.1016/j.compbiomed.2023.107784_b59) 2021 Brites (10.1016/j.compbiomed.2023.107784_b26) 2022 Pereira (10.1016/j.compbiomed.2023.107784_b2) 2017 Shuvo (10.1016/j.compbiomed.2023.107784_b32) 2021; 9 Huang (10.1016/j.compbiomed.2023.107784_b55) 2005; 17 Serbes (10.1016/j.compbiomed.2023.107784_b41) 2013; 23 Kalinauskienė (10.1016/j.compbiomed.2023.107784_b14) 2019; 55 Chorba (10.1016/j.compbiomed.2023.107784_b31) 2021; 10 Hsu (10.1016/j.compbiomed.2023.107784_b34) 2021; 16 Garvick (10.1016/j.compbiomed.2023.107784_b3) 2022; 19 Steyerberg (10.1016/j.compbiomed.2023.107784_b47) 2019 Breiman (10.1016/j.compbiomed.2023.107784_b46) 2001; 45 10.1016/j.compbiomed.2023.107784_b28 Cortes (10.1016/j.compbiomed.2023.107784_b53) 2021 |
| References_xml | – volume: 25 start-page: 2938 year: 2021 end-page: 2947 ident: b37 article-title: CNN-MoE based framework for classification of respiratory anomalies and lung disease detection publication-title: IEEE J. Biomed. Health Inform. – start-page: 247 year: 2019 end-page: 260 ident: b47 article-title: Modern estimation methods publication-title: Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating – volume: 25 start-page: 2583 year: 2021 end-page: 2594 ident: b13 article-title: Design and comparative performance of a robust lung auscultation system for noisy clinical settings publication-title: IEEE J. Biomed. Health Inform. – year: 2022 ident: b5 article-title: EU population: Population, total - European union from the world bank: Data – volume: 16 year: 2021 ident: b34 article-title: Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database–HF_lung_V1 publication-title: PLOS ONE – year: 2019 ident: b51 article-title: Distance approximation using isolation forests – volume: 19 year: 2019 ident: b10 article-title: A prospective study on the efficacy of patient simulation in heart and lung auscultation publication-title: BMC Med. Educ. – volume: 7 start-page: 4204 year: 2022 end-page: 4211 ident: b22 article-title: Automated heart and lung auscultation in robotic physical examinations publication-title: IEEE Robot. Autom. Lett. – volume: 178 start-page: 883 year: 2019 end-page: 890 ident: b23 article-title: Practical implementation of artificial intelligence algorithms in pulmonary auscultation examination publication-title: Eur. J. Pediatr. – volume: 10 start-page: 158 year: 2015 ident: b44 article-title: Auscultation of the respiratory system publication-title: Ann. Thorac. Med. – volume: 22 year: 2022 ident: b27 article-title: The coming era of a new auscultation system for analyzing respiratory sounds publication-title: BMC Pulm. Med. – volume: 140 year: 2020 ident: b17 article-title: Recognition of COVID-19 disease from X-ray images by hybrid model consisting of 2D curvelet transform, chaotic salp swarm algorithm and deep learning technique publication-title: Chaos Solitons Fractals – volume: 9 start-page: 36955 year: 2021 end-page: 36967 ident: b32 article-title: CardioXNet: A novel lightweight deep learning framework for cardiovascular disease classification using heart sound recordings publication-title: IEEE Access – volume: 23 start-page: 1012 year: 2013 end-page: 1021 ident: b41 article-title: Pulmonary crackle detection using time–frequency and time–scale analysis publication-title: Digit. Signal Process. – volume: 2 start-page: 456 year: 2021 end-page: 466 ident: b25 article-title: The discerning ear: cardiac auscultation in the era of artificial intelligence and telemedicine publication-title: Eur. Heart J. - Digit. Health – start-page: 33 year: 2017 end-page: 37 ident: b43 article-title: A respiratory sound database for the development of automated classification publication-title: Precision Medicine Powered by PHealth and Connected Health – volume: 5 start-page: 197 year: 1990 end-page: 227 ident: b60 article-title: The strength of weak learnability publication-title: Mach. Learn. – volume: 12 start-page: 7623 year: 2022 ident: b61 article-title: A progressively expanded database for automated lung sound analysis: An update publication-title: Appl. Sci. – volume: 9 year: 2021 ident: b35 article-title: Real-world verification of artificial intelligence algorithm-assisted auscultation of breath sounds in children publication-title: Front. Pediatr. – volume: 48 year: 2020 ident: b20 article-title: Artificial intelligence-aided decision support in paediatrics clinical diagnosis: development and future prospects publication-title: J. Int. Med. Res. – volume: 33 start-page: 1 year: 2010 end-page: 22 ident: b48 article-title: Regularization paths for generalized linear models via coordinate descent publication-title: J. Stat. Softw. – year: 2022 ident: b4 article-title: Eurostat: Consultation of a medical doctor (in private practice or as outpatient) per inhabitant – volume: 17 start-page: 601 year: 2020 end-page: 617 ident: b18 article-title: Telemedicine in COPD: An overview by topics publication-title: COPD: J. Chronic Obstr. Pulm. Dis. – volume: 10 year: 2021 ident: b31 article-title: Deep learning algorithm for automated cardiac murmur detection via a digital stethoscope platform publication-title: J. Am. Heart Assoc. – volume: 18 start-page: 9393 year: 2018 end-page: 9400 ident: b29 article-title: Phonocardiographic sensing using deep learning for abnormal heartbeat detection publication-title: IEEE Sens. J. – volume: 22 start-page: 3165 year: 2022 ident: b16 article-title: Remote auscultation of heart and lungs as an acceptable alternative to legacy measures in quarantined COVID-19 patients–prospective evaluation of 250 examinations publication-title: Sensors – volume: 45 start-page: 5 year: 2001 end-page: 32 ident: b46 article-title: Random forests publication-title: Mach. Learn. – volume: 14 start-page: 1 year: 2019 end-page: 16 ident: b6 article-title: The accuracy of lung auscultation in the practice of physicians and medical students publication-title: PLOS ONE – volume: 55 start-page: 94 year: 2019 ident: b14 article-title: A comparison of electronic and traditional stethoscopes in the heart auscultation of obese patients publication-title: Medicina – volume: 32 start-page: 17843 year: 2019 end-page: 17856 ident: b30 article-title: Machine learning-based classification of cardiac diseases from PCG recorded heart sounds publication-title: Neural Comput. Appl. – volume: 25 start-page: 2595 year: 2021 end-page: 2603 ident: b38 article-title: A lightweight CNN model for detecting respiratory diseases from lung auscultation sounds using EMD-CWT-based hybrid scalogram publication-title: IEEE J. Biomed. Health Inform. – start-page: 97 year: 2021 end-page: 106 ident: b59 article-title: Analysis of feature representations for anomalous sound detection publication-title: Proceedings of the 13th International Conference on Agents and Artificial Intelligence (ICAART), Vol. 2 – reference: Raphael Lenain, Jack Weston, Abhishek Shivkumar, Emil Fristed, Surfboard: Audio Feature Extraction for Modern Machine Learning, in: Proc. Interspeech 2020, 2020, pp. 2917–2921, – volume: 42 start-page: 42 year: 2022 end-page: 59 ident: b42 article-title: Computerized lung sound based classification of asthma and chronic obstructive pulmonary disease (COPD) publication-title: Biocybern. Biomed. Eng. – year: 2021 ident: b53 article-title: Revisiting randomized choices in isolation forests – start-page: 401 year: 2017 end-page: 420 ident: b2 article-title: IS4learning—A multiplatform simulation technology to teach and evaluate auscultation skills publication-title: Health Professionals’ Education in the Age of Clinical Information Systems Mobile Computing and Social Networks – volume: 17 start-page: 299 year: 2005 end-page: 310 ident: b55 article-title: Using AUC and accuracy in evaluating learning algorithms publication-title: IEEE Trans. Knowl. Data Eng. – volume: 100 year: 2021 ident: b36 article-title: A machine-learning based approach to quantify fine crackles in the diagnosis of interstitial pneumonia publication-title: Medicine – start-page: 413 year: 2008 end-page: 422 ident: b49 article-title: Isolation forest publication-title: 2008 Eighth IEEE International Conference on Data Mining – volume: 166 start-page: 610 year: 2006 ident: b9 article-title: Competency in cardiac examination skills in medical students trainees, physicians, and faculty publication-title: Arch. Intern. Med. – start-page: 356 year: 2022 end-page: 388 ident: b26 article-title: Machine learning and IoT applied to cardiovascular diseases identification through heart sounds: A literature review publication-title: Lecture Notes in Networks and Systems – volume: 41 start-page: 1 year: 2009 end-page: 58 ident: b54 article-title: Anomaly detection publication-title: ACM Comput. Surv. – volume: 3 start-page: 346 year: 2018 ident: b1 article-title: Time to add a fifth pillar to bedside physical examination publication-title: (JAMA) Cardiol. – volume: 25 start-page: 1542 year: 2021 end-page: 1549 ident: b11 article-title: Electronic stethoscope filtering mimics the perceived sound characteristics of acoustic stethoscope publication-title: IEEE J. Biomed. Health Inform. – volume: 2 start-page: 119 year: 2021 end-page: 124 ident: b15 article-title: Artificial intelligence-assisted auscultation in detecting congenital heart disease publication-title: Eur. Heart J. - Digit. Health – volume: 10 start-page: 7347 year: 2020 ident: b8 article-title: The diagnostic accuracy of lung auscultation in adult patients with acute pulmonary pathologies: a meta-analysis publication-title: Sci. Rep. – volume: 26 start-page: 2898 year: 2022 end-page: 2908 ident: b39 article-title: Robust and interpretable temporal convolution network for event detection in lung sound recordings publication-title: IEEE J. Biomed. Health Inform. – volume: 71 year: 2022 ident: b40 article-title: Untangling the graph based features for lung sound auscultation publication-title: Biomed. Signal Process. Control – start-page: 276 year: 2012 end-page: 282 ident: b58 article-title: Interrater reliability: the kappa statistic publication-title: Biochem. Med. – volume: 14 year: 2015 ident: b24 article-title: The electronic stethoscope publication-title: BioMed. Eng. OnLine – year: 2020 ident: b21 article-title: The respiratory sound features of COVID-19 patients fill gaps between clinical data and screening methods – volume: 20 start-page: 37 year: 1960 end-page: 46 ident: b57 article-title: A coefficient of agreement for nominal scales publication-title: Educ. Psychol. Meas. – reference: Jonathan Rubin, Rui Abreu, Anurag Ganguli, Saigopal Nelaturi, Ion Matei, Kumar Sricharan, Recognizing Abnormal Heart Sounds Using Deep Learning, in: Proceedings of the 2nd International Workshop on Knowledge Discovery in Healthcare Data (KHD@IJCAI), 2017, pp. 13–19, URL. – reference: . – volume: 19 start-page: 112 year: 2022 end-page: 120 ident: b3 article-title: Can cardiac auscultation accuracy be improved with an additional app-based learning tool? publication-title: Clin. Teacher – volume: 11 start-page: 4544 year: 2021 ident: b33 article-title: Methods for improving deep learning-based cardiac auscultation accuracy: Data augmentation and data generalization publication-title: Appl. Sci. – year: 2019 ident: b52 article-title: Imputing missing values with unsupervised random trees – year: 2022 ident: b50 article-title: Isotree: Isolation-based outlier detection – volume: 123 start-page: 984 year: 2019 end-page: 985 ident: b12 article-title: Digital stethoscope-improved auscultation at the bedside publication-title: Am. J. Cardiol. – volume: 11 start-page: 29 year: 2018 end-page: 36 ident: b19 article-title: Digital stethoscope: technology update publication-title: Med. Devices: Evid. Res. – year: 2016 ident: b56 article-title: Precision-recall curves publication-title: SSRN Electron. J. – volume: 11 start-page: 17186 year: 2021 ident: b7 article-title: Respiratory sound classification for crackles wheezes, and rhonchi in the clinical field using deep learning publication-title: Sci. Rep. – volume: 32 start-page: 17843 issue: 24 year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b30 article-title: Machine learning-based classification of cardiac diseases from PCG recorded heart sounds publication-title: Neural Comput. Appl. doi: 10.1007/s00521-019-04547-5 – volume: 9 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b35 article-title: Real-world verification of artificial intelligence algorithm-assisted auscultation of breath sounds in children publication-title: Front. Pediatr. – volume: 166 start-page: 610 year: 2006 ident: 10.1016/j.compbiomed.2023.107784_b9 article-title: Competency in cardiac examination skills in medical students trainees, physicians, and faculty publication-title: Arch. Intern. Med. doi: 10.1001/archinte.166.6.610 – volume: 2 start-page: 456 issue: 3 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b25 article-title: The discerning ear: cardiac auscultation in the era of artificial intelligence and telemedicine publication-title: Eur. Heart J. - Digit. Health doi: 10.1093/ehjdh/ztab059 – volume: 11 start-page: 29 year: 2018 ident: 10.1016/j.compbiomed.2023.107784_b19 article-title: Digital stethoscope: technology update publication-title: Med. Devices: Evid. Res. doi: 10.2147/MDER.S135882 – year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b51 – year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b52 – volume: 100 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b36 article-title: A machine-learning based approach to quantify fine crackles in the diagnosis of interstitial pneumonia publication-title: Medicine doi: 10.1097/MD.0000000000024738 – volume: 140 issn: 0960-0779 year: 2020 ident: 10.1016/j.compbiomed.2023.107784_b17 article-title: Recognition of COVID-19 disease from X-ray images by hybrid model consisting of 2D curvelet transform, chaotic salp swarm algorithm and deep learning technique publication-title: Chaos Solitons Fractals doi: 10.1016/j.chaos.2020.110071 – start-page: 276 year: 2012 ident: 10.1016/j.compbiomed.2023.107784_b58 article-title: Interrater reliability: the kappa statistic publication-title: Biochem. Med. doi: 10.11613/BM.2012.031 – volume: 16 issue: 7 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b34 article-title: Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database–HF_lung_V1 publication-title: PLOS ONE doi: 10.1371/journal.pone.0254134 – volume: 20 start-page: 37 year: 1960 ident: 10.1016/j.compbiomed.2023.107784_b57 article-title: A coefficient of agreement for nominal scales publication-title: Educ. Psychol. Meas. doi: 10.1177/001316446002000104 – year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b5 – start-page: 33 year: 2017 ident: 10.1016/j.compbiomed.2023.107784_b43 article-title: A respiratory sound database for the development of automated classification – year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b53 – volume: 55 start-page: 94 issn: 1648-9144 year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b14 article-title: A comparison of electronic and traditional stethoscopes in the heart auscultation of obese patients publication-title: Medicina doi: 10.3390/medicina55040094 – volume: 42 start-page: 42 issue: 1 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b42 article-title: Computerized lung sound based classification of asthma and chronic obstructive pulmonary disease (COPD) publication-title: Biocybern. Biomed. Eng. doi: 10.1016/j.bbe.2021.12.004 – volume: 45 start-page: 5 year: 2001 ident: 10.1016/j.compbiomed.2023.107784_b46 article-title: Random forests publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 – year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b50 – volume: 5 start-page: 197 issn: 1573-0565 issue: 2 year: 1990 ident: 10.1016/j.compbiomed.2023.107784_b60 article-title: The strength of weak learnability publication-title: Mach. Learn. doi: 10.1023/A:1022648800760 – volume: 7 start-page: 4204 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b22 article-title: Automated heart and lung auscultation in robotic physical examinations publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2022.3149576 – volume: 10 start-page: 158 issue: 3 year: 2015 ident: 10.1016/j.compbiomed.2023.107784_b44 article-title: Auscultation of the respiratory system publication-title: Ann. Thorac. Med. doi: 10.4103/1817-1737.160831 – volume: 10 start-page: 7347 year: 2020 ident: 10.1016/j.compbiomed.2023.107784_b8 article-title: The diagnostic accuracy of lung auscultation in adult patients with acute pulmonary pathologies: a meta-analysis publication-title: Sci. Rep. doi: 10.1038/s41598-020-64405-6 – volume: 2 start-page: 119 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b15 article-title: Artificial intelligence-assisted auscultation in detecting congenital heart disease publication-title: Eur. Heart J. - Digit. Health doi: 10.1093/ehjdh/ztaa017 – start-page: 97 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b59 article-title: Analysis of feature representations for anomalous sound detection – volume: 14 start-page: 1 year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b6 article-title: The accuracy of lung auscultation in the practice of physicians and medical students publication-title: PLOS ONE doi: 10.1371/journal.pone.0220606 – volume: 11 start-page: 17186 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b7 article-title: Respiratory sound classification for crackles wheezes, and rhonchi in the clinical field using deep learning publication-title: Sci. Rep. doi: 10.1038/s41598-021-96724-7 – volume: 17 start-page: 299 year: 2005 ident: 10.1016/j.compbiomed.2023.107784_b55 article-title: Using AUC and accuracy in evaluating learning algorithms publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2005.50 – volume: 48 issue: 9 year: 2020 ident: 10.1016/j.compbiomed.2023.107784_b20 article-title: Artificial intelligence-aided decision support in paediatrics clinical diagnosis: development and future prospects publication-title: J. Int. Med. Res. doi: 10.1177/0300060520945141 – volume: 178 start-page: 883 year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b23 article-title: Practical implementation of artificial intelligence algorithms in pulmonary auscultation examination publication-title: Eur. J. Pediatr. doi: 10.1007/s00431-019-03363-2 – volume: 3 start-page: 346 year: 2018 ident: 10.1016/j.compbiomed.2023.107784_b1 article-title: Time to add a fifth pillar to bedside physical examination publication-title: (JAMA) Cardiol. doi: 10.1001/jamacardio.2018.0001 – volume: 11 start-page: 4544 issue: 10 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b33 article-title: Methods for improving deep learning-based cardiac auscultation accuracy: Data augmentation and data generalization publication-title: Appl. Sci. doi: 10.3390/app11104544 – start-page: 247 year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b47 article-title: Modern estimation methods doi: 10.1007/978-3-030-16399-0_13 – volume: 19 start-page: 112 issue: 2 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b3 article-title: Can cardiac auscultation accuracy be improved with an additional app-based learning tool? publication-title: Clin. Teacher doi: 10.1111/tct.13462 – year: 2016 ident: 10.1016/j.compbiomed.2023.107784_b56 article-title: Precision-recall curves publication-title: SSRN Electron. J. doi: 10.2139/ssrn.2765419 – ident: 10.1016/j.compbiomed.2023.107784_b45 doi: 10.21437/Interspeech.2020-2879 – year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b4 – start-page: 356 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b26 article-title: Machine learning and IoT applied to cardiovascular diseases identification through heart sounds: A literature review doi: 10.1007/978-3-030-96293-7_32 – volume: 22 issue: 1 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b27 article-title: The coming era of a new auscultation system for analyzing respiratory sounds publication-title: BMC Pulm. Med. doi: 10.1186/s12890-022-01896-1 – volume: 12 start-page: 7623 issue: 15 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b61 article-title: A progressively expanded database for automated lung sound analysis: An update publication-title: Appl. Sci. doi: 10.3390/app12157623 – year: 2020 ident: 10.1016/j.compbiomed.2023.107784_b21 – volume: 25 start-page: 1542 issue: 5 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b11 article-title: Electronic stethoscope filtering mimics the perceived sound characteristics of acoustic stethoscope publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2020.3020494 – volume: 25 start-page: 2583 issue: 7 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b13 article-title: Design and comparative performance of a robust lung auscultation system for noisy clinical settings publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2021.3056916 – volume: 18 start-page: 9393 issue: 22 year: 2018 ident: 10.1016/j.compbiomed.2023.107784_b29 article-title: Phonocardiographic sensing using deep learning for abnormal heartbeat detection publication-title: IEEE Sens. J. doi: 10.1109/JSEN.2018.2870759 – volume: 33 start-page: 1 issue: 1 year: 2010 ident: 10.1016/j.compbiomed.2023.107784_b48 article-title: Regularization paths for generalized linear models via coordinate descent publication-title: J. Stat. Softw. doi: 10.18637/jss.v033.i01 – volume: 25 start-page: 2595 issue: 7 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b38 article-title: A lightweight CNN model for detecting respiratory diseases from lung auscultation sounds using EMD-CWT-based hybrid scalogram publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2020.3048006 – volume: 22 start-page: 3165 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b16 article-title: Remote auscultation of heart and lungs as an acceptable alternative to legacy measures in quarantined COVID-19 patients–prospective evaluation of 250 examinations publication-title: Sensors doi: 10.3390/s22093165 – ident: 10.1016/j.compbiomed.2023.107784_b28 – volume: 71 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b40 article-title: Untangling the graph based features for lung sound auscultation publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.103215 – volume: 25 start-page: 2938 issue: 8 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b37 article-title: CNN-MoE based framework for classification of respiratory anomalies and lung disease detection publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2021.3064237 – start-page: 401 year: 2017 ident: 10.1016/j.compbiomed.2023.107784_b2 article-title: IS4learning—A multiplatform simulation technology to teach and evaluate auscultation skills – volume: 19 year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b10 article-title: A prospective study on the efficacy of patient simulation in heart and lung auscultation publication-title: BMC Med. Educ. doi: 10.1186/s12909-019-1708-6 – volume: 123 start-page: 984 year: 2019 ident: 10.1016/j.compbiomed.2023.107784_b12 article-title: Digital stethoscope-improved auscultation at the bedside publication-title: Am. J. Cardiol. doi: 10.1016/j.amjcard.2018.12.022 – start-page: 413 year: 2008 ident: 10.1016/j.compbiomed.2023.107784_b49 article-title: Isolation forest – volume: 41 start-page: 1 issue: 3 year: 2009 ident: 10.1016/j.compbiomed.2023.107784_b54 article-title: Anomaly detection publication-title: ACM Comput. Surv. doi: 10.1145/1541880.1541882 – volume: 14 issue: 1 year: 2015 ident: 10.1016/j.compbiomed.2023.107784_b24 article-title: The electronic stethoscope publication-title: BioMed. Eng. OnLine doi: 10.1186/s12938-015-0056-y – volume: 10 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b31 article-title: Deep learning algorithm for automated cardiac murmur detection via a digital stethoscope platform publication-title: J. Am. Heart Assoc. doi: 10.1161/JAHA.120.019905 – volume: 26 start-page: 2898 issue: 7 year: 2022 ident: 10.1016/j.compbiomed.2023.107784_b39 article-title: Robust and interpretable temporal convolution network for event detection in lung sound recordings publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2022.3144314 – volume: 9 start-page: 36955 year: 2021 ident: 10.1016/j.compbiomed.2023.107784_b32 article-title: CardioXNet: A novel lightweight deep learning framework for cardiovascular disease classification using heart sound recordings publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3063129 – volume: 17 start-page: 601 issue: 5 year: 2020 ident: 10.1016/j.compbiomed.2023.107784_b18 article-title: Telemedicine in COPD: An overview by topics publication-title: COPD: J. Chronic Obstr. Pulm. Dis. doi: 10.1080/15412555.2020.1815182 – volume: 23 start-page: 1012 issue: 3 year: 2013 ident: 10.1016/j.compbiomed.2023.107784_b41 article-title: Pulmonary crackle detection using time–frequency and time–scale analysis publication-title: Digit. Signal Process. doi: 10.1016/j.dsp.2012.12.009 |
| SSID | ssj0004030 |
| Score | 2.385938 |
| Snippet | The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand... AbstractThe use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to... |
| SourceID | swepub proquest pubmed crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 107784 |
| SubjectTerms | Accuracy Algorithms Artificial intelligence Auscultation Decision trees Digital health Internal Medicine Isolation forest Learning algorithms Loudness Lung sounds Machine learning Medical research Other Outliers (statistics) Random forest Resonant frequencies Statistical analysis Stethoscopes Surfboard audio features extractor |
| Title | Exploring classical machine learning for identification of pathological lung auscultations |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S0010482523012490 https://www.clinicalkey.es/playcontent/1-s2.0-S0010482523012490 https://www.ncbi.nlm.nih.gov/pubmed/38042100 https://www.proquest.com/docview/2910200808 https://www.proquest.com/docview/2896811380 https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-53514 |
| Volume | 168 |
| WOSCitedRecordID | wos001130207800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-0534 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004030 issn: 0010-4825 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELe6DSFeEN8UxhSk7TFT4jp18li2oYFgQjCmihcrdmyWtUurtqnG_if-R86x47TdEAWJl6iKP9L4fj6fnd_dIbRLRNYJpaA-oTCbCODYT1LKfSGVVKnqJlmaVckm6MlJ3O8nn1qtn7UvzHxIiyK-ukrG_1XUcA-ErV1n_0LcrlO4Ab9B6HAFscN1LcE3rDqhLeNKCJcVZVLWOSIMdzLPLFPIWY06PbFThsNSuy-Wmqg6WzjWq6Ma2GwQFZ12MZLT6sf6z-n1PM2gn4FxHTvWDJMsdab8WZpXBu1hXg5-FKYOmPeLVd6UewfRXi8clFNDALnOL2E1byr0JsPmAR_KQbp0mIHJwmGGVdCwLJDY-EI7BW0S71gVC_tVarLK3dD-5iDiQgtvbKIX7Ovs8PtNk-WA2ysLoaMn1sy3C9b0xHRPzPS0gbYwjRJQq1u9d0f9940jbtAxPk_2LSx1zBAKb_9Xv7OHbu53VoLZVgbQ6QN03-5cvJ5B3EPUksUjdPejFfdj9M0Bz3PA8yzwvBp4HgDPWwaeN1LeIvA8DTxvCXhP0Ne3R6cHx77N3OELkoQzX4S8y7M0BuOQpAqHnGc6nx3PqBJKchVyMGQx5ZyIKFYB5SqIE8JJoHCHg7XUeYo2i1EhnyMP40AorMMGdiOidDK1SAdRlEEiQLsk3Tai9fgxYcPa6-wqQ_YnKbZR6FqOTWiXNdoktYhY7boMiy0DBK7Rlt7WVk6t8piykE0xC9iXKmgWwAfD6otJErTRdo0G5ipjMPQ1eSmI2-i1K4bFQX_xSws5KqEODFAchp0YunhmUOReFW4SHAZQsmtg5Up0xPnD_KzHRpPv7PycRdrb58U_jNZLdK-Z5NtoczYp5St0R8xn-XSygzZoP96xU-gX4rL7aA |
| linkProvider | Elsevier |
| 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=Exploring+classical+machine+learning+for+identification+of+pathological+lung+auscultations&rft.jtitle=Computers+in+biology+and+medicine&rft.au=Razvadauskas%2C+Haroldas&rft.au=Vai%C4%8Diukynas%2C+Evaldas&rft.au=Bu%C5%A1kus%2C+Kazimieras&rft.au=Arlauskas%2C+Lukas&rft.date=2024-01-01&rft.issn=0010-4825&rft.volume=168&rft.spage=107784&rft_id=info:doi/10.1016%2Fj.compbiomed.2023.107784&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_compbiomed_2023_107784 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0010-4825&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0010-4825&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0010-4825&client=summon |