Explaining deep neural networks for knowledge discovery in electrocardiogram analysis

Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a hu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Scientific reports Jg. 11; H. 1; S. 10949 - 11
Hauptverfasser: Hicks, Steven A., Isaksen, Jonas L., Thambawita, Vajira, Ghouse, Jonas, Ahlberg, Gustav, Linneberg, Allan, Grarup, Niels, Strümke, Inga, Ellervik, Christina, Olesen, Morten Salling, Hansen, Torben, Graff, Claus, Holstein-Rathlou, Niels-Henrik, Halvorsen, Pål, Maleckar, Mary M., Riegler, Michael A., Kanters, Jørgen K.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 26.05.2021
Nature Publishing Group
Nature Portfolio
Schlagworte:
ISSN:2045-2322, 2045-2322
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.
AbstractList Abstract Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.
Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.
Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.
ArticleNumber 10949
Author Strümke, Inga
Grarup, Niels
Riegler, Michael A.
Ghouse, Jonas
Ahlberg, Gustav
Halvorsen, Pål
Maleckar, Mary M.
Graff, Claus
Holstein-Rathlou, Niels-Henrik
Thambawita, Vajira
Linneberg, Allan
Hansen, Torben
Hicks, Steven A.
Kanters, Jørgen K.
Olesen, Morten Salling
Isaksen, Jonas L.
Ellervik, Christina
Author_xml – sequence: 1
  givenname: Steven A.
  surname: Hicks
  fullname: Hicks, Steven A.
  email: steven@simula.no
  organization: SimulaMet, Oslo Metropolitan University
– sequence: 2
  givenname: Jonas L.
  surname: Isaksen
  fullname: Isaksen, Jonas L.
  organization: University of Copenhagen
– sequence: 3
  givenname: Vajira
  surname: Thambawita
  fullname: Thambawita, Vajira
  organization: SimulaMet, Oslo Metropolitan University
– sequence: 4
  givenname: Jonas
  surname: Ghouse
  fullname: Ghouse, Jonas
  organization: University of Copenhagen
– sequence: 5
  givenname: Gustav
  surname: Ahlberg
  fullname: Ahlberg, Gustav
  organization: University of Copenhagen
– sequence: 6
  givenname: Allan
  surname: Linneberg
  fullname: Linneberg, Allan
  organization: University of Copenhagen
– sequence: 7
  givenname: Niels
  surname: Grarup
  fullname: Grarup, Niels
  organization: University of Copenhagen, Novo Nordisk Foundation Center for Basic Metabolic Research
– sequence: 8
  givenname: Inga
  surname: Strümke
  fullname: Strümke, Inga
  organization: SimulaMet
– sequence: 9
  givenname: Christina
  surname: Ellervik
  fullname: Ellervik, Christina
  organization: University of Copenhagen
– sequence: 10
  givenname: Morten Salling
  surname: Olesen
  fullname: Olesen, Morten Salling
  organization: University of Copenhagen
– sequence: 11
  givenname: Torben
  surname: Hansen
  fullname: Hansen, Torben
  organization: University of Copenhagen, Novo Nordisk Foundation Center for Basic Metabolic Research
– sequence: 12
  givenname: Claus
  surname: Graff
  fullname: Graff, Claus
  organization: Aalborg University
– sequence: 13
  givenname: Niels-Henrik
  surname: Holstein-Rathlou
  fullname: Holstein-Rathlou, Niels-Henrik
  organization: University of Copenhagen
– sequence: 14
  givenname: Pål
  surname: Halvorsen
  fullname: Halvorsen, Pål
  organization: SimulaMet, Oslo Metropolitan University
– sequence: 15
  givenname: Mary M.
  surname: Maleckar
  fullname: Maleckar, Mary M.
  organization: Simula Research Laboratory
– sequence: 16
  givenname: Michael A.
  surname: Riegler
  fullname: Riegler, Michael A.
  organization: SimulaMet
– sequence: 17
  givenname: Jørgen K.
  surname: Kanters
  fullname: Kanters, Jørgen K.
  organization: University of Copenhagen
BookMark eNp9Uk1v1DAUtFARLUv_AKdIXLgE_JnYFyRUFahUiQs9W479HLzN2oudtOy_x7tbBO2hvjzreWbe82heo5OYIiD0luAPBDP5sXAilGwxJa3CVIpWvEBnFHPRUkbpyX_3U3ReyhrXI6jiRL1Cp4xjjjFjZ-jm8vd2MiGGODYOYNtEWLKZapnvU74tjU-5uY3pfgI3QuNCsekO8q4JsYEJ7JyTNdmFNGazaUw0066E8ga99GYqcP5QV-jmy-WPi2_t9fevVxefr1srSD-30jlsBHceBqn6QXW4F53pjcJMDKIHSTrCwThPMQaOB-lFjwUjFvzQe0XYCl0ddV0ya73NYWPyTicT9KGR8qhNnoOdQHdeMsBgeTdYTnqhvJO9Z5g55z1QqFqfjlrbZdiAsxDnasQj0ccvMfzUY7rTkgiusKoC7x8Ecvq1QJn1proF02QipKVoKhhjpBNCVOi7J9B1WnI174CinBJWN1sheUTZnErJ4LUNs5lD2s8PkyZY76Ogj1HQNQr6EAW9H0CfUP_-41kSO5JKBccR8r-tnmH9AVhPyGQ
CitedBy_id crossref_primary_10_1259_bjr_20220239
crossref_primary_10_3390_diagnostics13010111
crossref_primary_10_1016_j_bspc_2025_108153
crossref_primary_10_1038_s41598_022_15539_2
crossref_primary_10_1016_j_compbiomed_2024_108525
crossref_primary_10_1016_j_bspc_2022_103584
crossref_primary_10_1007_s00399_022_00839_x
crossref_primary_10_1080_17434440_2025_2510537
crossref_primary_10_1007_s13534_025_00486_4
crossref_primary_10_1016_j_ijcha_2025_101783
crossref_primary_10_1016_j_neucom_2024_128920
crossref_primary_10_1093_jamia_ocae280
crossref_primary_10_3390_diagnostics13223413
crossref_primary_10_3390_diagnostics13142345
crossref_primary_10_1016_j_cvdhj_2021_12_003
crossref_primary_10_1016_j_cjca_2021_09_004
crossref_primary_10_1109_TBME_2023_3321792
crossref_primary_10_1016_j_eswa_2024_124775
crossref_primary_10_1109_TBME_2023_3348329
crossref_primary_10_1038_s41598_021_01295_2
crossref_primary_10_1016_j_jclinepi_2021_11_001
crossref_primary_10_1038_s41598_025_90152_7
crossref_primary_10_1016_j_oceaneng_2024_119263
crossref_primary_10_1109_TBME_2022_3221339
crossref_primary_10_1038_s43856_025_00814_w
crossref_primary_10_3390_asi5040081
crossref_primary_10_1016_j_cmpb_2025_108798
crossref_primary_10_3389_frai_2022_786091
crossref_primary_10_1016_j_cmpb_2024_108537
crossref_primary_10_3390_jpm14111069
crossref_primary_10_1016_j_jelectrocard_2025_154123
crossref_primary_10_1093_ehjdh_ztaf020
crossref_primary_10_3389_fphys_2021_745349
crossref_primary_10_1016_j_artmed_2023_102690
crossref_primary_10_1016_j_cjca_2024_07_003
crossref_primary_10_1007_s13239_025_00797_8
Cites_doi 10.1016/j.ins.2017.04.012
10.1001/jama.2017.7797
10.1093/eurheartj/ehu081
10.1016/j.jelectrocard.2009.08.001
10.1038/s41746-019-0122-0
10.1038/s41591-020-0870-z
10.1111/bjd.15778
10.1186/s12916-019-1426-2
10.1016/j.ijcard.2020.12.016
10.1038/s41591-018-0268-3
10.3390/electronics8080832
10.1007/s40031-020-00488-z
10.1161/01.RES.9.6.1138
10.1109/78.668803
10.1038/nature21056
10.1177/0091270009344853
10.1016/j.jacc.2013.03.032
10.1016/S0933-3657(96)00367-3
10.1038/s41746-019-0105-1
10.1007/s11263-019-01228-7
10.1093/eurheartj/ehv297
10.1016/0002-9149(91)90099-7
10.1007/s11277-020-08017-3
10.1136/hrt.47.3.209
10.1109/CIC.2001.977609
10.1007/978-1-84882-046-3
10.1109/CVPR.2016.90
10.1109/ICHI.2015.26
10.1161/JAHA.119.015138
10.1145/2964284.2976760
10.1109/IMTC.2007.379244
10.1088/1361-6579/aaf34d
10.1145/2783258.2788613
10.1109/CBMS.2018.00070
10.1161/CIRCEP.119.007284
10.1371/journal.pmed.1002683
ContentType Journal Article
Copyright The Author(s) 2021
The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2021
– notice: The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
AAYXX
CITATION
3V.
7X7
7XB
88A
88E
88I
8FE
8FH
8FI
8FJ
8FK
ABUWG
AEUYN
AFKRA
AZQEC
BBNVY
BENPR
BHPHI
CCPQU
DWQXO
FYUFA
GHDGH
GNUQQ
HCIFZ
K9.
LK8
M0S
M1P
M2P
M7P
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
Q9U
7X8
5PM
DOA
DOI 10.1038/s41598-021-90285-5
DatabaseName Springer Nature Open Access Journals
CrossRef
ProQuest Central (Corporate)
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Biology Database (Alumni Edition)
Medical Database (Alumni Edition)
Science Database (Alumni Edition)
ProQuest SciTech Collection
ProQuest Natural Science Collection
ProQuest Hospital Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest One Sustainability
ProQuest Central UK/Ireland
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
Natural Science Collection
ProQuest One
ProQuest Central
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
SciTech Premium Collection
ProQuest Health & Medical Complete (Alumni)
Biological Sciences
ProQuest Health & Medical Collection
Medical Database
Science Database
Biological Science Database
ProQuest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest Central Basic
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
ProQuest Central Student
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Natural Science Collection
ProQuest Central China
ProQuest Biology Journals (Alumni Edition)
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest One Sustainability
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
Natural Science Collection
ProQuest Central Korea
Health & Medical Research Collection
Biological Science Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
ProQuest Science Journals (Alumni Edition)
ProQuest Biological Science Collection
ProQuest Central Basic
ProQuest Science Journals
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
Biological Science Database
ProQuest SciTech Collection
ProQuest Hospital Collection (Alumni)
ProQuest Health & Medical Complete
ProQuest Medical Library
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
CrossRef

Publicly Available Content Database

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 2045-2322
EndPage 11
ExternalDocumentID oai_doaj_org_article_6f83e0ec46bc41759fd87f303ddffe2e
PMC8154909
10_1038_s41598_021_90285_5
GrantInformation_xml – fundername: Novo Nordisk Foundation
  grantid: NNF18CC0034900
– fundername: ;
  grantid: NNF18CC0034900
GroupedDBID 0R~
3V.
4.4
53G
5VS
7X7
88A
88E
88I
8FE
8FH
8FI
8FJ
AAFWJ
AAJSJ
AAKDD
ABDBF
ABUWG
ACGFS
ACSMW
ACUHS
ADBBV
ADRAZ
AENEX
AEUYN
AFKRA
AJTQC
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AOIJS
AZQEC
BAWUL
BBNVY
BCNDV
BENPR
BHPHI
BPHCQ
BVXVI
C6C
CCPQU
DIK
DWQXO
EBD
EBLON
EBS
ESX
FYUFA
GNUQQ
GROUPED_DOAJ
GX1
HCIFZ
HH5
HMCUK
HYE
KQ8
LK8
M0L
M1P
M2P
M48
M7P
M~E
NAO
OK1
PIMPY
PQQKQ
PROAC
PSQYO
RNT
RNTTT
RPM
SNYQT
UKHRP
AASML
AAYXX
AFFHD
AFPKN
CITATION
PHGZM
PHGZT
PJZUB
PPXIY
PQGLB
7XB
8FK
K9.
PKEHL
PQEST
PQUKI
PRINS
Q9U
7X8
5PM
ID FETCH-LOGICAL-c517t-8dd0a54dfeb897b960756a7a9035b57e81614eadf200e40b8f570531cefb7f913
IEDL.DBID DOA
ISICitedReferencesCount 48
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000659146000005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2045-2322
IngestDate Tue Oct 14 19:06:26 EDT 2025
Tue Nov 04 01:52:20 EST 2025
Sun Nov 09 12:13:33 EST 2025
Tue Oct 07 09:16:38 EDT 2025
Sat Nov 29 05:58:12 EST 2025
Tue Nov 18 20:02:33 EST 2025
Fri Feb 21 02:38:54 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c517t-8dd0a54dfeb897b960756a7a9035b57e81614eadf200e40b8f570531cefb7f913
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
OpenAccessLink https://doaj.org/article/6f83e0ec46bc41759fd87f303ddffe2e
PMID 34040033
PQID 2532421330
PQPubID 2041939
PageCount 11
ParticipantIDs doaj_primary_oai_doaj_org_article_6f83e0ec46bc41759fd87f303ddffe2e
pubmedcentral_primary_oai_pubmedcentral_nih_gov_8154909
proquest_miscellaneous_2533316555
proquest_journals_2532421330
crossref_citationtrail_10_1038_s41598_021_90285_5
crossref_primary_10_1038_s41598_021_90285_5
springer_journals_10_1038_s41598_021_90285_5
PublicationCentury 2000
PublicationDate 2021-05-26
PublicationDateYYYYMMDD 2021-05-26
PublicationDate_xml – month: 05
  year: 2021
  text: 2021-05-26
  day: 26
PublicationDecade 2020
PublicationPlace London
PublicationPlace_xml – name: London
PublicationTitle Scientific reports
PublicationTitleAbbrev Sci Rep
PublicationYear 2021
Publisher Nature Publishing Group UK
Nature Publishing Group
Nature Portfolio
Publisher_xml – name: Nature Publishing Group UK
– name: Nature Publishing Group
– name: Nature Portfolio
References Carvalho, Pereira, Cardoso (CR12) 2019; 8
Nielsen (CR22) 2013; 61
CR39
CR38
CR15
CR37
CR36
CR13
CR35
CR10
CR32
Hannun (CR11) 2019; 25
Ghouse (CR30) 2015; 36
Badgeley (CR16) 2019; 2
Chen (CR18) 2019; 2
Cullen, Stenhouse, Wearne, Cumpston (CR19) 1982; 47
Nielsen (CR21) 2014; 35
Gupta, Mittal (CR1) 2020; 101
Graff (CR31) 2009; 49
Silipo, Marchesi (CR4) 1998; 46
Acharya (CR9) 2017; 405
Juhl, Miller, Jemec, Kanters, Ellervik (CR29) 2018; 178
Raghunath (CR41) 2020; 26
Cabitza, Rasoini, Gensini (CR25) 2017; 318
Stallmann, Pipberger (CR23) 1961; 9
CR3
Cooper (CR14) 1997; 9
Isaksen (CR34) 2021; 328
CR6
CR5
Haarmark (CR33) 2010; 43
CR7
CR28
CR27
CR24
Esteva (CR8) 2017; 542
CR40
Goldberg (CR20) 1991; 67
Selvaraju (CR26) 2020; 128
Gupta, Mittal, Mittal (CR2) 2021; 118
Kelly, Karthikesalingam, Suleyman, Corrado, King (CR17) 2019; 17
C Haarmark (90285_CR33) 2010; 43
90285_CR40
FW Stallmann (90285_CR23) 1961; 9
CJ Kelly (90285_CR17) 2019; 17
J Ghouse (90285_CR30) 2015; 36
90285_CR24
90285_CR27
90285_CR5
90285_CR28
90285_CR3
K Cullen (90285_CR19) 1982; 47
JL Isaksen (90285_CR34) 2021; 328
D Chen (90285_CR18) 2019; 2
V Gupta (90285_CR2) 2021; 118
AY Hannun (90285_CR11) 2019; 25
R Silipo (90285_CR4) 1998; 46
C Graff (90285_CR31) 2009; 49
JB Nielsen (90285_CR22) 2013; 61
90285_CR10
90285_CR32
90285_CR36
90285_CR13
90285_CR35
90285_CR38
90285_CR15
90285_CR37
90285_CR39
UR Acharya (90285_CR9) 2017; 405
F Cabitza (90285_CR25) 2017; 318
V Gupta (90285_CR1) 2020; 101
90285_CR7
RR Selvaraju (90285_CR26) 2020; 128
S Raghunath (90285_CR41) 2020; 26
90285_CR6
CR Juhl (90285_CR29) 2018; 178
DV Carvalho (90285_CR12) 2019; 8
GF Cooper (90285_CR14) 1997; 9
RJ Goldberg (90285_CR20) 1991; 67
A Esteva (90285_CR8) 2017; 542
MA Badgeley (90285_CR16) 2019; 2
JB Nielsen (90285_CR21) 2014; 35
References_xml – volume: 405
  start-page: 81
  year: 2017
  end-page: 90
  ident: CR9
  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: 318
  start-page: 517
  year: 2017
  end-page: 518
  ident: CR25
  article-title: Unintended consequences of machine learning in medicine
  publication-title: JAMA
  doi: 10.1001/jama.2017.7797
– ident: CR39
– ident: CR37
– volume: 35
  start-page: 1335
  year: 2014
  end-page: 1344
  ident: CR21
  article-title: Risk prediction of cardiovascular death based on the QTc interval: evaluating age and gender differences in a large primary care population
  publication-title: Eur. Heart J.
  doi: 10.1093/eurheartj/ehu081
– ident: CR10
– volume: 43
  start-page: 31
  year: 2010
  end-page: 39
  ident: CR33
  article-title: Reference values of electrocardiogram repolarization variables in a healthy population
  publication-title: J. Electrocardiol.
  doi: 10.1016/j.jelectrocard.2009.08.001
– volume: 2
  start-page: 43
  year: 2019
  ident: CR18
  article-title: Deep learning and alternative learning strategies for retrospective real-world clinical data
  publication-title: NPJ Digit. Med.
  doi: 10.1038/s41746-019-0122-0
– ident: CR35
– volume: 26
  start-page: 886
  year: 2020
  end-page: 891
  ident: CR41
  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
– ident: CR6
– volume: 178
  start-page: 222
  year: 2018
  end-page: 228
  ident: CR29
  article-title: Hidradenitis suppurativa and electrocardiographic changes: A cross-sectional population study
  publication-title: Br. J. Dermatol.
  doi: 10.1111/bjd.15778
– volume: 17
  start-page: 195
  year: 2019
  ident: CR17
  article-title: Key challenges for delivering clinical impact with artificial intelligence
  publication-title: BMC Med.
  doi: 10.1186/s12916-019-1426-2
– ident: CR40
– volume: 328
  start-page: 199
  year: 2021
  end-page: 205
  ident: CR34
  article-title: Electrocardiographic T-wave morphology and risk of mortality
  publication-title: Int. J. Cardiol.
  doi: 10.1016/j.ijcard.2020.12.016
– ident: CR27
– volume: 25
  start-page: 65
  year: 2019
  end-page: 69
  ident: CR11
  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
– volume: 8
  start-page: 832
  year: 2019
  ident: CR12
  article-title: Machine learning interpretability: A survey on methods and metrics
  publication-title: Electronics
  doi: 10.3390/electronics8080832
– volume: 101
  start-page: 451
  year: 2020
  end-page: 461
  ident: CR1
  article-title: Arrhythmia detection in ECG signal using fractional wavelet transform with principal component analysis
  publication-title: J. Inst. Eng. India Ser. B
  doi: 10.1007/s40031-020-00488-z
– volume: 9
  start-page: 1138
  year: 1961
  end-page: 1143
  ident: CR23
  article-title: Automatic recognition of electrocardiographic waves by digital computer
  publication-title: Circ. Res.
  doi: 10.1161/01.RES.9.6.1138
– ident: CR3
– volume: 46
  start-page: 1417
  year: 1998
  end-page: 1425
  ident: CR4
  article-title: Artificial neural networks for automatic ECG analysis
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/78.668803
– ident: CR15
– ident: CR38
– volume: 542
  start-page: 115
  year: 2017
  end-page: 118
  ident: CR8
  article-title: Dermatologist-level classification of skin cancer with deep neural networks
  publication-title: Nature
  doi: 10.1038/nature21056
– volume: 49
  start-page: 1331
  year: 2009
  end-page: 1342
  ident: CR31
  article-title: Quantitative analysis of T-wave morphology increases confidence in drug-induced cardiac repolarization abnormalities: Evidence from the investigational IKr inhibitor Lu 35–138
  publication-title: J. Clin. Pharmacol.
  doi: 10.1177/0091270009344853
– ident: CR13
– volume: 61
  start-page: 2557
  year: 2013
  end-page: 2564
  ident: CR22
  article-title: J-shaped association between QTc interval duration and the risk of atrial fibrillation: results from the Copenhagen ECG study
  publication-title: J. Am. Coll. Cardiol.
  doi: 10.1016/j.jacc.2013.03.032
– volume: 9
  start-page: 107
  year: 1997
  end-page: 138
  ident: CR14
  article-title: An evaluation of machine-learning methods for predicting pneumonia mortality
  publication-title: Artif. Intell. Med.
  doi: 10.1016/S0933-3657(96)00367-3
– volume: 2
  start-page: 31
  year: 2019
  ident: CR16
  article-title: Deep learning predicts hip fracture using confounding patient and healthcare variables
  publication-title: NPJ Digit. Med.
  doi: 10.1038/s41746-019-0105-1
– ident: CR32
– volume: 128
  start-page: 336
  year: 2020
  end-page: 359
  ident: CR26
  article-title: Grad-CAM: Visual explanations from deep networks via gradient-based localization
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-019-01228-7
– volume: 36
  start-page: 2523
  year: 2015
  end-page: 2529
  ident: CR30
  article-title: Rare genetic variants previously associated with congenital forms of long QT syndrome have little or no effect on the QT interval
  publication-title: Eur. Heart J.
  doi: 10.1093/eurheartj/ehv297
– ident: CR36
– ident: CR5
– volume: 67
  start-page: 55
  year: 1991
  end-page: 58
  ident: CR20
  article-title: Duration of the QT interval and total and cardiovascular mortality in healthy persons (The Framingham Heart Study experience)
  publication-title: Am. J. Cardiol.
  doi: 10.1016/0002-9149(91)90099-7
– ident: CR7
– volume: 118
  start-page: 359
  year: 2021
  end-page: 381
  ident: CR2
  article-title: An efficient low computational cost method of R-peak detection
  publication-title: Wirel. Pers. Commun.
  doi: 10.1007/s11277-020-08017-3
– volume: 47
  start-page: 209
  year: 1982
  end-page: 212
  ident: CR19
  article-title: Electrocardiograms and 13 year cardiovascular mortality in Busselton study
  publication-title: Br. Heart J.
  doi: 10.1136/hrt.47.3.209
– ident: CR28
– ident: CR24
– volume: 101
  start-page: 451
  year: 2020
  ident: 90285_CR1
  publication-title: J. Inst. Eng. India Ser. B
  doi: 10.1007/s40031-020-00488-z
– ident: 90285_CR5
  doi: 10.1109/CIC.2001.977609
– volume: 35
  start-page: 1335
  year: 2014
  ident: 90285_CR21
  publication-title: Eur. Heart J.
  doi: 10.1093/eurheartj/ehu081
– ident: 90285_CR27
  doi: 10.1007/978-1-84882-046-3
– ident: 90285_CR37
  doi: 10.1109/CVPR.2016.90
– ident: 90285_CR24
  doi: 10.1109/ICHI.2015.26
– volume: 43
  start-page: 31
  year: 2010
  ident: 90285_CR33
  publication-title: J. Electrocardiol.
  doi: 10.1016/j.jelectrocard.2009.08.001
– ident: 90285_CR39
  doi: 10.1161/JAHA.119.015138
– ident: 90285_CR28
– volume: 318
  start-page: 517
  year: 2017
  ident: 90285_CR25
  publication-title: JAMA
  doi: 10.1001/jama.2017.7797
– ident: 90285_CR15
  doi: 10.1145/2964284.2976760
– volume: 9
  start-page: 107
  year: 1997
  ident: 90285_CR14
  publication-title: Artif. Intell. Med.
  doi: 10.1016/S0933-3657(96)00367-3
– volume: 25
  start-page: 65
  year: 2019
  ident: 90285_CR11
  publication-title: Nat. Med.
  doi: 10.1038/s41591-018-0268-3
– volume: 17
  start-page: 195
  year: 2019
  ident: 90285_CR17
  publication-title: BMC Med.
  doi: 10.1186/s12916-019-1426-2
– volume: 36
  start-page: 2523
  year: 2015
  ident: 90285_CR30
  publication-title: Eur. Heart J.
  doi: 10.1093/eurheartj/ehv297
– ident: 90285_CR3
  doi: 10.1109/IMTC.2007.379244
– ident: 90285_CR35
– ident: 90285_CR6
– volume: 328
  start-page: 199
  year: 2021
  ident: 90285_CR34
  publication-title: Int. J. Cardiol.
  doi: 10.1016/j.ijcard.2020.12.016
– volume: 178
  start-page: 222
  year: 2018
  ident: 90285_CR29
  publication-title: Br. J. Dermatol.
  doi: 10.1111/bjd.15778
– volume: 46
  start-page: 1417
  year: 1998
  ident: 90285_CR4
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/78.668803
– ident: 90285_CR10
– volume: 67
  start-page: 55
  year: 1991
  ident: 90285_CR20
  publication-title: Am. J. Cardiol.
  doi: 10.1016/0002-9149(91)90099-7
– ident: 90285_CR40
  doi: 10.1088/1361-6579/aaf34d
– volume: 26
  start-page: 886
  year: 2020
  ident: 90285_CR41
  publication-title: Nat. Med.
  doi: 10.1038/s41591-020-0870-z
– ident: 90285_CR13
  doi: 10.1145/2783258.2788613
– volume: 47
  start-page: 209
  year: 1982
  ident: 90285_CR19
  publication-title: Br. Heart J.
  doi: 10.1136/hrt.47.3.209
– volume: 118
  start-page: 359
  year: 2021
  ident: 90285_CR2
  publication-title: Wirel. Pers. Commun.
  doi: 10.1007/s11277-020-08017-3
– volume: 542
  start-page: 115
  year: 2017
  ident: 90285_CR8
  publication-title: Nature
  doi: 10.1038/nature21056
– volume: 8
  start-page: 832
  year: 2019
  ident: 90285_CR12
  publication-title: Electronics
  doi: 10.3390/electronics8080832
– volume: 61
  start-page: 2557
  year: 2013
  ident: 90285_CR22
  publication-title: J. Am. Coll. Cardiol.
  doi: 10.1016/j.jacc.2013.03.032
– volume: 49
  start-page: 1331
  year: 2009
  ident: 90285_CR31
  publication-title: J. Clin. Pharmacol.
  doi: 10.1177/0091270009344853
– volume: 2
  start-page: 31
  year: 2019
  ident: 90285_CR16
  publication-title: NPJ Digit. Med.
  doi: 10.1038/s41746-019-0105-1
– volume: 128
  start-page: 336
  year: 2020
  ident: 90285_CR26
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-019-01228-7
– volume: 2
  start-page: 43
  year: 2019
  ident: 90285_CR18
  publication-title: NPJ Digit. Med.
  doi: 10.1038/s41746-019-0122-0
– volume: 405
  start-page: 81
  year: 2017
  ident: 90285_CR9
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2017.04.012
– ident: 90285_CR38
– ident: 90285_CR32
  doi: 10.1109/CBMS.2018.00070
– ident: 90285_CR36
  doi: 10.1161/CIRCEP.119.007284
– ident: 90285_CR7
  doi: 10.1371/journal.pmed.1002683
– volume: 9
  start-page: 1138
  year: 1961
  ident: 90285_CR23
  publication-title: Circ. Res.
  doi: 10.1161/01.RES.9.6.1138
SSID ssj0000529419
Score 2.5596173
Snippet Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors...
Abstract Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical...
SourceID doaj
pubmedcentral
proquest
crossref
springer
SourceType Open Website
Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 10949
SubjectTerms 631/114/1305
692/4019
Clinical decision making
Decision making
Deep learning
EKG
Electrocardiography
Humanities and Social Sciences
multidisciplinary
Neural networks
Science
Science (multidisciplinary)
SummonAdditionalLinks – databaseName: ProQuest Central
  dbid: BENPR
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7BFiQuvBGBgozEDaI6cRzbJ0RRKw5oVSGKerPiF6yEsstmW6n_vh7Hu1Uq0QvX2FacjMcznvn8DcB7I1tBbcfLVjlTNtaosuOdKZHKyte1CjTRF__8JuZzeXamTnLAbciwyu2emDZqt7QYIz-oOZr-eKKin1Z_S6wahdnVXELjLuwhU1kzg73Do_nJ912UBfNYTaXybRnK5MEQLRbeKkvIhFrykk8sUiLun3ibN7GSNxKmyQ4dP_rfL3gMD7MHSj6PS-YJ3PH9U7g_1qS8fAaniMoby0YQ5_2KIONl7N-PePGBRC-X7CJxBG_1Igr0kix6kmvq2IRxRdgX6TLnyXM4PT768eVrmWsvlJZXYlNK52jHGxe8kUqYeM4RvO1Epyjjhgsvo6fYxFUYopb5hhoZuEB9tj4YEVTFXsCsX_b-JRAWnSha26ZyLY2HwS4OZ4I6I1kTWHQQCqi2_1_bTEyO9TH-6JQgZ1KPMtNRZjrJTPMCPuzGrEZajlt7H6JYdz2RUjs9WK5_6ayhug2Seept05o4V8FVcFKEaOGdC8HXvoD9rVh11vNBX8u0gHe75qihmHbper88T30Yq1rO4zzEZDFNJjRt6Re_E9e3RAo9qgr4uF121y__9we_un2ur-FBjQpAEeC4D7PN-ty_gXv2YrMY1m-zDl0B1QMlGQ
  priority: 102
  providerName: ProQuest
Title Explaining deep neural networks for knowledge discovery in electrocardiogram analysis
URI https://link.springer.com/article/10.1038/s41598-021-90285-5
https://www.proquest.com/docview/2532421330
https://www.proquest.com/docview/2533316555
https://pubmed.ncbi.nlm.nih.gov/PMC8154909
https://doaj.org/article/6f83e0ec46bc41759fd87f303ddffe2e
Volume 11
WOSCitedRecordID wos000659146000005&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2045-2322
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000529419
  issn: 2045-2322
  databaseCode: DOA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2045-2322
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000529419
  issn: 2045-2322
  databaseCode: M~E
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 2045-2322
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000529419
  issn: 2045-2322
  databaseCode: M7P
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 2045-2322
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000529419
  issn: 2045-2322
  databaseCode: 7X7
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2045-2322
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000529419
  issn: 2045-2322
  databaseCode: BENPR
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2045-2322
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000529419
  issn: 2045-2322
  databaseCode: PIMPY
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 2045-2322
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000529419
  issn: 2045-2322
  databaseCode: M2P
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwEB1BCxIXxKcILSsjcYOoThzH9pGiViDRVYQoWk5WHNtiJZRW3S1S_31nnOzSVAIuXHxIbMUez3jG8fMbgDdO14p3rcxr411edc7krWxdTlRWoSxN5Im--NtnNZ_rxcI0N1J9ESZsoAceBHdQRy0CD11Vu65CX2ei1yriwut9jKEMtPpi1HNjMzWwepemKsx4S4YLfbBCT0W3yRIiodQylxNPlAj7J1HmbYzkrYPS5H-OH8HDMXBk74cOP4Y7oX8C94dUkldP4ZTAdEO2B-ZDOGdEVIn1-wHmvWIYnLLtDzRGl3EJvHnFlj0bU-F0CZpKaC3WjlQlz-D0-Ojrh4_5mDIh72Sh1rn2nrey8jE4bZTD7YmSdataw4V0UgWNAV6FyhPROELFnY5SkRl2IToVTSGew05_1ocXwATGPrxEmfua4x6uxeZCce-0qKJAv55BsRGf7UY-cUpr8dOmc22h7SByiyK3SeRWZvB22-Z8YNP4a-1DmpVtTWLCTg9QP-yoH_Zf-pHB_mZO7WieK1tKiiNxe84zeL19jYZFpyVtH84uUx0hilpK7Iea6MKkQ9M3_fJHoujWxHzHTQbvNlrz--N_HvDL_zHgPXhQkpZzQi_uw8764jK8gnvdr_VydTGDu2qhUqlnsHt4NG--zJLpYHlSNlQqLHebTyfN92tAQh48
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VAoIL34iFAkaCE0R14jh2DgjxVbXqsuLQor2ZOLZhJZRddreg_VP8RmacZKutRG89cE3sxImfx2PP8xuA51YXiteVTIrS2SSvbZlUsrIJSVn5LCsDj_LFX4ZqNNLjcfl5C_70Z2GIVtnbxGio3bSmPfLdTNLUjysq_mb2M6GsURRd7VNotLA49KvfuGRbvD74gP37Isv2Ph6930-6rAJJLVO1TLRzvJK5C97qUln04JUsKlWVXEgrldfoA-X4fwPix-fc6iAVIbX2wapQpgKfewkuox1XRCFTY7Xe06GoWZ6W3dkcLvTuAudHOsMWeRCZloncmP9imoAN3_YsM_NMeDbOens3_7f_dQtudP41e9sOiNuw5Zs7cLXNuLm6C8fEOWyTYjDn_YyRnieWb1o2_IKhD8_W-4yMziwTx3XFJg3rMgbVkcFLpDZWdYou9-D4Qr7pPmw308Y_ACbQReRZnaeu4LjUrbC6UNxZLfIg0P0ZQNr3t6k72XXK_vHDxPC_0KbFiEGMmIgRIwfwcl1n1oqOnFv6HcFoXZIEw-OF6fyb6eyPKYIWnvs6Lyy2VckyOK0C-i_OheAzP4CdHkams2ILc4qhATxb30b7Q0GlqvHTk1hGiLSQEtuhNsC70aDNO83ke1Qy1yQQyMsBvOphfvryf3_ww_Pb-hSu7R99GprhwejwEVzPaPBxonLuwPZyfuIfw5X613KymD-Jo5fB14uG_1_pDYB3
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6V8hAX3oiFAkaCE0TrxHHsHBACyoqqZdUDRb2ZOLZhJZRddreg_Wv8OmacZKutRG89cE3sxI_P47H9-RuA51YXiteVTIrS2SSvbZlUsrIJSVn5LCsDj_LFXw7UeKyPj8vDLfjT34UhWmVvE6OhdtOa9siHmaSpH1dUfBg6WsTh7ujN7GdCEaTopLUPp9FCZN-vfuPybfF6bxf7-kWWjT58fv8x6SIMJLVM1TLRzvFK5i54q0tl0ZtXsqhUVXIhrVReoz-UY1sHxJLPudVBKkJt7YNVoUwFfvcSXFa5lDS6PmWH6_0dOkHL07K7p8OFHi5wrqT7bJETkWmZyI25MIYM2PBzz7I0zxzVxhlwdPN_brtbcKPzu9nbdqDchi3f3IGrbSTO1V04Ii5iGyyDOe9njHQ-MX3TsuQXDH17tt5_ZHSXmbivKzZpWBdJqI7MXiK7sapTerkHRxdSp_uw3Uwb_wCYQNeRZ3WeuoLjErjC7EJxZ7XIg0C3aABp3_em7uTYKSrIDxNpAUKbFi8G8WIiXowcwMt1nlkrRnJu6ncEqXVKEhKPD6bzb6azS6YIWnju67ywWFYly-C0CujXOBeCz_wAdnpImc66LcwpngbwbP0a7RIdNlWNn57ENEKkhZRYDrUB5I0Cbb5pJt-jwrkm4UBeDuBVD_nTn_-7wg_PL-tTuIaoNwd74_1HcD2jcciJ4bkD28v5iX8MV-pfy8li_iQOZAZfLxr9fwHDkYlE
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=Explaining+deep+neural+networks+for+knowledge+discovery+in+electrocardiogram+analysis&rft.jtitle=Scientific+reports&rft.au=Steven+A.+Hicks&rft.au=Jonas+L.+Isaksen&rft.au=Vajira+Thambawita&rft.au=Jonas+Ghouse&rft.date=2021-05-26&rft.pub=Nature+Portfolio&rft.eissn=2045-2322&rft.volume=11&rft.issue=1&rft.spage=1&rft.epage=11&rft_id=info:doi/10.1038%2Fs41598-021-90285-5&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_6f83e0ec46bc41759fd87f303ddffe2e
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2045-2322&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2045-2322&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2045-2322&client=summon