Retraining an Artificial Intelligence Algorithm to Calculate Left Ventricular Ejection Fraction in Pediatrics

Identifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a deep-learning algorithm predict pediatric LVEF within clinically acceptable error? The study authors wanted to fine-tune an adult deep-learning algor...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of cardiothoracic and vascular anesthesia Ročník 36; číslo 9; s. 3610 - 3616
Hlavní autoři: Zuercher, Mael, Ufkes, Steven, Erdman, Lauren, Slorach, Cameron, Mertens, Luc, Taylor, Katherine
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Elsevier Inc 01.09.2022
Témata:
ISSN:1053-0770, 1532-8422, 1532-8422
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Identifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a deep-learning algorithm predict pediatric LVEF within clinically acceptable error? The study authors wanted to fine-tune an adult deep-learning algorithm to calculate LVEF in pediatric patients. A priori, their objective was to refine the algorithm to perform LVEF calculation with a mean absolute error (MAE) ≤5%. A quaternary pediatric hospital A convenience sample (n = 321) of echocardiograms from newborns to 18 years old with normal cardiac anatomy or hemodynamically insignificant anomalies. Echocardiograms were chosen from a group of healthy controls with known normal LVEF (n = 267) and a dilated cardiomyopathy patient group with reduced LVEF (n = 54). The artificial intelligence model EchoNet-Dynamic was tested on this data set and then retrained, tested, and further validated to improve LVEF calculation. The gold standard value was LVEF calculated by clinical experts. In a random subset of subjects (n = 40) not analyzed prior to selection of the final model, EchoNet-Dynamic calculated LVEF with a MAE of 8.39%, R2 = 0.47 without, and MAE 4.47%, R2 = 0.87 with fine-tuning. Bland-Altman analysis suggested that the model slightly underestimates LVEF (bias = –2.42%). The 95% limits of agreement between actual and calculated values were –12.32% to 7.47%. The fine-tuned model calculates LVEF in a range of pediatric patients within clinically acceptable error. Potential advantages include reducing operator error in LVEF calculation and supporting independent LVEF assessment by inexperienced users. [Display omitted]
AbstractList Identifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a deep-learning algorithm predict pediatric LVEF within clinically acceptable error? The study authors wanted to fine-tune an adult deep-learning algorithm to calculate LVEF in pediatric patients. A priori, their objective was to refine the algorithm to perform LVEF calculation with a mean absolute error (MAE) ≤5%. A quaternary pediatric hospital A convenience sample (n = 321) of echocardiograms from newborns to 18 years old with normal cardiac anatomy or hemodynamically insignificant anomalies. Echocardiograms were chosen from a group of healthy controls with known normal LVEF (n = 267) and a dilated cardiomyopathy patient group with reduced LVEF (n = 54). The artificial intelligence model EchoNet-Dynamic was tested on this data set and then retrained, tested, and further validated to improve LVEF calculation. The gold standard value was LVEF calculated by clinical experts. In a random subset of subjects (n = 40) not analyzed prior to selection of the final model, EchoNet-Dynamic calculated LVEF with a MAE of 8.39%, R2 = 0.47 without, and MAE 4.47%, R2 = 0.87 with fine-tuning. Bland-Altman analysis suggested that the model slightly underestimates LVEF (bias = –2.42%). The 95% limits of agreement between actual and calculated values were –12.32% to 7.47%. The fine-tuned model calculates LVEF in a range of pediatric patients within clinically acceptable error. Potential advantages include reducing operator error in LVEF calculation and supporting independent LVEF assessment by inexperienced users. [Display omitted]
Identifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a deep-learning algorithm predict pediatric LVEF within clinically acceptable error?OBJECTIVESIdentifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a deep-learning algorithm predict pediatric LVEF within clinically acceptable error?The study authors wanted to fine-tune an adult deep-learning algorithm to calculate LVEF in pediatric patients. A priori, their objective was to refine the algorithm to perform LVEF calculation with a mean absolute error (MAE) ≤5%.DESIGNThe study authors wanted to fine-tune an adult deep-learning algorithm to calculate LVEF in pediatric patients. A priori, their objective was to refine the algorithm to perform LVEF calculation with a mean absolute error (MAE) ≤5%.A quaternary pediatric hospital PARTICIPANTS: A convenience sample (n = 321) of echocardiograms from newborns to 18 years old with normal cardiac anatomy or hemodynamically insignificant anomalies. Echocardiograms were chosen from a group of healthy controls with known normal LVEF (n = 267) and a dilated cardiomyopathy patient group with reduced LVEF (n = 54).SETTINGA quaternary pediatric hospital PARTICIPANTS: A convenience sample (n = 321) of echocardiograms from newborns to 18 years old with normal cardiac anatomy or hemodynamically insignificant anomalies. Echocardiograms were chosen from a group of healthy controls with known normal LVEF (n = 267) and a dilated cardiomyopathy patient group with reduced LVEF (n = 54).The artificial intelligence model EchoNet-Dynamic was tested on this data set and then retrained, tested, and further validated to improve LVEF calculation. The gold standard value was LVEF calculated by clinical experts.INTERVENTIONSThe artificial intelligence model EchoNet-Dynamic was tested on this data set and then retrained, tested, and further validated to improve LVEF calculation. The gold standard value was LVEF calculated by clinical experts.In a random subset of subjects (n = 40) not analyzed prior to selection of the final model, EchoNet-Dynamic calculated LVEF with a MAE of 8.39%, R2 = 0.47 without, and MAE 4.47%, R2 = 0.87 with fine-tuning. Bland-Altman analysis suggested that the model slightly underestimates LVEF (bias = -2.42%). The 95% limits of agreement between actual and calculated values were -12.32% to 7.47%.MEASUREMENTS AND MAIN RESULTSIn a random subset of subjects (n = 40) not analyzed prior to selection of the final model, EchoNet-Dynamic calculated LVEF with a MAE of 8.39%, R2 = 0.47 without, and MAE 4.47%, R2 = 0.87 with fine-tuning. Bland-Altman analysis suggested that the model slightly underestimates LVEF (bias = -2.42%). The 95% limits of agreement between actual and calculated values were -12.32% to 7.47%.The fine-tuned model calculates LVEF in a range of pediatric patients within clinically acceptable error. Potential advantages include reducing operator error in LVEF calculation and supporting independent LVEF assessment by inexperienced users.CONCLUSIONSThe fine-tuned model calculates LVEF in a range of pediatric patients within clinically acceptable error. Potential advantages include reducing operator error in LVEF calculation and supporting independent LVEF assessment by inexperienced users.
Identifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a deep-learning algorithm predict pediatric LVEF within clinically acceptable error? The study authors wanted to fine-tune an adult deep-learning algorithm to calculate LVEF in pediatric patients. A priori, their objective was to refine the algorithm to perform LVEF calculation with a mean absolute error (MAE) ≤5%. A quaternary pediatric hospital PARTICIPANTS: A convenience sample (n = 321) of echocardiograms from newborns to 18 years old with normal cardiac anatomy or hemodynamically insignificant anomalies. Echocardiograms were chosen from a group of healthy controls with known normal LVEF (n = 267) and a dilated cardiomyopathy patient group with reduced LVEF (n = 54). The artificial intelligence model EchoNet-Dynamic was tested on this data set and then retrained, tested, and further validated to improve LVEF calculation. The gold standard value was LVEF calculated by clinical experts. In a random subset of subjects (n = 40) not analyzed prior to selection of the final model, EchoNet-Dynamic calculated LVEF with a MAE of 8.39%, R  = 0.47 without, and MAE 4.47%, R  = 0.87 with fine-tuning. Bland-Altman analysis suggested that the model slightly underestimates LVEF (bias = -2.42%). The 95% limits of agreement between actual and calculated values were -12.32% to 7.47%. The fine-tuned model calculates LVEF in a range of pediatric patients within clinically acceptable error. Potential advantages include reducing operator error in LVEF calculation and supporting independent LVEF assessment by inexperienced users.
Author Slorach, Cameron
Ufkes, Steven
Erdman, Lauren
Mertens, Luc
Taylor, Katherine
Zuercher, Mael
Author_xml – sequence: 1
  givenname: Mael
  orcidid: 0000-0002-9644-2940
  surname: Zuercher
  fullname: Zuercher, Mael
  organization: Department of Anesthesia and Pain Medicine, The Hospital for Sick Children, Toronto, Ontario, Canada
– sequence: 2
  givenname: Steven
  orcidid: 0000-0001-7460-8666
  surname: Ufkes
  fullname: Ufkes, Steven
  organization: Division of Genetics and Genome Biology, Hospital for Sick Children, Research Institute, Toronto, Ontario, Canada
– sequence: 3
  givenname: Lauren
  surname: Erdman
  fullname: Erdman, Lauren
  organization: Division of Genetics and Genome Biology, Hospital for Sick Children, Research Institute, Toronto, Ontario, Canada
– sequence: 4
  givenname: Cameron
  surname: Slorach
  fullname: Slorach, Cameron
  organization: Department of Cardiology, The Hospital for Sick Children, Toronto, Ontario, Canada
– sequence: 5
  givenname: Luc
  surname: Mertens
  fullname: Mertens, Luc
  organization: Department of Cardiology, The Hospital for Sick Children, Toronto, Ontario, Canada
– sequence: 6
  givenname: Katherine
  orcidid: 0000-0001-8663-3578
  surname: Taylor
  fullname: Taylor, Katherine
  email: Katherine.taylor@sickkids.ca
  organization: Department of Anesthesia and Pain Medicine, The Hospital for Sick Children, Toronto, Ontario, Canada
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35641411$$D View this record in MEDLINE/PubMed
BookMark eNqFkc1u1DAUhS1URH_gBVggL9kk-DfOIDajUQuVRipCwNby2DeDg-MU21Opb4-jaTddtCtfWee70v3OOTqJcwSE3lPSUiL5p7Ed76xpGWGsJbIlRLxCZ1Ry1vSCsZM611RDlCKn6DznkRBKpVRv0CmXnaCC0jM0_YCSjI8-7rGJeJ2KH7z1JuDrWCAEv4doAa_Dfk6-_JlwmfHGBHsIpgDewlDwb4gl-eUn4csRbPFzxFfJHAcf8Xdw3iyR_Ba9HkzI8O7hvUC_ri5_br4125uv15v1trGCqNIMltidEJIQs-KiNyvhuOk4pcCUGxRQN3RSEqMYH_odcNevXKeUZWKlmKvMBfp43Hub5n8HyEVPPtt6jokwH7JmXUWrt57X6IeH6GE3gdO3yU8m3etHRTXQHwM2zTknGLT1xSy3LeKCpkQvnvWolzb00oYmUtc2KsqeoI_bn4W-HCGogu48JJ2tX0pwPlW52s3-efzzE9yGWq814S_cvwT_B7iqtyQ
CitedBy_id crossref_primary_10_1016_j_echo_2023_01_015
crossref_primary_10_1109_ACCESS_2025_3545829
crossref_primary_10_3390_children12010014
crossref_primary_10_1088_2057_1976_ad7594
crossref_primary_10_3390_jcm11237072
crossref_primary_10_1017_pcm_2023_4
Cites_doi 10.1016/j.echo.2010.03.019
10.1016/j.jcmg.2011.06.004
10.1111/echo.14086
10.1186/s13089-017-0075-y
10.1161/JAHA.118.009124
10.1016/j.cardfail.2012.03.001
10.1016/j.ultrasmedbio.2018.07.024
10.1038/s41586-020-2145-8
10.1002/clc.20262
10.1007/s00246-010-9832-4
10.1093/ehjci/jev014
10.1016/j.echo.2019.05.025
10.1111/echo.15025
10.1038/s41746-019-0216-8
10.1007/s00246-013-0835-9
10.1016/j.echo.2015.03.004
10.1186/s13054-020-2787-9
10.1016/j.pedneo.2017.01.001
10.1093/eurheartj/ehw128
10.3390/jcm10071391
10.1213/ANE.0b013e3181c9f927
10.1186/s13089-016-0052-x
10.1101/2021.03.29.437045
ContentType Journal Article
Copyright 2022
Crown Copyright © 2022. Published by Elsevier Inc. All rights reserved.
Copyright_xml – notice: 2022
– notice: Crown Copyright © 2022. Published by Elsevier Inc. All rights reserved.
DBID AAYXX
CITATION
NPM
7X8
DOI 10.1053/j.jvca.2022.05.004
DatabaseName CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
PubMed

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1532-8422
EndPage 3616
ExternalDocumentID 35641411
10_1053_j_jvca_2022_05_004
S1053077022003299
Genre Journal Article
GroupedDBID ---
--K
--M
.1-
.FO
.GJ
.~1
0R~
1B1
1P~
1RT
1~.
1~5
4.4
457
4G.
53G
5GY
5RE
5VS
7-5
71M
8P~
9JM
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQQT
AAQXK
AATTM
AAXKI
AAXUO
AAYWO
ABBQC
ABFRF
ABJNI
ABMAC
ABMZM
ABOCM
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACIEU
ACLOT
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADMUD
ADNMO
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AEVXI
AFJKZ
AFPUW
AFRHN
AFTJW
AFXIZ
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJRQY
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ANZVX
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
BNPGV
CAG
COF
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HEB
HMK
HMO
HVGLF
HZ~
IHE
J1W
J5H
K-O
KOM
M29
M41
MO0
N9A
O-L
O9-
O90
OAUVE
OL-
OZT
P-8
P-9
P2P
PC.
Q38
R2-
ROL
RPZ
SAE
SCC
SDF
SDG
SDP
SEL
SES
SEW
SJN
SPCBC
SSH
SSZ
T5K
UHS
UNMZH
UV1
WUQ
Z5R
~G-
~HD
AACTN
AAIAV
ABLVK
ABYKQ
AFKWA
AJBFU
AJOXV
AMFUW
LCYCR
RIG
ZA5
9DU
AAYXX
CITATION
AFCTW
NPM
7X8
ID FETCH-LOGICAL-c407t-fc0cb44500a9348a94d3a6311e27df7e1df6550a723f8be3d89d677c24972da93
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000863663200023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1053-0770
1532-8422
IngestDate Sun Sep 28 08:56:35 EDT 2025
Thu Apr 03 06:59:37 EDT 2025
Sat Nov 29 06:57:34 EST 2025
Tue Nov 18 21:38:37 EST 2025
Fri Feb 23 02:41:22 EST 2024
Tue Oct 14 19:30:16 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 9
Keywords deep learning
cardiac function
artificial intelligence
pediatric patients
Language English
License Crown Copyright © 2022. Published by Elsevier Inc. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c407t-fc0cb44500a9348a94d3a6311e27df7e1df6550a723f8be3d89d677c24972da93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-9644-2940
0000-0001-8663-3578
0000-0001-7460-8666
PMID 35641411
PQID 2672320283
PQPubID 23479
PageCount 7
ParticipantIDs proquest_miscellaneous_2672320283
pubmed_primary_35641411
crossref_citationtrail_10_1053_j_jvca_2022_05_004
crossref_primary_10_1053_j_jvca_2022_05_004
elsevier_sciencedirect_doi_10_1053_j_jvca_2022_05_004
elsevier_clinicalkey_doi_10_1053_j_jvca_2022_05_004
PublicationCentury 2000
PublicationDate 2022-09-01
PublicationDateYYYYMMDD 2022-09-01
PublicationDate_xml – month: 09
  year: 2022
  text: 2022-09-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of cardiothoracic and vascular anesthesia
PublicationTitleAlternate J Cardiothorac Vasc Anesth
PublicationYear 2022
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Rajpurkar P, Hannun AY, Haghpanahi M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv 2017:1707.01836v1:1-9.
Kouris, Kostopoulos, Psarrou (bib0010) 2021; 38
Ouyang, He, Ghorbani (bib0015) 2020; 580
Ramamoorthy, Haberkern, Bhananker (bib0002) 2010; 110
Ponikowski, Voors, Anker (bib0007) 2016; 37
Akkus, Aly, Attia (bib0019) 2021; 10
Lang, Badano, Mor-Avi (bib0006) 2015; 16
Gandhi, Mosleh, Shen (bib0022) 2018; 35
Murphy, Smith, Ranger (bib0004) 2011; 32
Blanco, Volpicelli (bib0026) 2016; 8
Lee, Margossian, Sleeper (bib0013) 2014; 35
Accessed April 18, 2021.
Ghorbani, Ouyang, Abid (bib0014) 2020; 3
Masarone, Valente, Rubino (bib0005) 2017; 58
O'Dell (bib0018) 2019; 8
Singh, Tissot, Fraga (bib0024) 2020; 24
Lopez, Colan, Frommelt (bib0011) 2010; 23
Frommelt, Minich, Trachtenberg (bib0012) 2019; 32
Østvik, Smistad, Aase (bib0023) 2019; 45
Accessed April 2021
Daubert, Yow, Barnhart (bib0009) 2015; 28
Accessed April 18 2021
Massin, Astadicko, Dessy (bib0001) 2008; 31
Wang Y, Haghpanah FS, Zhang X, et al. ID-Seg: An accurate and reliable infant deep learning segmentation framework for limbic structures [e-pub ahead of print]. bioRxiv. doi
Rossano, Kim, Decker (bib0003) 2012; 18
Tran D, Wang H, Torresani L, et al. A closer look at spatiotemporal convolutions for action recognition. Available at
Kingma DP, Ba J. Adam: A method for stochastic optimization. Available at
Johri, Picard, Newell (bib0008) 2011; 4
De Marchi, Meineri (bib0025) 2017; 9
10.1053/j.jvca.2022.05.004_bib0017
Østvik (10.1053/j.jvca.2022.05.004_bib0023) 2019; 45
Rossano (10.1053/j.jvca.2022.05.004_bib0003) 2012; 18
Frommelt (10.1053/j.jvca.2022.05.004_bib0012) 2019; 32
Johri (10.1053/j.jvca.2022.05.004_bib0008) 2011; 4
Daubert (10.1053/j.jvca.2022.05.004_bib0009) 2015; 28
Singh (10.1053/j.jvca.2022.05.004_bib0024) 2020; 24
Akkus (10.1053/j.jvca.2022.05.004_bib0019) 2021; 10
10.1053/j.jvca.2022.05.004_bib0020
10.1053/j.jvca.2022.05.004_bib0021
Murphy (10.1053/j.jvca.2022.05.004_bib0004) 2011; 32
Gandhi (10.1053/j.jvca.2022.05.004_bib0022) 2018; 35
Ouyang (10.1053/j.jvca.2022.05.004_bib0015) 2020; 580
Lang (10.1053/j.jvca.2022.05.004_bib0006) 2015; 16
Blanco (10.1053/j.jvca.2022.05.004_bib0026) 2016; 8
De Marchi (10.1053/j.jvca.2022.05.004_bib0025) 2017; 9
Massin (10.1053/j.jvca.2022.05.004_bib0001) 2008; 31
Ramamoorthy (10.1053/j.jvca.2022.05.004_bib0002) 2010; 110
Kouris (10.1053/j.jvca.2022.05.004_bib0010) 2021; 38
Ponikowski (10.1053/j.jvca.2022.05.004_bib0007) 2016; 37
Lopez (10.1053/j.jvca.2022.05.004_bib0011) 2010; 23
Ghorbani (10.1053/j.jvca.2022.05.004_bib0014) 2020; 3
Masarone (10.1053/j.jvca.2022.05.004_bib0005) 2017; 58
Lee (10.1053/j.jvca.2022.05.004_bib0013) 2014; 35
10.1053/j.jvca.2022.05.004_bib0016
O'Dell (10.1053/j.jvca.2022.05.004_bib0018) 2019; 8
References_xml – volume: 9
  start-page: 19
  year: 2017
  ident: bib0025
  article-title: POCUS in perioperative medicine: A North American perspective
  publication-title: Crit Ultrasound J
– volume: 28
  start-page: 959
  year: 2015
  end-page: 968
  ident: bib0009
  article-title: Quality improvement implementation: Improving reproducibility in the echocardiography laboratory
  publication-title: J Am Soc Echocardiogr
– volume: 32
  start-page: 1331
  year: 2019
  end-page: 1338
  ident: bib0012
  article-title: Challenges with left ventricular functional parameters: The Pediatric Heart Network Normal Echocardiogram Database
  publication-title: J Am Soc Echocardiogr
– volume: 110
  start-page: 1376
  year: 2010
  end-page: 1382
  ident: bib0002
  article-title: Anesthesia-related cardiac arrest in children with heart disease: Data from the Pediatric Perioperative Cardiac Arrest (POCA) Registry
  publication-title: Anesth Analg
– volume: 31
  start-page: 388
  year: 2008
  end-page: 391
  ident: bib0001
  article-title: Epidemiology of heart failure in a tertiary pediatric center
  publication-title: Clin Cardiol
– volume: 37
  start-page: 2129
  year: 2016
  end-page: 2200
  ident: bib0007
  article-title: 2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: The Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC) Developed with the special contribution of the Heart Failure Association (HFA) of the ESC
  publication-title: Eur Heart J
– volume: 16
  start-page: 233
  year: 2015
  end-page: 271
  ident: bib0006
  article-title: Recommendations for cardiac chamber quantification by echocardiography in adults: An update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging
  publication-title: Eur Heart J Cardiovasc Imaging
– volume: 38
  start-page: 582
  year: 2021
  end-page: 589
  ident: bib0010
  article-title: Left ventricular ejection fraction and Global Longitudinal Strain variability between methodology and experience
  publication-title: Echocardiography
– volume: 32
  start-page: 139
  year: 2011
  end-page: 144
  ident: bib0004
  article-title: General anesthesia for children with severe heart failure
  publication-title: Pediatr Cardiol
– volume: 8
  year: 2019
  ident: bib0018
  article-title: Accuracy of left ventricular cavity volume and ejection fraction for conventional estimation methods and 3D surface fitting
  publication-title: J Am Heart Assoc
– volume: 8
  start-page: 15
  year: 2016
  ident: bib0026
  article-title: Common pitfalls in point-of-care ultrasound: A practical guide for emergency and critical care physicians
  publication-title: Crit Ultrasound J
– reference: . Accessed April 2021
– volume: 18
  start-page: 459
  year: 2012
  end-page: 470
  ident: bib0003
  article-title: Prevalence, morbidity, and mortality of heart failure-related hospitalizations in children in the United States: A population-based study
  publication-title: J Card Fail
– reference: Wang Y, Haghpanah FS, Zhang X, et al. ID-Seg: An accurate and reliable infant deep learning segmentation framework for limbic structures [e-pub ahead of print]. bioRxiv. doi:
– volume: 3
  start-page: 10
  year: 2020
  ident: bib0014
  article-title: Deep learning interpretation of echocardiograms
  publication-title: NPJ Digit Med
– reference: Kingma DP, Ba J. Adam: A method for stochastic optimization. Available at:
– reference: Tran D, Wang H, Torresani L, et al. A closer look at spatiotemporal convolutions for action recognition. Available at:
– volume: 24
  start-page: 65
  year: 2020
  ident: bib0024
  article-title: International evidence-based guidelines on Point of Care Ultrasound (POCUS) for critically ill neonates and children issued by the POCUS Working Group of the European Society of Paediatric and Neonatal Intensive Care (ESPNIC)
  publication-title: Crit Care
– volume: 4
  start-page: 821
  year: 2011
  end-page: 829
  ident: bib0008
  article-title: Can a teaching intervention reduce interobserver variability in LVEF assessment: A quality control exercise in the echocardiography lab
  publication-title: JACC Cardiovasc Imaging
– reference: . Accessed April 18 2021
– volume: 23
  start-page: 465
  year: 2010
  end-page: 495
  ident: bib0011
  article-title: Recommendations for quantification methods during the performance of a pediatric echocardiogram: A report from the Pediatric Measurements Writing Group of the American Society of Echocardiography Pediatric and Congenital Heart Disease Council
  publication-title: J Am Soc Echocardiogr
– volume: 35
  start-page: 658
  year: 2014
  end-page: 667
  ident: bib0013
  article-title: Variability of M-mode versus two-dimensional echocardiography measurements in children with dilated cardiomyopathy
  publication-title: Pediatr Cardiol
– volume: 45
  start-page: 374
  year: 2019
  end-page: 384
  ident: bib0023
  article-title: Real-time standard view classification in transthoracic echocardiography using convolutional neural networks
  publication-title: Ultrasound Med Biol
– reference: . Accessed April 18, 2021.
– volume: 58
  start-page: 303
  year: 2017
  end-page: 312
  ident: bib0005
  article-title: Pediatric heart failure: A practical guide to diagnosis and management
  publication-title: Pediatr Neonatol
– volume: 10
  start-page: 1391
  year: 2021
  ident: bib0019
  article-title: Artificial intelligence (AI)-empowered echocardiography interpretation: A state-of-the-art review
  publication-title: J Clin Med
– reference: Rajpurkar P, Hannun AY, Haghpanahi M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv 2017:1707.01836v1:1-9.
– volume: 580
  start-page: 252
  year: 2020
  end-page: 256
  ident: bib0015
  article-title: Video-based AI for beat-to-beat assessment of cardiac function
  publication-title: Nature
– volume: 35
  start-page: 1402
  year: 2018
  end-page: 1418
  ident: bib0022
  article-title: Automation, machine learning, and artificial intelligence in echocardiography: A brave new world
  publication-title: Echocardiography
– volume: 23
  start-page: 465
  year: 2010
  ident: 10.1053/j.jvca.2022.05.004_bib0011
  article-title: Recommendations for quantification methods during the performance of a pediatric echocardiogram: A report from the Pediatric Measurements Writing Group of the American Society of Echocardiography Pediatric and Congenital Heart Disease Council
  publication-title: J Am Soc Echocardiogr
  doi: 10.1016/j.echo.2010.03.019
– volume: 4
  start-page: 821
  year: 2011
  ident: 10.1053/j.jvca.2022.05.004_bib0008
  article-title: Can a teaching intervention reduce interobserver variability in LVEF assessment: A quality control exercise in the echocardiography lab
  publication-title: JACC Cardiovasc Imaging
  doi: 10.1016/j.jcmg.2011.06.004
– ident: 10.1053/j.jvca.2022.05.004_bib0017
– volume: 35
  start-page: 1402
  year: 2018
  ident: 10.1053/j.jvca.2022.05.004_bib0022
  article-title: Automation, machine learning, and artificial intelligence in echocardiography: A brave new world
  publication-title: Echocardiography
  doi: 10.1111/echo.14086
– volume: 9
  start-page: 19
  year: 2017
  ident: 10.1053/j.jvca.2022.05.004_bib0025
  article-title: POCUS in perioperative medicine: A North American perspective
  publication-title: Crit Ultrasound J
  doi: 10.1186/s13089-017-0075-y
– volume: 8
  year: 2019
  ident: 10.1053/j.jvca.2022.05.004_bib0018
  article-title: Accuracy of left ventricular cavity volume and ejection fraction for conventional estimation methods and 3D surface fitting
  publication-title: J Am Heart Assoc
  doi: 10.1161/JAHA.118.009124
– volume: 18
  start-page: 459
  year: 2012
  ident: 10.1053/j.jvca.2022.05.004_bib0003
  article-title: Prevalence, morbidity, and mortality of heart failure-related hospitalizations in children in the United States: A population-based study
  publication-title: J Card Fail
  doi: 10.1016/j.cardfail.2012.03.001
– volume: 45
  start-page: 374
  year: 2019
  ident: 10.1053/j.jvca.2022.05.004_bib0023
  article-title: Real-time standard view classification in transthoracic echocardiography using convolutional neural networks
  publication-title: Ultrasound Med Biol
  doi: 10.1016/j.ultrasmedbio.2018.07.024
– volume: 580
  start-page: 252
  year: 2020
  ident: 10.1053/j.jvca.2022.05.004_bib0015
  article-title: Video-based AI for beat-to-beat assessment of cardiac function
  publication-title: Nature
  doi: 10.1038/s41586-020-2145-8
– volume: 31
  start-page: 388
  year: 2008
  ident: 10.1053/j.jvca.2022.05.004_bib0001
  article-title: Epidemiology of heart failure in a tertiary pediatric center
  publication-title: Clin Cardiol
  doi: 10.1002/clc.20262
– volume: 32
  start-page: 139
  year: 2011
  ident: 10.1053/j.jvca.2022.05.004_bib0004
  article-title: General anesthesia for children with severe heart failure
  publication-title: Pediatr Cardiol
  doi: 10.1007/s00246-010-9832-4
– volume: 16
  start-page: 233
  year: 2015
  ident: 10.1053/j.jvca.2022.05.004_bib0006
  article-title: Recommendations for cardiac chamber quantification by echocardiography in adults: An update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging
  publication-title: Eur Heart J Cardiovasc Imaging
  doi: 10.1093/ehjci/jev014
– volume: 32
  start-page: 1331
  year: 2019
  ident: 10.1053/j.jvca.2022.05.004_bib0012
  article-title: Challenges with left ventricular functional parameters: The Pediatric Heart Network Normal Echocardiogram Database
  publication-title: J Am Soc Echocardiogr
  doi: 10.1016/j.echo.2019.05.025
– volume: 38
  start-page: 582
  year: 2021
  ident: 10.1053/j.jvca.2022.05.004_bib0010
  article-title: Left ventricular ejection fraction and Global Longitudinal Strain variability between methodology and experience
  publication-title: Echocardiography
  doi: 10.1111/echo.15025
– ident: 10.1053/j.jvca.2022.05.004_bib0016
– volume: 3
  start-page: 10
  year: 2020
  ident: 10.1053/j.jvca.2022.05.004_bib0014
  article-title: Deep learning interpretation of echocardiograms
  publication-title: NPJ Digit Med
  doi: 10.1038/s41746-019-0216-8
– volume: 35
  start-page: 658
  year: 2014
  ident: 10.1053/j.jvca.2022.05.004_bib0013
  article-title: Variability of M-mode versus two-dimensional echocardiography measurements in children with dilated cardiomyopathy
  publication-title: Pediatr Cardiol
  doi: 10.1007/s00246-013-0835-9
– volume: 28
  start-page: 959
  year: 2015
  ident: 10.1053/j.jvca.2022.05.004_bib0009
  article-title: Quality improvement implementation: Improving reproducibility in the echocardiography laboratory
  publication-title: J Am Soc Echocardiogr
  doi: 10.1016/j.echo.2015.03.004
– volume: 24
  start-page: 65
  year: 2020
  ident: 10.1053/j.jvca.2022.05.004_bib0024
  article-title: International evidence-based guidelines on Point of Care Ultrasound (POCUS) for critically ill neonates and children issued by the POCUS Working Group of the European Society of Paediatric and Neonatal Intensive Care (ESPNIC)
  publication-title: Crit Care
  doi: 10.1186/s13054-020-2787-9
– volume: 58
  start-page: 303
  year: 2017
  ident: 10.1053/j.jvca.2022.05.004_bib0005
  article-title: Pediatric heart failure: A practical guide to diagnosis and management
  publication-title: Pediatr Neonatol
  doi: 10.1016/j.pedneo.2017.01.001
– volume: 37
  start-page: 2129
  year: 2016
  ident: 10.1053/j.jvca.2022.05.004_bib0007
  publication-title: Eur Heart J
  doi: 10.1093/eurheartj/ehw128
– volume: 10
  start-page: 1391
  year: 2021
  ident: 10.1053/j.jvca.2022.05.004_bib0019
  article-title: Artificial intelligence (AI)-empowered echocardiography interpretation: A state-of-the-art review
  publication-title: J Clin Med
  doi: 10.3390/jcm10071391
– volume: 110
  start-page: 1376
  year: 2010
  ident: 10.1053/j.jvca.2022.05.004_bib0002
  article-title: Anesthesia-related cardiac arrest in children with heart disease: Data from the Pediatric Perioperative Cardiac Arrest (POCA) Registry
  publication-title: Anesth Analg
  doi: 10.1213/ANE.0b013e3181c9f927
– volume: 8
  start-page: 15
  year: 2016
  ident: 10.1053/j.jvca.2022.05.004_bib0026
  article-title: Common pitfalls in point-of-care ultrasound: A practical guide for emergency and critical care physicians
  publication-title: Crit Ultrasound J
  doi: 10.1186/s13089-016-0052-x
– ident: 10.1053/j.jvca.2022.05.004_bib0020
  doi: 10.1101/2021.03.29.437045
– ident: 10.1053/j.jvca.2022.05.004_bib0021
SSID ssj0011557
Score 2.3638349
Snippet Identifying patients with low left ventricular ejection fraction (LVEF) and monitoring LVEF responses to treatment are important clinical goals. Can a...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 3610
SubjectTerms artificial intelligence
cardiac function
deep learning
pediatric patients
Title Retraining an Artificial Intelligence Algorithm to Calculate Left Ventricular Ejection Fraction in Pediatrics
URI https://www.clinicalkey.com/#!/content/1-s2.0-S1053077022003299
https://dx.doi.org/10.1053/j.jvca.2022.05.004
https://www.ncbi.nlm.nih.gov/pubmed/35641411
https://www.proquest.com/docview/2672320283
Volume 36
WOSCitedRecordID wos000863663200023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1532-8422
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011557
  issn: 1053-0770
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELdKh9BeEN90wGQk3qpAYidx8lhNnQBpE4INVbxEjmOzlDad0rTaf8e_xjm20_LRwR54iRqrzofv5_NdfHc_hF5JpWgklPIoUQwclJR7XES-R_IgzyPQi1z4LdkEOz1NJpP0Q6_33eXCrGesqpKrq_Tyv4oa2kDYOnX2BuLuLgoN8BuEDkcQOxz_SfAfpaN9GMLcHdVtMJApqbFVfXM0-7qoy-Ziro3PIz7T4aiNzu5RzfCz_uJbmgDV8VQaMvHj2rKKl6A1Hb_HcodtK9oo1-YC8CVsQdgu5JWDcgWrc1l2C8KXlawddk5cDD-0n6tvRokZ6rXO-K8LlzHBV1upbJ9m-nZmy4jPZW0BZz9pgDfsYracFgbN4PnMMIo4NW3qpFg4pls6l8Y2MFa60_iPa4PfEnxMX0_XQhecIqQt2WrIj38uxP3LAtmFLbYb9hEFh0lfI9PXyPwoa-vR7hEWpUkf7Y3ejSfvu40sMNdafh_3RjZvC07f_P4ku2yjXb5PawOd3UN3rYDxyIDuPurJ6gG6c2LDMx6i-QZ7mFd4gz28jT3cYQ83C9xhD2vs4S3sYYc97LCHywpvsPcInR-Pz47eepbPwxOhzxpPCV_kYQgagKc0THgaFpTHNAgkYYViMihUDA4zZ4SqJJe0SNIiZkyQMGWkgD6PUb9aVPIpwknOKVineShkHEYFT0gg_TRXMVGcw7IyQIEbyUzYYvd6AGbZbhkO0LDrc2lKvVz7b-oElLkkZlh2M0Dbtb2irpc1cY3p-td-Lx0GMtD_elMPZutitcxIDMNFtJcwQE8MOLqnp1EcBmEQHNzozZ6h_c2kfI76Tb2SL9BtsW7KZX2IbrFJcmhh_gM_7-EE
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=Retraining+an+Artificial+Intelligence+Algorithm+to+Calculate+Left+Ventricular+Ejection+Fraction+in+Pediatrics&rft.jtitle=Journal+of+cardiothoracic+and+vascular+anesthesia&rft.au=Zuercher%2C+Mael&rft.au=Ufkes%2C+Steven&rft.au=Erdman%2C+Lauren&rft.au=Slorach%2C+Cameron&rft.date=2022-09-01&rft.issn=1053-0770&rft.volume=36&rft.issue=9&rft.spage=3610&rft.epage=3616&rft_id=info:doi/10.1053%2Fj.jvca.2022.05.004&rft.externalDBID=n%2Fa&rft.externalDocID=10_1053_j_jvca_2022_05_004
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-0770&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-0770&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-0770&client=summon