An adaptive threshold-based semi-supervised learning method for cardiovascular disease detection
Deep cardiovascular disease (CVD) detection usually achieves good performance with large-scale labeled electrocardiograms (ECGs), but manual labeling of ECGs is tedious. Semi-supervised learning (SSL) aims to improve model performance through unlabeled data. In this study, an adaptive threshold-base...
Uloženo v:
| Vydáno v: | Information sciences Ročník 677; s. 120881 |
|---|---|
| Hlavní autoři: | , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Inc
01.08.2024
|
| Témata: | |
| ISSN: | 0020-0255 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Deep cardiovascular disease (CVD) detection usually achieves good performance with large-scale labeled electrocardiograms (ECGs), but manual labeling of ECGs is tedious. Semi-supervised learning (SSL) aims to improve model performance through unlabeled data. In this study, an adaptive threshold-based semi-supervised learning model (ATSS-LGP) is proposed. It introduces the multibranch network (MBN) to generate local and global predictions for 12-lead ECG. The labeled ECGs are used to train the model in supervised manner and produce adaptive thresholds through the proposed prediction voting decision mechanism. The unlabeled ECGs are divided into high-confidence and low-confidence parts by the adaptive thresholds. The pseudo-labeling technique and consistency regularization are used to jointly guide the unsupervised learning, which can fully utilize all unlabeled ECGs. To the best of our knowledge, this is the first SSL algorithm that explores adaptive threshold in ECG. ATSS-LGP shows impressive performance in CVD detection. Using the same number of labeled ECGs, it achieves at least a 5.15% increase in accuracy over pure supervised learning. Moreover, ATSS-LGP achieves comparable performance to fully supervised method using only 10% of labeled ECGs. In summary, ATSS-LGP is a suitable SSL algorithm for 12-lead ECGs, which can greatly reduce the burden of ECG labeling in deep learning. |
|---|---|
| AbstractList | Deep cardiovascular disease (CVD) detection usually achieves good performance with large-scale labeled electrocardiograms (ECGs), but manual labeling of ECGs is tedious. Semi-supervised learning (SSL) aims to improve model performance through unlabeled data. In this study, an adaptive threshold-based semi-supervised learning model (ATSS-LGP) is proposed. It introduces the multibranch network (MBN) to generate local and global predictions for 12-lead ECG. The labeled ECGs are used to train the model in supervised manner and produce adaptive thresholds through the proposed prediction voting decision mechanism. The unlabeled ECGs are divided into high-confidence and low-confidence parts by the adaptive thresholds. The pseudo-labeling technique and consistency regularization are used to jointly guide the unsupervised learning, which can fully utilize all unlabeled ECGs. To the best of our knowledge, this is the first SSL algorithm that explores adaptive threshold in ECG. ATSS-LGP shows impressive performance in CVD detection. Using the same number of labeled ECGs, it achieves at least a 5.15% increase in accuracy over pure supervised learning. Moreover, ATSS-LGP achieves comparable performance to fully supervised method using only 10% of labeled ECGs. In summary, ATSS-LGP is a suitable SSL algorithm for 12-lead ECGs, which can greatly reduce the burden of ECG labeling in deep learning. |
| ArticleNumber | 120881 |
| Author | Shi, Jiguang Luo, Deyu Li, Zhoutong Ge, Yue Zhang, Huaicheng Chang, Sheng He, Jin Huang, Qijun Liu, Wenhan Wang, Hao |
| Author_xml | – sequence: 1 givenname: Jiguang surname: Shi fullname: Shi, Jiguang organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 2 givenname: Zhoutong surname: Li fullname: Li, Zhoutong organization: Huangpu Branch of Shanghai Ninth People's Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200011, China – sequence: 3 givenname: Wenhan surname: Liu fullname: Liu, Wenhan organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 4 givenname: Huaicheng surname: Zhang fullname: Zhang, Huaicheng organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 5 givenname: Deyu surname: Luo fullname: Luo, Deyu organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 6 givenname: Yue surname: Ge fullname: Ge, Yue organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 7 givenname: Sheng orcidid: 0000-0003-4875-5501 surname: Chang fullname: Chang, Sheng organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 8 givenname: Hao surname: Wang fullname: Wang, Hao organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 9 givenname: Jin surname: He fullname: He, Jin organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China – sequence: 10 givenname: Qijun orcidid: 0000-0001-9679-5191 surname: Huang fullname: Huang, Qijun email: huangqj@whu.edu.cn organization: School of Physics and Technology, Wuhan University, Wuhan, 430072, China |
| BookMark | eNp9kMtqAzEMRb1IoUnaD-jOPzBT25knXYXQFwS6adeuxpYbh4kdbGegf98Z0lUWWQkJHaF7FmTmvENCHjjLOePV4z63LuaCiSLngjUNn5E5Y4JlTJTlLVnEuGeMFXVVzcn32lHQcEx2QJp2AePO9zrrIKKmEQ82i6cjhsFOfY8QnHU_9IBp5zU1PlAFQVs_QFSnHgLV4-LIUo0JVbLe3ZEbA33E-_-6JF8vz5-bt2z78fq-WW8zJdo6ZaZd6dIYzk2pwHBtOqWqoih4A01XIevGWal5qzvRdJ0uWQ1KcSwMrEzTtPVqSerzXRV8jAGNVDbB9EEKYHvJmZzkyL0c5chJjjzLGUl-QR6DPUD4vco8nRkcIw0Wg4zKolOobRhzS-3tFfoPS6mEnQ |
| CitedBy_id | crossref_primary_10_1016_j_autcon_2025_106228 crossref_primary_10_1016_j_knosys_2025_113173 crossref_primary_10_1016_j_ins_2024_121788 |
| Cites_doi | 10.1016/j.eswa.2020.113411 10.1007/s10489-021-02696-6 10.1038/s41597-020-0495-6 10.1109/MCAS.2012.2221521 10.1109/JBHI.2021.3060433 10.1109/JBHI.2019.2910082 10.1056/NEJMra022700 10.1016/j.cmpb.2019.105138 10.1016/j.eswa.2023.121723 10.1038/s41597-020-0386-x 10.1038/s41591-018-0268-3 10.1016/j.ins.2017.04.012 10.1016/j.knosys.2021.107187 10.3390/bios12010015 10.1016/j.cmpb.2021.106379 10.1016/j.compbiomed.2021.105114 10.1109/JBHI.2022.3173655 10.1038/s41467-020-15432-4 10.1016/j.compbiomed.2019.103378 10.1109/JBHI.2020.2980454 10.1038/s41551-022-00914-1 10.1109/JBHI.2018.2858789 10.1016/j.bspc.2021.102771 10.1016/j.engappai.2023.106230 10.3390/electronics9010121 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Inc. |
| Copyright_xml | – notice: 2024 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ins.2024.120881 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Library & Information Science |
| ExternalDocumentID | 10_1016_j_ins_2024_120881 S0020025524007953 |
| GroupedDBID | --K --M --Z -~X .DC .~1 0R~ 1B1 1OL 1RT 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AAAKG AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXKI AAXUO AAYFN ABAOU ABBOA ABEFU ABFNM ABJNI ABMAC ABTAH ABUCO ABWVN ABXDB ACDAQ ACGFS ACNNM ACRLP ACRPL ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADNMO ADTZH ADVLN AEBSH AECPX AEKER AENEX AFFNX AFJKZ AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGVJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM LG9 LY1 M41 MHUIS MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SST SSV SSW SSZ T5K TN5 TWZ UHS WH7 WUQ XPP YYP ZMT ZY4 ~02 ~G- 77I 9DU AATTM AAYWO AAYXX ACLOT ACVFH ADCNI AEIPS AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c297t-f93d5ff11f5caf1dfbcc644418a8b6e0bf1d5d19db28bbd507acc1e4fa3f88973 |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001302601600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0020-0255 |
| IngestDate | Sat Nov 29 02:44:14 EST 2025 Tue Nov 18 21:58:01 EST 2025 Sat Dec 28 15:52:45 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Cardiovascular disease detection Semi-supervised learning (SSL) Adaptive threshold Electrocardiogram (ECG) |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c297t-f93d5ff11f5caf1dfbcc644418a8b6e0bf1d5d19db28bbd507acc1e4fa3f88973 |
| ORCID | 0000-0001-9679-5191 0000-0003-4875-5501 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_ins_2024_120881 crossref_primary_10_1016_j_ins_2024_120881 elsevier_sciencedirect_doi_10_1016_j_ins_2024_120881 |
| PublicationCentury | 2000 |
| PublicationDate | August 2024 2024-08-00 |
| PublicationDateYYYYMMDD | 2024-08-01 |
| PublicationDate_xml | – month: 08 year: 2024 text: August 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | Information sciences |
| PublicationYear | 2024 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Ebrahimi, Loni, Daneshtalab, Gharehbaghi (br0070) 2020; 7 Cai, Chen, Guo, Han, Shi, Ji, Wang, Zhang, Luo (br0220) 2020; 116 Han, Shi (br0190) 2020; 185 Wang, Chen, Heng, Hou, Fan, Wu, Wang, Savvides, Shinozaki, Raj (br0330) 2022 Ribeiro, Ribeiro, Paixão, Oliveira, Gomes, Canazart, Ferreira, Andersson, Macfarlane, Meira (br0170) 2020; 11 Zhai, Zhou, Tin (br0370) 2020; 158 Zimetbaum, Josephson (br0030) 2003; 348 Bachman, Alsharif, Precup (br0310) 2014; 27 Tang, Xiao, Zhang, Lei, Wang, Xu (br0050) 2024; 237 Wang, Tang, Lei (br0060) 2023; 123 Van der Maaten, Hinton (br0500) 2008; 9 Li, Yang, Liu, Wu (br0090) 2012; 12 Otto (br0020) 2012 Hu, Yang, Hu, Nevatia (br0450) 2021 Gao, Zhang, Lu, Wang (br0120) 2019 Zhang, Wang, Hou, Wu, Wang, Okumura, Shinozaki (br0280) 2021; 34 Hammad, Alkinani, Gupta, El-Latif (br0200) 2021 Sohn, Zhang, Li, Zhang, Lee, Pfister (br0440) 2020 Xu, Shang, Ye, Qian, Li, Sun, Li, Jin (br0340) 2021 Mehari, Strodthoff (br0460) 2022; 141 Simonyan, Zisserman (br0480) 2014 Lai, Bu, Su, Zhang, Ma (br0160) 2020; 24 Liu, Ji, Chang, Wang, He, Huang (br0380) 2021; 12 Zheng, Zhang, Danioko, Yao, Guo, Rakovski (br0420) 2020; 7 Fan, Yao, Cai, Miao, Sun, Li (br0150) 2018; 22 Berthelot, Carlini, Goodfellow, Papernot, Oliver, Raffel (br0260) 2019; 32 Krishnan, Rajpurkar, Topol (br0230) 2022; 6 Krizhevsky, Hinton (br0320) 2009 Krizhevsky, Sutskever, Hinton (br0470) 2012; 25 Mensah, Roth, Fuster (br0010) 2019 Grandvalet, Bengio (br0240) 2004; 17 Lee (br0250) 2013 Laine, Aila (br0300) 2016 Ying, Zhang, Pan, Chu, Liu (br0350) 2023; 35 Liu, Wang, Huang, Chang, Wang, He (br0410) 2019; 24 Wagner, Strodthoff, Bousseljot, Kreiseler, Lunze, Samek, Schaeffter (br0430) 2020; 7 Cao, Wei, Zhang, Lin, Rodrigues, Li, Zhang (br0400) 2021; 25 Yang, Tong, Chen, Zhou (br0100) 2022; 70 Sohn, Berthelot, Carlini, Zhang, Zhang, Raffel, Cubuk, Kurakin, Li (br0270) 2020; 33 Liu, Wang, Li, Qin (br0040) 2021; 227 Tong, Ma, Chen, Wei, Shi (br0080) 2023 Zhang, Chen, Lin, Wu, Yang, Li (br0360) 2022; 26 He, Yuan, An, Zhao, Du (br0390) 2021; 210 Acharya, Fujita, Lih, Hagiwara, Tan, Adam (br0140) 2017; 405 Rai, Chatterjee (br0180) 2022; 52 Sajjadi, Javanmardi, Tasdizen (br0290) 2016; 29 Hannun, Rajpurkar, Haghpanahi, Tison, Bourn, Turakhia, Ng (br0210) 2019; 25 Liu, Jin, Liu, Qin, Lin, Shi, Tao, Zhao, Liu (br0110) 2021; 68 Zheng, Chen, Hu, Zhu, Tang, Liang (br0130) 2020; 9 He, Zhang, Ren, Sun (br0490) 2016 Krishnan (10.1016/j.ins.2024.120881_br0230) 2022; 6 Van der Maaten (10.1016/j.ins.2024.120881_br0500) 2008; 9 Zhang (10.1016/j.ins.2024.120881_br0360) 2022; 26 Zimetbaum (10.1016/j.ins.2024.120881_br0030) 2003; 348 Tang (10.1016/j.ins.2024.120881_br0050) 2024; 237 He (10.1016/j.ins.2024.120881_br0390) 2021; 210 Ebrahimi (10.1016/j.ins.2024.120881_br0070) 2020; 7 Zheng (10.1016/j.ins.2024.120881_br0130) 2020; 9 Acharya (10.1016/j.ins.2024.120881_br0140) 2017; 405 Hammad (10.1016/j.ins.2024.120881_br0200) 2021 Xu (10.1016/j.ins.2024.120881_br0340) 2021 Ying (10.1016/j.ins.2024.120881_br0350) 2023; 35 Fan (10.1016/j.ins.2024.120881_br0150) 2018; 22 Lee (10.1016/j.ins.2024.120881_br0250) 2013 Krizhevsky (10.1016/j.ins.2024.120881_br0320) 2009 Ribeiro (10.1016/j.ins.2024.120881_br0170) 2020; 11 Sohn (10.1016/j.ins.2024.120881_br0270) 2020; 33 Liu (10.1016/j.ins.2024.120881_br0040) 2021; 227 Zheng (10.1016/j.ins.2024.120881_br0420) 2020; 7 Hu (10.1016/j.ins.2024.120881_br0450) 2021 Rai (10.1016/j.ins.2024.120881_br0180) 2022; 52 Yang (10.1016/j.ins.2024.120881_br0100) 2022; 70 Mehari (10.1016/j.ins.2024.120881_br0460) 2022; 141 Lai (10.1016/j.ins.2024.120881_br0160) 2020; 24 Liu (10.1016/j.ins.2024.120881_br0110) 2021; 68 Gao (10.1016/j.ins.2024.120881_br0120) 2019 Wang (10.1016/j.ins.2024.120881_br0330) Hannun (10.1016/j.ins.2024.120881_br0210) 2019; 25 Han (10.1016/j.ins.2024.120881_br0190) 2020; 185 Li (10.1016/j.ins.2024.120881_br0090) 2012; 12 Cao (10.1016/j.ins.2024.120881_br0400) 2021; 25 Mensah (10.1016/j.ins.2024.120881_br0010) 2019 Liu (10.1016/j.ins.2024.120881_br0380) 2021; 12 Wagner (10.1016/j.ins.2024.120881_br0430) 2020; 7 Zhai (10.1016/j.ins.2024.120881_br0370) 2020; 158 Simonyan (10.1016/j.ins.2024.120881_br0480) Bachman (10.1016/j.ins.2024.120881_br0310) 2014; 27 Krizhevsky (10.1016/j.ins.2024.120881_br0470) 2012; 25 Laine (10.1016/j.ins.2024.120881_br0300) Tong (10.1016/j.ins.2024.120881_br0080) 2023 Grandvalet (10.1016/j.ins.2024.120881_br0240) 2004; 17 Berthelot (10.1016/j.ins.2024.120881_br0260) 2019; 32 Otto (10.1016/j.ins.2024.120881_br0020) 2012 Zhang (10.1016/j.ins.2024.120881_br0280) 2021; 34 Wang (10.1016/j.ins.2024.120881_br0060) 2023; 123 Cai (10.1016/j.ins.2024.120881_br0220) 2020; 116 He (10.1016/j.ins.2024.120881_br0490) 2016 Liu (10.1016/j.ins.2024.120881_br0410) 2019; 24 Sohn (10.1016/j.ins.2024.120881_br0440) Sajjadi (10.1016/j.ins.2024.120881_br0290) 2016; 29 |
| References_xml | – year: 2022 ident: br0330 article-title: Freematch: self-adaptive thresholding for semi-supervised learning – volume: 33 start-page: 596 year: 2020 end-page: 608 ident: br0270 article-title: Fixmatch: simplifying semi-supervised learning with consistency and confidence publication-title: Adv. Neural Inf. Process. Syst. – volume: 17 year: 2004 ident: br0240 article-title: Semi-supervised learning by entropy minimization publication-title: Adv. Neural Inf. Process. Syst. – start-page: 11525 year: 2021 end-page: 11536 ident: br0340 article-title: Dash: semi-supervised learning with dynamic thresholding publication-title: International Conference on Machine Learning – start-page: 770 year: 2016 end-page: 778 ident: br0490 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 12 start-page: 33 year: 2012 end-page: 46 ident: br0090 article-title: Bridging time series dynamics and complex network theory with application to electrocardiogram analysis publication-title: IEEE Circuits Syst. Mag. – volume: 7 start-page: 154 year: 2020 ident: br0430 article-title: Ptb-xl, a large publicly available electrocardiography dataset publication-title: Sci. Data – volume: 123 year: 2023 ident: br0060 article-title: A q-learning artificial bee colony for distributed assembly flow shop scheduling with factory eligibility, transportation capacity and setup time publication-title: Eng. Appl. Artif. Intell. – start-page: 1 year: 2021 end-page: 13 ident: br0200 article-title: Myocardial infarction detection based on deep neural network on imbalanced data publication-title: Multimed. Syst. – volume: 52 start-page: 5366 year: 2022 end-page: 5384 ident: br0180 article-title: Hybrid cnn-lstm deep learning model and ensemble technique for automatic detection of myocardial infarction using big ecg data publication-title: Appl. Intell. – start-page: 2019 year: 2019 ident: br0120 article-title: An effective lstm recurrent network to detect arrhythmia on imbalanced ecg dataset publication-title: J. Healthcare Eng. – volume: 116 year: 2020 ident: br0220 article-title: Accurate detection of atrial fibrillation from 12-lead ecg using deep neural network publication-title: Comput. Biol. Med. – volume: 32 year: 2019 ident: br0260 article-title: Mixmatch: a holistic approach to semi-supervised learning publication-title: Adv. Neural Inf. Process. Syst. – volume: 22 start-page: 1744 year: 2018 end-page: 1753 ident: br0150 article-title: Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ecg recordings publication-title: IEEE J. Biomed. Health Inform. – start-page: 896 year: 2013 ident: br0250 article-title: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks publication-title: Workshop on Challenges in Representation Learning, ICML, vol. 3 – volume: 29 year: 2016 ident: br0290 article-title: Regularization with stochastic transformations and perturbations for deep semi-supervised learning publication-title: Adv. Neural Inf. Process. Syst. – volume: 24 start-page: 503 year: 2019 end-page: 514 ident: br0410 article-title: Mfb-cbrnn: a hybrid network for mi detection using 12-lead ecgs publication-title: IEEE J. Biomed. Health Inform. – volume: 11 start-page: 1760 year: 2020 ident: br0170 article-title: Automatic diagnosis of the 12-lead ecg using a deep neural network publication-title: Nat. Commun. – volume: 25 year: 2012 ident: br0470 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inf. Process. Syst. – volume: 26 start-page: 3791 year: 2022 end-page: 3801 ident: br0360 article-title: Semi-supervised learning for automatic atrial fibrillation detection in 24-hour holter monitoring publication-title: IEEE J. Biomed. Health Inform. – volume: 9 start-page: 121 year: 2020 ident: br0130 article-title: An automatic diagnosis of arrhythmias using a combination of cnn and lstm technology publication-title: Electronics – volume: 6 start-page: 1346 year: 2022 end-page: 1352 ident: br0230 article-title: Self-supervised learning in medicine and healthcare publication-title: Nature Biomed. Eng. – volume: 68 year: 2021 ident: br0110 article-title: Precise and efficient heartbeat classification using a novel lightweight-modified method publication-title: Biomed. Signal Process. Control – year: 2016 ident: br0300 article-title: Temporal ensembling for semi-supervised learning – volume: 227 year: 2021 ident: br0040 article-title: Deep learning in ecg diagnosis: a review publication-title: Knowl.-Based Syst. – year: 2009 ident: br0320 article-title: Learning Multiple Layers of Features from Tiny Images – volume: 185 year: 2020 ident: br0190 article-title: Ml–resnet: a novel network to detect and locate myocardial infarction using 12 leads ecg publication-title: Comput. Methods Programs Biomed. – volume: 348 start-page: 933 year: 2003 end-page: 940 ident: br0030 article-title: Use of the electrocardiogram in acute myocardial infarction publication-title: N. Engl. J. Med. – year: 2019 ident: br0010 article-title: The Global Burden of Cardiovascular Diseases and Risk Factors: 2020 and Beyond – volume: 24 start-page: 1569 year: 2020 end-page: 1578 ident: br0160 article-title: Non-standardized patch-based ecg lead together with deep learning based algorithm for automatic screening of atrial fibrillation publication-title: IEEE J. Biomed. Health Inform. – volume: 25 start-page: 3721 year: 2021 end-page: 3731 ident: br0400 article-title: Ml-net: multi-channel lightweight network for detecting myocardial infarction publication-title: IEEE J. Biomed. Health Inform. – volume: 405 start-page: 81 year: 2017 end-page: 90 ident: br0140 article-title: Automated detection of arrhythmias using different intervals of tachycardia ecg segments with convolutional neural network publication-title: Inf. Sci. – volume: 9 year: 2008 ident: br0500 article-title: Visualizing data using t-sne publication-title: J. Mach. Learn. Res. – volume: 141 year: 2022 ident: br0460 article-title: Self-supervised representation learning from 12-lead ecg data publication-title: Comput. Biol. Med. – volume: 237 year: 2024 ident: br0050 article-title: A dql-nsga-iii algorithm for solving the flexible job shop dynamic scheduling problem publication-title: Expert Syst. Appl. – year: 2012 ident: br0020 article-title: Practice of Clinical Echocardiography e-Book – volume: 70 start-page: 1555 year: 2022 end-page: 1559 ident: br0100 article-title: Fixed-time synchronization and energy consumption for kuramoto-oscillator networks with multilayer distributed control publication-title: IEEE Trans. Circuits Syst. II, Express Briefs – volume: 7 start-page: 48 year: 2020 ident: br0420 article-title: A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients publication-title: Sci. Data – volume: 35 year: 2023 ident: br0350 article-title: Fedecg: a federated semi-supervised learning framework for electrocardiogram abnormalities prediction publication-title: J. King Saud Univ, Comput. Inf. Sci. – start-page: 15099 year: 2021 end-page: 15108 ident: br0450 article-title: Simple: similar pseudo label exploitation for semi-supervised classification publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – year: 2023 ident: br0080 article-title: Finite-time synchronization and energy consumption prediction for multilayer fractional-order networks publication-title: IEEE Trans. Circuits Syst. II, Express Briefs – volume: 25 start-page: 65 year: 2019 end-page: 69 ident: br0210 article-title: Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network publication-title: Nat. Med. – volume: 27 year: 2014 ident: br0310 article-title: Learning with pseudo-ensembles publication-title: Adv. Neural Inf. Process. Syst. – year: 2020 ident: br0440 article-title: A simple semi-supervised learning framework for object detection – year: 2014 ident: br0480 article-title: Very deep convolutional networks for large-scale image recognition – volume: 158 year: 2020 ident: br0370 article-title: Semi-supervised learning for ecg classification without patient-specific labeled data publication-title: Expert Syst. Appl. – volume: 12 start-page: 15 year: 2021 ident: br0380 article-title: Evombn: evolving multi-branch networks on myocardial infarction diagnosis using 12-lead electrocardiograms publication-title: Biosensors – volume: 7 start-page: 100033 year: 2020 ident: br0070 article-title: A review on deep learning methods for ecg arrhythmia classification publication-title: Expert Syst. Appl. – volume: 210 year: 2021 ident: br0390 article-title: Mfb-lann: a lightweight and updatable myocardial infarction diagnosis system based on convolutional neural networks and active learning publication-title: Comput. Methods Programs Biomed. – volume: 34 start-page: 18408 year: 2021 end-page: 18419 ident: br0280 article-title: Flexmatch: boosting semi-supervised learning with curriculum pseudo labeling publication-title: Adv. Neural Inf. Process. Syst. – volume: 70 start-page: 1555 issue: 4 year: 2022 ident: 10.1016/j.ins.2024.120881_br0100 article-title: Fixed-time synchronization and energy consumption for kuramoto-oscillator networks with multilayer distributed control publication-title: IEEE Trans. Circuits Syst. II, Express Briefs – volume: 158 year: 2020 ident: 10.1016/j.ins.2024.120881_br0370 article-title: Semi-supervised learning for ecg classification without patient-specific labeled data publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2020.113411 – volume: 52 start-page: 5366 issue: 5 year: 2022 ident: 10.1016/j.ins.2024.120881_br0180 article-title: Hybrid cnn-lstm deep learning model and ensemble technique for automatic detection of myocardial infarction using big ecg data publication-title: Appl. Intell. doi: 10.1007/s10489-021-02696-6 – start-page: 770 year: 2016 ident: 10.1016/j.ins.2024.120881_br0490 article-title: Deep residual learning for image recognition – year: 2019 ident: 10.1016/j.ins.2024.120881_br0010 – volume: 7 start-page: 154 issue: 1 year: 2020 ident: 10.1016/j.ins.2024.120881_br0430 article-title: Ptb-xl, a large publicly available electrocardiography dataset publication-title: Sci. Data doi: 10.1038/s41597-020-0495-6 – volume: 12 start-page: 33 issue: 4 year: 2012 ident: 10.1016/j.ins.2024.120881_br0090 article-title: Bridging time series dynamics and complex network theory with application to electrocardiogram analysis publication-title: IEEE Circuits Syst. Mag. doi: 10.1109/MCAS.2012.2221521 – volume: 25 start-page: 3721 issue: 10 year: 2021 ident: 10.1016/j.ins.2024.120881_br0400 article-title: Ml-net: multi-channel lightweight network for detecting myocardial infarction publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2021.3060433 – volume: 24 start-page: 503 issue: 2 year: 2019 ident: 10.1016/j.ins.2024.120881_br0410 article-title: Mfb-cbrnn: a hybrid network for mi detection using 12-lead ecgs publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2019.2910082 – volume: 348 start-page: 933 issue: 10 year: 2003 ident: 10.1016/j.ins.2024.120881_br0030 article-title: Use of the electrocardiogram in acute myocardial infarction publication-title: N. Engl. J. Med. doi: 10.1056/NEJMra022700 – volume: 9 issue: 11 year: 2008 ident: 10.1016/j.ins.2024.120881_br0500 article-title: Visualizing data using t-sne publication-title: J. Mach. Learn. Res. – ident: 10.1016/j.ins.2024.120881_br0480 – volume: 34 start-page: 18408 year: 2021 ident: 10.1016/j.ins.2024.120881_br0280 article-title: Flexmatch: boosting semi-supervised learning with curriculum pseudo labeling publication-title: Adv. Neural Inf. Process. Syst. – volume: 33 start-page: 596 year: 2020 ident: 10.1016/j.ins.2024.120881_br0270 article-title: Fixmatch: simplifying semi-supervised learning with consistency and confidence publication-title: Adv. Neural Inf. Process. Syst. – volume: 185 year: 2020 ident: 10.1016/j.ins.2024.120881_br0190 article-title: Ml–resnet: a novel network to detect and locate myocardial infarction using 12 leads ecg publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2019.105138 – volume: 237 year: 2024 ident: 10.1016/j.ins.2024.120881_br0050 article-title: A dql-nsga-iii algorithm for solving the flexible job shop dynamic scheduling problem publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.121723 – volume: 7 start-page: 48 issue: 1 year: 2020 ident: 10.1016/j.ins.2024.120881_br0420 article-title: A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients publication-title: Sci. Data doi: 10.1038/s41597-020-0386-x – year: 2023 ident: 10.1016/j.ins.2024.120881_br0080 article-title: Finite-time synchronization and energy consumption prediction for multilayer fractional-order networks publication-title: IEEE Trans. Circuits Syst. II, Express Briefs – start-page: 11525 year: 2021 ident: 10.1016/j.ins.2024.120881_br0340 article-title: Dash: semi-supervised learning with dynamic thresholding – volume: 25 start-page: 65 issue: 1 year: 2019 ident: 10.1016/j.ins.2024.120881_br0210 article-title: Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network publication-title: Nat. Med. doi: 10.1038/s41591-018-0268-3 – start-page: 1 year: 2021 ident: 10.1016/j.ins.2024.120881_br0200 article-title: Myocardial infarction detection based on deep neural network on imbalanced data publication-title: Multimed. Syst. – volume: 405 start-page: 81 year: 2017 ident: 10.1016/j.ins.2024.120881_br0140 article-title: Automated detection of arrhythmias using different intervals of tachycardia ecg segments with convolutional neural network publication-title: Inf. Sci. doi: 10.1016/j.ins.2017.04.012 – volume: 227 year: 2021 ident: 10.1016/j.ins.2024.120881_br0040 article-title: Deep learning in ecg diagnosis: a review publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2021.107187 – volume: 12 start-page: 15 issue: 1 year: 2021 ident: 10.1016/j.ins.2024.120881_br0380 article-title: Evombn: evolving multi-branch networks on myocardial infarction diagnosis using 12-lead electrocardiograms publication-title: Biosensors doi: 10.3390/bios12010015 – volume: 210 year: 2021 ident: 10.1016/j.ins.2024.120881_br0390 article-title: Mfb-lann: a lightweight and updatable myocardial infarction diagnosis system based on convolutional neural networks and active learning publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2021.106379 – start-page: 2019 year: 2019 ident: 10.1016/j.ins.2024.120881_br0120 article-title: An effective lstm recurrent network to detect arrhythmia on imbalanced ecg dataset publication-title: J. Healthcare Eng. – volume: 141 year: 2022 ident: 10.1016/j.ins.2024.120881_br0460 article-title: Self-supervised representation learning from 12-lead ecg data publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2021.105114 – volume: 26 start-page: 3791 issue: 8 year: 2022 ident: 10.1016/j.ins.2024.120881_br0360 article-title: Semi-supervised learning for automatic atrial fibrillation detection in 24-hour holter monitoring publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2022.3173655 – ident: 10.1016/j.ins.2024.120881_br0300 – volume: 29 year: 2016 ident: 10.1016/j.ins.2024.120881_br0290 article-title: Regularization with stochastic transformations and perturbations for deep semi-supervised learning publication-title: Adv. Neural Inf. Process. Syst. – start-page: 15099 year: 2021 ident: 10.1016/j.ins.2024.120881_br0450 article-title: Simple: similar pseudo label exploitation for semi-supervised classification – volume: 11 start-page: 1760 issue: 1 year: 2020 ident: 10.1016/j.ins.2024.120881_br0170 article-title: Automatic diagnosis of the 12-lead ecg using a deep neural network publication-title: Nat. Commun. doi: 10.1038/s41467-020-15432-4 – volume: 116 year: 2020 ident: 10.1016/j.ins.2024.120881_br0220 article-title: Accurate detection of atrial fibrillation from 12-lead ecg using deep neural network publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2019.103378 – volume: 24 start-page: 1569 issue: 6 year: 2020 ident: 10.1016/j.ins.2024.120881_br0160 article-title: Non-standardized patch-based ecg lead together with deep learning based algorithm for automatic screening of atrial fibrillation publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2020.2980454 – volume: 6 start-page: 1346 issue: 12 year: 2022 ident: 10.1016/j.ins.2024.120881_br0230 article-title: Self-supervised learning in medicine and healthcare publication-title: Nature Biomed. Eng. doi: 10.1038/s41551-022-00914-1 – volume: 27 year: 2014 ident: 10.1016/j.ins.2024.120881_br0310 article-title: Learning with pseudo-ensembles publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.ins.2024.120881_br0440 – volume: 17 year: 2004 ident: 10.1016/j.ins.2024.120881_br0240 article-title: Semi-supervised learning by entropy minimization publication-title: Adv. Neural Inf. Process. Syst. – volume: 7 start-page: 100033 year: 2020 ident: 10.1016/j.ins.2024.120881_br0070 article-title: A review on deep learning methods for ecg arrhythmia classification publication-title: Expert Syst. Appl. – volume: 22 start-page: 1744 issue: 6 year: 2018 ident: 10.1016/j.ins.2024.120881_br0150 article-title: Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ecg recordings publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2018.2858789 – volume: 25 year: 2012 ident: 10.1016/j.ins.2024.120881_br0470 article-title: Imagenet classification with deep convolutional neural networks publication-title: Adv. Neural Inf. Process. Syst. – ident: 10.1016/j.ins.2024.120881_br0330 – volume: 68 year: 2021 ident: 10.1016/j.ins.2024.120881_br0110 article-title: Precise and efficient heartbeat classification using a novel lightweight-modified method publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.102771 – volume: 123 year: 2023 ident: 10.1016/j.ins.2024.120881_br0060 article-title: A q-learning artificial bee colony for distributed assembly flow shop scheduling with factory eligibility, transportation capacity and setup time publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2023.106230 – volume: 32 year: 2019 ident: 10.1016/j.ins.2024.120881_br0260 article-title: Mixmatch: a holistic approach to semi-supervised learning publication-title: Adv. Neural Inf. Process. Syst. – volume: 35 issue: 6 year: 2023 ident: 10.1016/j.ins.2024.120881_br0350 article-title: Fedecg: a federated semi-supervised learning framework for electrocardiogram abnormalities prediction publication-title: J. King Saud Univ, Comput. Inf. Sci. – year: 2012 ident: 10.1016/j.ins.2024.120881_br0020 – year: 2009 ident: 10.1016/j.ins.2024.120881_br0320 – volume: 9 start-page: 121 issue: 1 year: 2020 ident: 10.1016/j.ins.2024.120881_br0130 article-title: An automatic diagnosis of arrhythmias using a combination of cnn and lstm technology publication-title: Electronics doi: 10.3390/electronics9010121 – start-page: 896 year: 2013 ident: 10.1016/j.ins.2024.120881_br0250 article-title: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks |
| SSID | ssj0004766 |
| Score | 2.4624882 |
| Snippet | Deep cardiovascular disease (CVD) detection usually achieves good performance with large-scale labeled electrocardiograms (ECGs), but manual labeling of ECGs... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 120881 |
| SubjectTerms | Adaptive threshold Cardiovascular disease detection Electrocardiogram (ECG) Semi-supervised learning (SSL) |
| Title | An adaptive threshold-based semi-supervised learning method for cardiovascular disease detection |
| URI | https://dx.doi.org/10.1016/j.ins.2024.120881 |
| Volume | 677 |
| WOSCitedRecordID | wos001302601600001&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 issn: 0020-0255 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0004766 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELfKxgM8IBggxhjyA-KByihOnMZ5rNDQmNCExEAVL8GfW6eSVWsy7c_f2XE-Wm2IPfAStZZzjXq_nM_n390h9E4zFiVcRCQ1PnTDKMmFVoQLYaTMqOS-2PPPr9nxMZ_N8m-jUd3mwlwtsrLk19f58r-qGsZA2S519h7q7oTCAHwGpcMV1A7Xf1L8tBwLLZaeElSBplbugIm41UqPV-bPnKzqpTMQ7vuiDYw0jaQ951CtM1TDCc5Ym8qztsqhOxuSmTyGwlra-ejffbvg8dH8tBZheXTEHz_46-yiBqdzMFp7sp8pz3q0drHsw1o4wmqYHkIUMesIcn3KQETc5mVodiehfUtjOGkM5o7eatOb8MI5bERcefWYfeznrtfP3ljXOrZhS2Q7L0BE4UQUjYgHaDvO0hzs-fb0y8HsqE-ozZpD7va52-NwTwzceI7bHZqBk3LyFD0Juws8bVDxDI1MuYMeD2pO7qD9kKmC3-OB9nCw8c_R72mJW_zgDfzgDfzgFj-4wQ8GeXgdPzjgB3f4eYF-fD44-XRIQhsOouI8q4jNE51aS6lNlbBUW6kUeNGMcsHlxEQSxlJNcy1jLqWGDYZQihpmRWI5z7PkJdoqL0rzCmE6iXNGIwsOkWWZZlIznYh44sIGGWw0dlHU_peFCjXqXauURXGnDnfRh-6WZVOg5W-TWaugIrwVjedYANjuvu31fX5jDz3q34E3aKu6rM0-eqiuqvnq8m1A2g1q0p9k |
| 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=An+adaptive+threshold-based+semi-supervised+learning+method+for+cardiovascular+disease+detection&rft.jtitle=Information+sciences&rft.au=Shi%2C+Jiguang&rft.au=Li%2C+Zhoutong&rft.au=Liu%2C+Wenhan&rft.au=Zhang%2C+Huaicheng&rft.date=2024-08-01&rft.issn=0020-0255&rft.volume=677&rft.spage=120881&rft_id=info:doi/10.1016%2Fj.ins.2024.120881&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ins_2024_120881 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0020-0255&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0020-0255&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0020-0255&client=summon |