Deep learning evaluation of biomarkers from echocardiogram videos
Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding d...
Saved in:
Published in | EBioMedicine Vol. 73; p. 103613 |
---|---|
Main Authors | , , , , , , , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Netherlands
Elsevier B.V
01.11.2021
Elsevier |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results.
We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets.
On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques.
These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods.
J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship. |
---|---|
AbstractList | BACKGROUNDLaboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results. METHODSWe developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets. FINDINGSOn the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques. INTERPRETATIONThese results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods. FUNDINGJ.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship. Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results. We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets. On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques. These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods. J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship. Background: Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results. Methods: We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets. Findings: On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques. Interpretation: These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods. Funding: J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship. |
ArticleNumber | 103613 |
Author | Tooley, James E. Zou, James Y. Cheng, Susan Liang, David H. Hughes, J Weston Ouyang, Jiahong Lungren, Matthew P. Lee, Jasper Ashley, Euan A. Schnittger, Ingela Yuan, Neal Nieman, Koen Chen, Jonathan H. Theurer, John Ebinger, Joseph Botting, Patrick He, Bryan Ouyang, David |
Author_xml | – sequence: 1 givenname: J Weston surname: Hughes fullname: Hughes, J Weston organization: Department of Computer Science, Stanford University, Palo Alto, CA 94025 – sequence: 2 givenname: Neal surname: Yuan fullname: Yuan, Neal organization: Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048 – sequence: 3 givenname: Bryan surname: He fullname: He, Bryan organization: Department of Computer Science, Stanford University, Palo Alto, CA 94025 – sequence: 4 givenname: Jiahong surname: Ouyang fullname: Ouyang, Jiahong organization: Department of Electrical Engineering, Stanford University, Palo Alto, CA, 94025 – sequence: 5 givenname: Joseph surname: Ebinger fullname: Ebinger, Joseph organization: Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048 – sequence: 6 givenname: Patrick surname: Botting fullname: Botting, Patrick organization: Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048 – sequence: 7 givenname: Jasper surname: Lee fullname: Lee, Jasper organization: Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048 – sequence: 8 givenname: John surname: Theurer fullname: Theurer, John organization: Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048 – sequence: 9 givenname: James E. surname: Tooley fullname: Tooley, James E. organization: Department of Medicine, Stanford University, Palo Alto, CA, 94025 – sequence: 10 givenname: Koen surname: Nieman fullname: Nieman, Koen organization: Department of Medicine, Stanford University, Palo Alto, CA, 94025 – sequence: 11 givenname: Matthew P. surname: Lungren fullname: Lungren, Matthew P. organization: Department of Radiology, Stanford University, Palo Alto, CA, 94025 – sequence: 12 givenname: David H. orcidid: 0000-0002-7343-7583 surname: Liang fullname: Liang, David H. organization: Department of Medicine, Stanford University, Palo Alto, CA, 94025 – sequence: 13 givenname: Ingela surname: Schnittger fullname: Schnittger, Ingela organization: Department of Medicine, Stanford University, Palo Alto, CA, 94025 – sequence: 14 givenname: Jonathan H. surname: Chen fullname: Chen, Jonathan H. organization: Department of Medicine, Stanford University, Palo Alto, CA, 94025 – sequence: 15 givenname: Euan A. surname: Ashley fullname: Ashley, Euan A. organization: Department of Medicine, Stanford University, Palo Alto, CA, 94025 – sequence: 16 givenname: Susan surname: Cheng fullname: Cheng, Susan organization: Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048 – sequence: 17 givenname: David orcidid: 0000-0002-3813-7518 surname: Ouyang fullname: Ouyang, David email: david.ouyang@cshs.org organization: Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048 – sequence: 18 givenname: James Y. surname: Zou fullname: Zou, James Y. email: jamesz@stanford.edu organization: Department of Computer Science, Stanford University, Palo Alto, CA 94025 |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34656880$$D View this record in MEDLINE/PubMed |
BookMark | eNp9Uctu1DAUtVARLaVfgISyZDOD304WIFXlVakSG1hbN_b11EMSD3ZmpP49nqZU7YaVrXvP4-qc1-RkShMS8pbRNaNMf9iusY9pXHPKWZ0IzcQLcsaF4ivRaXny5H9KLkrZUkqZknXYviKnQmql25aekcvPiLtmQMhTnDYNHmDYwxzT1KTQHB0g_8ZcmpDT2KC7TQ6yj2mTYWwO0WMqb8jLAEPBi4f3nPz6-uXn1ffVzY9v11eXNyunuJpXneyCAN3S0BvvoeMoETsMijLDW-5YMMZIMKYXzINzvVZcg5Gd5Fx6dOKcXC-6PsHW7nKsp93ZBNHeD1LeWMhzdANar4Vj2B9ZnaTVrFOmB48qeMpbaarWp0Vrt-9H9A6nOcPwTPT5Zoq3dpMOtlVc1rSrwPsHgZz-7LHMdozF4TDAhGlfLFetENxIzStULFCXUykZw6MNo_bYpd3a-y7tsUu7dFlZ755e-Mj511wFfFwAWDM_RMy2uIiTQx8zurmGEv9r8BcRLLOY |
CitedBy_id | crossref_primary_10_1038_s41598_023_50735_8 crossref_primary_10_1007_s40119_024_00368_3 crossref_primary_10_3390_electronics11111800 crossref_primary_10_1053_j_jvca_2024_02_004 crossref_primary_10_1093_ehjdh_ztad077 crossref_primary_10_1161_CIRCOUTCOMES_122_009055 crossref_primary_10_1016_j_jemermed_2023_02_005 crossref_primary_10_1038_s41746_022_00720_8 crossref_primary_10_1039_D3SM01337E crossref_primary_10_3389_fcvm_2022_941148 crossref_primary_10_1109_TMI_2022_3229136 crossref_primary_10_15420_aer_2022_42 crossref_primary_10_1016_j_athoracsur_2022_05_023 crossref_primary_10_1063_5_0176850 crossref_primary_10_3389_fdgth_2023_1201392 crossref_primary_10_1016_j_mayocp_2023_01_012 crossref_primary_10_1016_S2589_7500_23_00022_5 crossref_primary_10_1038_s42256_022_00516_1 crossref_primary_10_1038_s43018_022_00436_4 crossref_primary_10_1016_j_xcrm_2022_100869 crossref_primary_10_1161_CIRCIMAGING_123_015495 crossref_primary_10_1038_s41591_022_01981_2 crossref_primary_10_1109_ACCESS_2023_3260652 |
Cites_doi | 10.1016/j.echo.2010.12.008 10.1038/s41551-020-0578-x 10.1016/S0140-6736(10)60452-7 10.1038/s41746-019-0192-z 10.1093/ndt/gfz206 10.1148/radiol.2020200642 10.1016/j.jacc.2015.10.090 10.1016/S2589-7500(20)30108-4 10.1016/S0140-6736(19)31721-0 10.1161/CIRCULATIONAHA.118.034338 10.1038/s41586-020-2145-8 10.1038/s41586-019-1876-x 10.1038/s41551-018-0195-0 10.1161/CIRCEP.119.007284 10.1038/s41591-020-1010-5 10.1016/j.cell.2012.02.009 10.1016/j.jacc.2019.12.030 10.1038/s41746-019-0216-8 10.1038/s41591-020-0870-z 10.1016/j.jelectrocard.2020.02.008 |
ContentType | Journal Article |
Copyright | 2021 The Authors Copyright © 2021 The Authors. Published by Elsevier B.V. All rights reserved. 2021 The Authors 2021 |
Copyright_xml | – notice: 2021 The Authors – notice: Copyright © 2021 The Authors. Published by Elsevier B.V. All rights reserved. – notice: 2021 The Authors 2021 |
DBID | 6I. AAFTH CGR CUY CVF ECM EIF NPM AAYXX CITATION 7X8 5PM DOA |
DOI | 10.1016/j.ebiom.2021.103613 |
DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) CrossRef MEDLINE - Academic |
DatabaseTitleList | MEDLINE - Academic MEDLINE |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Biology |
EISSN | 2352-3964 |
EndPage | 103613 |
ExternalDocumentID | oai_doaj_org_article_d63c1ebdec3940da9957bade5fd02847 10_1016_j_ebiom_2021_103613 34656880 S2352396421004060 |
Genre | Journal Article |
GrantInformation | J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship. |
GrantInformation_xml | – fundername: NIMHD NIH HHS grantid: R21 MD012867 – fundername: NIA NIH HHS grantid: P30 AG059307 – fundername: NHLBI NIH HHS grantid: K99 HL157421 |
GroupedDBID | .1- .FO 0R~ 0SF 4.4 457 53G 5VS 6I. AACTN AAEDT AAEDW AAFTH AAIKJ AALRI AAXUO ABMAC ACGFS ADBBV ADEZE ADRAZ AEXQZ AFCTW AFRHN AFTJW AGHFR AITUG AJUYK ALMA_UNASSIGNED_HOLDINGS AMRAJ AOIJS BCNDV EBS EJD FDB GROUPED_DOAJ HYE HZ~ IPNFZ KQ8 M41 M48 NCXOZ O9- OK1 RIG ROL RPM SSZ Z5R AAMRU ADVLN AKRWK CGR CUY CVF ECM EIF NPM AAYXX CITATION 7X8 5PM |
ID | FETCH-LOGICAL-c525t-949f3a680fb7dda92e4ee9ef5017282c1f7774a77b31daccb6526a7494224dec3 |
IEDL.DBID | RPM |
ISSN | 2352-3964 |
IngestDate | Tue Oct 22 15:12:35 EDT 2024 Tue Sep 17 21:33:25 EDT 2024 Fri Oct 25 23:33:13 EDT 2024 Thu Sep 26 16:14:19 EDT 2024 Sat Sep 28 08:21:44 EDT 2024 Tue Jul 25 20:58:58 EDT 2023 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Deep learning Artificial intelligence Echocardiography |
Language | English |
License | This is an open access article under the CC BY-NC-ND license. Copyright © 2021 The Authors. Published by Elsevier B.V. All rights reserved. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c525t-949f3a680fb7dda92e4ee9ef5017282c1f7774a77b31daccb6526a7494224dec3 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 To whom correspondence should be addressed. Co-senior author |
ORCID | 0000-0002-7343-7583 0000-0002-3813-7518 |
OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8524103/ |
PMID | 34656880 |
PQID | 2583327462 |
PQPubID | 23479 |
PageCount | 1 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_d63c1ebdec3940da9957bade5fd02847 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8524103 proquest_miscellaneous_2583327462 crossref_primary_10_1016_j_ebiom_2021_103613 pubmed_primary_34656880 elsevier_sciencedirect_doi_10_1016_j_ebiom_2021_103613 |
PublicationCentury | 2000 |
PublicationDate | 2021-11-01 |
PublicationDateYYYYMMDD | 2021-11-01 |
PublicationDate_xml | – month: 11 year: 2021 text: 2021-11-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Netherlands |
PublicationPlace_xml | – name: Netherlands |
PublicationTitle | EBioMedicine |
PublicationTitleAlternate | EBioMedicine |
PublicationYear | 2021 |
Publisher | Elsevier B.V Elsevier |
Publisher_xml | – name: Elsevier B.V – name: Elsevier |
References | Grossman (bib0005) 2018 Poplin (bib0008) 2018; 2 Owens (bib0007) 2019; 321 Ghorbani (bib0009) 2020; 3 He (bib0013) 2020; 4 Hunter, Bailey (bib0020) 2019; 34 Ashley (bib0001) 2010; 375 Dauvin (bib0010) 2019; 2 Bibbins-Domingo (bib0006) 2016 Kwon (bib0014) 2020; 59 Chen (bib0002) 2012; 148 Papolos, Narula, Bavishi, Chaudhry, Sengupta (bib0016) 2016; 67 Jackson (bib0003) 2020; 578 Attia (bib0012) 2019; 394 Ouyang (bib0019) 2020; 580 Carreira, Zissmerman (bib0025) 2017 Avram (bib0011) 2020; 26 Douglas (bib0017) 2011; 24 Ai (bib0004) 2020; 296 Attia (bib0021) 2019; 12 Raghunath (bib0022) 2020 Zhang (bib0018) 2018; 138 Kwon (bib0023) 2020; 2 Ko (bib0015) 2020; 75 Tran (bib0024) 2018 Zhang (10.1016/j.ebiom.2021.103613_bib0018) 2018; 138 Ashley (10.1016/j.ebiom.2021.103613_bib0001) 2010; 375 Kwon (10.1016/j.ebiom.2021.103613_bib0014) 2020; 59 Hunter (10.1016/j.ebiom.2021.103613_bib0020) 2019; 34 Attia (10.1016/j.ebiom.2021.103613_bib0021) 2019; 12 Grossman (10.1016/j.ebiom.2021.103613_bib0005) 2018 Ko (10.1016/j.ebiom.2021.103613_bib0015) 2020; 75 Ouyang (10.1016/j.ebiom.2021.103613_bib0019) 2020; 580 Jackson (10.1016/j.ebiom.2021.103613_bib0003) 2020; 578 Bibbins-Domingo (10.1016/j.ebiom.2021.103613_bib0006) 2016 Ai (10.1016/j.ebiom.2021.103613_bib0004) 2020; 296 Dauvin (10.1016/j.ebiom.2021.103613_bib0010) 2019; 2 Owens (10.1016/j.ebiom.2021.103613_bib0007) 2019; 321 He (10.1016/j.ebiom.2021.103613_bib0013) 2020; 4 Avram (10.1016/j.ebiom.2021.103613_bib0011) 2020; 26 Papolos (10.1016/j.ebiom.2021.103613_bib0016) 2016; 67 Attia (10.1016/j.ebiom.2021.103613_bib0012) 2019; 394 Tran (10.1016/j.ebiom.2021.103613_bib0024) 2018 Poplin (10.1016/j.ebiom.2021.103613_bib0008) 2018; 2 Kwon (10.1016/j.ebiom.2021.103613_bib0023) 2020; 2 Raghunath (10.1016/j.ebiom.2021.103613_bib0022) 2020 Carreira (10.1016/j.ebiom.2021.103613_bib0025) 2017 Douglas (10.1016/j.ebiom.2021.103613_bib0017) 2011; 24 Chen (10.1016/j.ebiom.2021.103613_bib0002) 2012; 148 Ghorbani (10.1016/j.ebiom.2021.103613_bib0009) 2020; 3 |
References_xml | – volume: 26 start-page: 1576 year: 2020 end-page: 1582 ident: bib0011 article-title: A digital biomarker of diabetes from smartphone-based vascular signals publication-title: Nat. Med. contributor: fullname: Avram – start-page: 315 year: 2016 ident: bib0006 article-title: Screening for colorectal cancer: US preventive services task force recommendation statement publication-title: JAMA contributor: fullname: Bibbins-Domingo – volume: 2 start-page: 158 year: 2018 end-page: 164 ident: bib0008 article-title: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning publication-title: Nat. Biomed. Eng. contributor: fullname: Poplin – volume: 75 year: 2020 ident: bib0015 article-title: Detection of hypertrophic cardiomyopathy using a convolutional neural network-enabled electrocardiogram publication-title: J. Am. Coll. Cardiol. contributor: fullname: Ko – volume: 148 start-page: 1293 year: 2012 end-page: 1307 ident: bib0002 article-title: Personal omics profiling reveals dynamic molecular and medical phenotypes publication-title: Cell contributor: fullname: Chen – volume: 375 start-page: 1525 year: 2010 end-page: 1535 ident: bib0001 article-title: Clinical assessment incorporating a personal genome publication-title: Lancet contributor: fullname: Ashley – volume: 4 start-page: 827 year: 2020 end-page: 834 ident: bib0013 article-title: Integrating spatial gene expression and breast tumour morphology via deep learning publication-title: Nat. Biomed. Eng. contributor: fullname: He – volume: 578 year: 2020 ident: bib0003 article-title: The single-cell pathology landscape of breast cancer publication-title: Nature contributor: fullname: Jackson – volume: 296 start-page: E32 year: 2020 end-page: E40 ident: bib0004 article-title: Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases publication-title: Radiology contributor: fullname: Ai – volume: 2 start-page: 116 year: 2019 ident: bib0010 article-title: Machine learning can accurately predict pre-admission baseline hemoglobin and creatinine in intensive care patients publication-title: NPJ Digit. Med. contributor: fullname: Dauvin – year: 2020 ident: bib0022 article-title: Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network publication-title: Nat. Med. contributor: fullname: Raghunath – volume: 321 year: 2019 ident: bib0007 article-title: Screening for HIV infection: US preventive services task force recommendation statement publication-title: JAMA contributor: fullname: Owens – volume: 12 year: 2019 ident: bib0021 article-title: Age and sex estimation using artificial intelligence from standard 12-lead ECGs publication-title: Circ. Arrhythm. Electrophysiol. contributor: fullname: Attia – volume: 2 start-page: e358 year: 2020 end-page: e367 ident: bib0023 article-title: A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study publication-title: Lancet Digit Health contributor: fullname: Kwon – year: 2018 ident: bib0024 article-title: A closer look at spatiotemporal convolutions for action recognition publication-title: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition contributor: fullname: Tran – volume: 394 start-page: 861 year: 2019 end-page: 867 ident: bib0012 article-title: An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction publication-title: Lancet contributor: fullname: Attia – start-page: 319 year: 2018 ident: bib0005 article-title: Screening for prostate cancer: US preventive services task force recommendation statement publication-title: JAMA contributor: fullname: Grossman – volume: 580 start-page: 252 year: 2020 end-page: 256 ident: bib0019 article-title: Video-based AI for beat-to-beat assessment of cardiac function publication-title: Nature contributor: fullname: Ouyang – volume: 34 year: 2019 ident: bib0020 article-title: Hyperkalemia: pathophysiology, risk factors and consequences publication-title: Nephrol. Dial. Transplant contributor: fullname: Bailey – year: 2017 ident: bib0025 article-title: Action recognition? publication-title: A New Model and the Kinetics Dataset. contributor: fullname: Zissmerman – volume: 59 start-page: 151 year: 2020 end-page: 157 ident: bib0014 article-title: Artificial intelligence for detecting mitral regurgitation using electrocardiography publication-title: J. Electrocardiol. contributor: fullname: Kwon – volume: 24 start-page: 229 year: 2011 end-page: 267 ident: bib0017 article-title: ACCF/ASE/AHA/ASNC/HFSA/HRS/SCAI/SCCM/SCCT/SCMR 2011 appropriate use criteria for echocardiography. A report of the American college of cardiology foundation appropriate use criteria task force, American society of echocardiography, American heart association, American society of nuclear cardiology, heart failure society of America, heart rhythm society, society for cardiovascular angiography and interventions, society of critical care medicine, society of cardiovascular computed tomography, society for cardiovascular magnetic resonance American college of chest physicians publication-title: J. Am. Soc. Echocardiogr. contributor: fullname: Douglas – volume: 3 start-page: 10 year: 2020 ident: bib0009 article-title: Deep learning interpretation of echocardiograms publication-title: NPJ Digit. Med. contributor: fullname: Ghorbani – volume: 67 start-page: 502 year: 2016 end-page: 511 ident: bib0016 article-title: US hospital use of echocardiography: insights from the nationwide inpatient sample publication-title: J. Am. Coll. Cardiol. contributor: fullname: Sengupta – volume: 138 start-page: 1623 year: 2018 end-page: 1635 ident: bib0018 article-title: Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy publication-title: Circulation contributor: fullname: Zhang – volume: 24 start-page: 229 year: 2011 ident: 10.1016/j.ebiom.2021.103613_bib0017 publication-title: J. Am. Soc. Echocardiogr. doi: 10.1016/j.echo.2010.12.008 contributor: fullname: Douglas – volume: 4 start-page: 827 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0013 article-title: Integrating spatial gene expression and breast tumour morphology via deep learning publication-title: Nat. Biomed. Eng. doi: 10.1038/s41551-020-0578-x contributor: fullname: He – volume: 375 start-page: 1525 year: 2010 ident: 10.1016/j.ebiom.2021.103613_bib0001 article-title: Clinical assessment incorporating a personal genome publication-title: Lancet doi: 10.1016/S0140-6736(10)60452-7 contributor: fullname: Ashley – volume: 2 start-page: 116 year: 2019 ident: 10.1016/j.ebiom.2021.103613_bib0010 article-title: Machine learning can accurately predict pre-admission baseline hemoglobin and creatinine in intensive care patients publication-title: NPJ Digit. Med. doi: 10.1038/s41746-019-0192-z contributor: fullname: Dauvin – volume: 34 year: 2019 ident: 10.1016/j.ebiom.2021.103613_bib0020 article-title: Hyperkalemia: pathophysiology, risk factors and consequences publication-title: Nephrol. Dial. Transplant doi: 10.1093/ndt/gfz206 contributor: fullname: Hunter – start-page: 315 year: 2016 ident: 10.1016/j.ebiom.2021.103613_bib0006 article-title: Screening for colorectal cancer: US preventive services task force recommendation statement publication-title: JAMA contributor: fullname: Bibbins-Domingo – volume: 296 start-page: E32 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0004 article-title: Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases publication-title: Radiology doi: 10.1148/radiol.2020200642 contributor: fullname: Ai – start-page: 319 year: 2018 ident: 10.1016/j.ebiom.2021.103613_bib0005 article-title: Screening for prostate cancer: US preventive services task force recommendation statement publication-title: JAMA contributor: fullname: Grossman – year: 2017 ident: 10.1016/j.ebiom.2021.103613_bib0025 article-title: Action recognition? contributor: fullname: Carreira – volume: 67 start-page: 502 year: 2016 ident: 10.1016/j.ebiom.2021.103613_bib0016 article-title: US hospital use of echocardiography: insights from the nationwide inpatient sample publication-title: J. Am. Coll. Cardiol. doi: 10.1016/j.jacc.2015.10.090 contributor: fullname: Papolos – volume: 2 start-page: e358 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0023 article-title: A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study publication-title: Lancet Digit Health doi: 10.1016/S2589-7500(20)30108-4 contributor: fullname: Kwon – volume: 394 start-page: 861 year: 2019 ident: 10.1016/j.ebiom.2021.103613_bib0012 article-title: An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction publication-title: Lancet doi: 10.1016/S0140-6736(19)31721-0 contributor: fullname: Attia – volume: 138 start-page: 1623 year: 2018 ident: 10.1016/j.ebiom.2021.103613_bib0018 article-title: Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy publication-title: Circulation doi: 10.1161/CIRCULATIONAHA.118.034338 contributor: fullname: Zhang – year: 2018 ident: 10.1016/j.ebiom.2021.103613_bib0024 article-title: A closer look at spatiotemporal convolutions for action recognition contributor: fullname: Tran – volume: 321 year: 2019 ident: 10.1016/j.ebiom.2021.103613_bib0007 article-title: Screening for HIV infection: US preventive services task force recommendation statement publication-title: JAMA contributor: fullname: Owens – volume: 580 start-page: 252 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0019 article-title: Video-based AI for beat-to-beat assessment of cardiac function publication-title: Nature doi: 10.1038/s41586-020-2145-8 contributor: fullname: Ouyang – volume: 578 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0003 article-title: The single-cell pathology landscape of breast cancer publication-title: Nature doi: 10.1038/s41586-019-1876-x contributor: fullname: Jackson – volume: 2 start-page: 158 year: 2018 ident: 10.1016/j.ebiom.2021.103613_bib0008 article-title: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning publication-title: Nat. Biomed. Eng. doi: 10.1038/s41551-018-0195-0 contributor: fullname: Poplin – volume: 12 year: 2019 ident: 10.1016/j.ebiom.2021.103613_bib0021 article-title: Age and sex estimation using artificial intelligence from standard 12-lead ECGs publication-title: Circ. Arrhythm. Electrophysiol. doi: 10.1161/CIRCEP.119.007284 contributor: fullname: Attia – volume: 26 start-page: 1576 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0011 article-title: A digital biomarker of diabetes from smartphone-based vascular signals publication-title: Nat. Med. doi: 10.1038/s41591-020-1010-5 contributor: fullname: Avram – volume: 148 start-page: 1293 year: 2012 ident: 10.1016/j.ebiom.2021.103613_bib0002 article-title: Personal omics profiling reveals dynamic molecular and medical phenotypes publication-title: Cell doi: 10.1016/j.cell.2012.02.009 contributor: fullname: Chen – volume: 75 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0015 article-title: Detection of hypertrophic cardiomyopathy using a convolutional neural network-enabled electrocardiogram publication-title: J. Am. Coll. Cardiol. doi: 10.1016/j.jacc.2019.12.030 contributor: fullname: Ko – volume: 3 start-page: 10 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0009 article-title: Deep learning interpretation of echocardiograms publication-title: NPJ Digit. Med. doi: 10.1038/s41746-019-0216-8 contributor: fullname: Ghorbani – year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0022 article-title: Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network publication-title: Nat. Med. doi: 10.1038/s41591-020-0870-z contributor: fullname: Raghunath – volume: 59 start-page: 151 year: 2020 ident: 10.1016/j.ebiom.2021.103613_bib0014 article-title: Artificial intelligence for detecting mitral regurgitation using electrocardiography publication-title: J. Electrocardiol. doi: 10.1016/j.jelectrocard.2020.02.008 contributor: fullname: Kwon |
SSID | ssj0001542358 |
Score | 2.398871 |
Snippet | Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from... BACKGROUNDLaboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from... Background: Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from... |
SourceID | doaj pubmedcentral proquest crossref pubmed elsevier |
SourceType | Open Website Open Access Repository Aggregation Database Index Database Publisher |
StartPage | 103613 |
SubjectTerms | Algorithms Artificial intelligence Biomarkers Deep Learning Echocardiography Humans Image Interpretation, Computer-Assisted - methods Image Processing, Computer-Assisted - methods Research Paper ROC Curve Software |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwELUQEhKXqh_QpqXIlTgSNfFncoQCQpXaE0jcrNget_SQRexy6L_vjJ3Abiu1l16TKPG8sT1jZd4bxo7AQNvZEOrYN7JWNmlcc72tDWA6miLglCE28pev5vJafb7RN2utvqgmrMgDF-A-RiNDCz5CoB7eceh7bf0QQafY0Naad99GrB2mCj9YEQc0d5bTopa9UbPkUC7uAiK34-lQtMQ6z80N1sJSVu_fiE5_Zp-_F1GuRaWL5-zZlE7yk2LGC7YF40u2UxpM_nzFTs4A7vjUGeIbf5L25ovEaXBUnHO_5EQy4YA7YcjlqVSxxYmgt1juseuL86tPl_XUNKEOWuhV3SPEcjBdk7yNCJcABdBD0nTY60Rok8WMb7DWyzYOIXijhRms6hUGc0J5n22PixHeMI6ZUdNEoaCDqDrZ-cYr6aVOIkiRvKrY8YyZuyvaGG4uGvvhMsSOIHYF4oqdEq6Pj5Kwdb6A7naTu92_3F0xM3vFTTlCif34qtu_f_3D7EOHK4h-iwwjLB6WThDxDA_nRlTsdfHp4xglycnhfK2Y3fD2hhGbd8bb71mlu9OYHDXy7f-w-h3bJVMKB_KAba_uH-A9JkMrf5jn_S9JbweM priority: 102 providerName: Directory of Open Access Journals – databaseName: Scholars Portal Journals: Open Access dbid: M48 link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1ba9VAEF5KRfBFvBtvrOCjkWSv2QeReilFqE8e6NuS3Z2tlZLUc07B_ntncmmNFsHHXEg238ww35L5Zhh7BQbqxsZYJlfJUtmsMeacLQ0gHc0J0GVIjXz4xRys1OcjfbTD5qmoE4Cba7d2NE9qtT598_PHxTsM-LdXtVpAWnXc7ImaROSGptjeEJgaqcbrcOL7o2xYkTR0GDinRSmdUXMnouufs8hWQ1P_RdL6m5T-WVv5W7Lav8NuTyyT741ucZftQHeP3RznTl7cZ3sfAc74NDDimF91_OZ95rQ4qtlZbzhpTzggRnGoWqVCLk66vX7zgK32P339cFBOsxTKqIXelg6Rl61pqhxsSq0ToAAcZE17wEbEOlskgq21QdapjTEYLUxrlVOY4xNE-ZDtdn0HjxlHwlRVSShoIKlGNqEKSgaps4hS5KAK9nrGzJ-NLTP8XEv23Q8Qe4LYjxAX7D3henkr9bseTvTrYz-Fj09GxhoCLcSpCtfvtA1tAp1TRQm2YGa2ip-ow0gJ8FEn_377y9mGHgOL_pa0HfTnGy9Ij4Z7diMK9mi06eUaJXWZQzcumF1Ye_ERyyvdybeheXejkTNV8sn_gfSU3aKjUQT5jO1u1-fwHNnQNrwYPPwXPxIHEA priority: 102 providerName: Scholars Portal |
Title | Deep learning evaluation of biomarkers from echocardiogram videos |
URI | https://dx.doi.org/10.1016/j.ebiom.2021.103613 https://www.ncbi.nlm.nih.gov/pubmed/34656880 https://search.proquest.com/docview/2583327462 https://pubmed.ncbi.nlm.nih.gov/PMC8524103 https://doaj.org/article/d63c1ebdec3940da9957bade5fd02847 |
Volume | 73 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9RADLbaSqBeEG_CowoSR9JN5pFJjqVQVUiLOFCpt1Fmxilb0WS1uz3w77EnSdkFiQOXHPJ0bCefJ_k-D8A7LLGojPdZqHOZKdNqeuZqk5VI5WgbkFKG1cjzL-X5hfp8qS_3QE9amEja925x3P24Oe4W3yO3cnnjZxNPbPZ1flppwp1czvZhn-B3a4g-SIMVyz-nDkORy4WsZafBoChYZE4Idgj3JXcKq7gd5BYgxb79O7j0d935J31yC4_OHsKDsZBMTwaDH8Eedo_h3jC15M8ncPIRcZmOc0Jcpb-beqd9m7KdTMtZrVOWl6RI70AfianM1UpZmtevn8LF2advp-fZOF1C5rXQm6wm58qmrPLWmRCaWqBCrLHVPMyrhC9aQ7VeY4yTRWi8d6UWZWNUrQjGA3r5DA66vsMXkFJNlOdBKKwwqEpWLndKOqlb4aVonUrg_eQzuxy6YtiJLnZto7cte9sO3k7gA_v1blduaR1X9KsrOwbWhlL6Ah0bUquc7K-1cU1A3YacMTSBcoqKHauDAfXpVIt_X_3tFENLzw7_EGk67G_XVrDkjIblpUjg-RDTOxun9EjA7ER75yZ2t1C6xv7cY3q-_O8jX8Eh2z9IHl_DwWZ1i2-o9tm4o_jNgJZzVR3FvP8FpV0Grw |
link.rule.ids | 230,314,727,780,784,864,885,2102,24318,27924,27925,53791,53793 |
linkProvider | National Library of Medicine |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEB6VIqAXxJvwDBJH0k38iONjKVQLdCsOrdSbFduTsogmq93tgX-Px0nKLkgcuOY5nhnnGyvfNwZ4iyUWlXIu8zrnmVCNDHNOq6zEUI42HkPKkBp5dlJOz8Tnc3m-A3LUwkTSvrPz_fbH5X47_xa5lYtLNxl5YpOvs8NKBtzJ-eQG3JRc6WJjkd6LgwUJQMceQ5HNhaRmD8tBVpDMPGDYHtzm1CusooaQG5AUO_dvIdPfleefBMoNRDq6B3eHUjI96E2-DzvYPoBb_eaSPx_CwQfERTrsCnGR_m7rnXZNSnYSMWe5SklgkmL4CrpITSW2VkrivG71CM6OPp4eTrNhw4TMSSbXmQ7u5XVZ5Y1V3teaoUDU2Eha6FXMFY0K1V6tlOWFr52zpWRlrYQWAcg9Ov4YdtuuxaeQhqoozz0TWKEXFa9sbgW3XDbMcdZYkcC70Wdm0ffFMCNh7LuJ3jbkbdN7O4H35NfrS6mpdTzQLS_MEFrjS-4KtGSIFnmwX0tla4-y8TmhaALlGBUz1Ac97odHzf_99jdjDE2YPfRLpG6xu1oZRqKzsDAvWQJP-phe2zimRwJqK9pbg9g-ExI2dugeEvTZf9_5Gu5MT2fH5vjTyZfnsEdj6QWQL2B3vbzCl6ESWttXMe9_ATx-CDU |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9RADLagiKoXxJuUV5A4km4yz-RYWlbl0aoHKvU2ysx42kU0We1uD_33jPMouyBx4Jqnx_bEtvJ9NsB7VFiU2rnMVznPhA4y7rlKZwpjOho8RpchNvLxiTo6E1_O5fnaqK8OtO_sbK_5ebXXzC47bOX8yk1GnNjk9PiglDHu5Hwy92FyF-5JHp1srVDvCcKCSKBjn6EO0YXEaI8lISuIah7j2A5sc-oXVlJTyLWw1HXv34hOf2eff4Io16LS9CE8GNLJdL8X-xHcweYx3O8HTN48gf1DxHk6TIa4SH-39k7bkJKcBM5ZLFMimaQYv4Sug6cSYislgl67fApn00_fD46yYWhC5iSTq6yKKua1KvNgtfd1xVAgVhgkFXslc0XQMeOrtba88LVzVkmmai0qEYO5R8efwVbTNvgC0pgZ5blnAkv0ouSlza3glsvAHGfBigQ-jDoz8743hhlBYz9Mp21D2ja9thP4SHq9vZQaW3cH2sWFGcxrvOKuQEuCVCKP8ldS29qjDD6nSJqAGq1ihhyhj_3xUbN_v_3daEMTdxD9FqkbbK-XhhHxLBbniiXwvLfprYyjeySgN6y9sYjNM9Fpuy7dg5Pu_vedb2H79HBqvn0--foSdmgpPQfyFWytFtf4OiZDK_umc_tfAlAJSA |
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=Deep+learning+evaluation+of+biomarkers+from+echocardiogram+videos&rft.jtitle=EBioMedicine&rft.au=Hughes%2C+J+Weston&rft.au=Yuan%2C+Neal&rft.au=He%2C+Bryan&rft.au=Ouyang%2C+Jiahong&rft.date=2021-11-01&rft.issn=2352-3964&rft.eissn=2352-3964&rft.volume=73&rft.spage=103613&rft_id=info:doi/10.1016%2Fj.ebiom.2021.103613&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ebiom_2021_103613 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2352-3964&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2352-3964&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2352-3964&client=summon |