Deep conditional generative model for personalization of 12-lead electrocardiograms and cardiovascular risk prediction

12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting abnormalities such as arrhythmias and myocardial infarction, enabling early intervention and risk stratification. However, traditional analysis relies h...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Frontiers in digital health Ročník 7; s. 1558589
Hlavní autori: Sang, Yuling, Banerjee, Abhirup, Beetz, Marcel, Grau, Vicente
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland Frontiers Media S.A 16.04.2025
Predmet:
ISSN:2673-253X, 2673-253X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract 12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting abnormalities such as arrhythmias and myocardial infarction, enabling early intervention and risk stratification. However, traditional analysis relies heavily on manual interpretation, which is time-consuming and expertise-dependent. Moreover, existing machine learning models often lack personalization, as they fail to integrate subject-specific anatomical and demographic information. Advances in deep generative models offer an opportunity to overcome these challenges by synthesizing personalized ECGs and extracting clinically relevant features for improved risk assessment. We propose a conditional Variational Autoencoder (cVAE) framework to generate realistic, subject-specific 12-lead ECGs by incorporating demographic metadata, anatomical heart features, and ECG electrodes' positions as conditioning factors. This allows for physiologically consistent and personalized ECG synthesis. Furthermore, we introduce a revised Cox proportional-hazards regression model that utilizes the latent embeddings learned by the cVAE to predict future CVD risk. This approach not only enhances the interpretability of ECG-derived risk factors but also demonstrates the potential of deep generative models in personalized cardiac assessment. Our model is trained and validated on the UK Biobank dataset and simulation data. By incorporating heart position and electrodes' positions, the generated ECGs demonstrate strong consistency with simulations, providing insights into the relationship between cardiac anatomy and ECG morphology. Furthermore, our CVD risk prediction model achieves a C-index of 0.65, indicating that ECG signals, together with demographic and anatomical information, contain valuable prognostic information for stratifying subjects based on future cardiovascular risk. This work marks a significant advancement in ECG analysis by providing a conditional VAE framework that not only improves ECG generation but also enriches our understanding of the relationship between ECG patterns and subject-specific information. Importantly, our approach enables clinically significant information to be extracted from 12-lead ECGs, providing valuable insights for predicting future CVD risks.
AbstractList 12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting abnormalities such as arrhythmias and myocardial infarction, enabling early intervention and risk stratification. However, traditional analysis relies heavily on manual interpretation, which is time-consuming and expertise-dependent. Moreover, existing machine learning models often lack personalization, as they fail to integrate subject-specific anatomical and demographic information. Advances in deep generative models offer an opportunity to overcome these challenges by synthesizing personalized ECGs and extracting clinically relevant features for improved risk assessment. We propose a conditional Variational Autoencoder (cVAE) framework to generate realistic, subject-specific 12-lead ECGs by incorporating demographic metadata, anatomical heart features, and ECG electrodes' positions as conditioning factors. This allows for physiologically consistent and personalized ECG synthesis. Furthermore, we introduce a revised Cox proportional-hazards regression model that utilizes the latent embeddings learned by the cVAE to predict future CVD risk. This approach not only enhances the interpretability of ECG-derived risk factors but also demonstrates the potential of deep generative models in personalized cardiac assessment. Our model is trained and validated on the UK Biobank dataset and simulation data. By incorporating heart position and electrodes' positions, the generated ECGs demonstrate strong consistency with simulations, providing insights into the relationship between cardiac anatomy and ECG morphology. Furthermore, our CVD risk prediction model achieves a C-index of 0.65, indicating that ECG signals, together with demographic and anatomical information, contain valuable prognostic information for stratifying subjects based on future cardiovascular risk. This work marks a significant advancement in ECG analysis by providing a conditional VAE framework that not only improves ECG generation but also enriches our understanding of the relationship between ECG patterns and subject-specific information. Importantly, our approach enables clinically significant information to be extracted from 12-lead ECGs, providing valuable insights for predicting future CVD risks.
12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting abnormalities such as arrhythmias and myocardial infarction, enabling early intervention and risk stratification. However, traditional analysis relies heavily on manual interpretation, which is time-consuming and expertise-dependent. Moreover, existing machine learning models often lack personalization, as they fail to integrate subject-specific anatomical and demographic information. Advances in deep generative models offer an opportunity to overcome these challenges by synthesizing personalized ECGs and extracting clinically relevant features for improved risk assessment.Background12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting abnormalities such as arrhythmias and myocardial infarction, enabling early intervention and risk stratification. However, traditional analysis relies heavily on manual interpretation, which is time-consuming and expertise-dependent. Moreover, existing machine learning models often lack personalization, as they fail to integrate subject-specific anatomical and demographic information. Advances in deep generative models offer an opportunity to overcome these challenges by synthesizing personalized ECGs and extracting clinically relevant features for improved risk assessment.We propose a conditional Variational Autoencoder (cVAE) framework to generate realistic, subject-specific 12-lead ECGs by incorporating demographic metadata, anatomical heart features, and ECG electrodes' positions as conditioning factors. This allows for physiologically consistent and personalized ECG synthesis. Furthermore, we introduce a revised Cox proportional-hazards regression model that utilizes the latent embeddings learned by the cVAE to predict future CVD risk. This approach not only enhances the interpretability of ECG-derived risk factors but also demonstrates the potential of deep generative models in personalized cardiac assessment.MethodsWe propose a conditional Variational Autoencoder (cVAE) framework to generate realistic, subject-specific 12-lead ECGs by incorporating demographic metadata, anatomical heart features, and ECG electrodes' positions as conditioning factors. This allows for physiologically consistent and personalized ECG synthesis. Furthermore, we introduce a revised Cox proportional-hazards regression model that utilizes the latent embeddings learned by the cVAE to predict future CVD risk. This approach not only enhances the interpretability of ECG-derived risk factors but also demonstrates the potential of deep generative models in personalized cardiac assessment.Our model is trained and validated on the UK Biobank dataset and in silico simulation data. By incorporating heart position and electrodes' positions, the generated ECGs demonstrate strong consistency with in silico simulations, providing insights into the relationship between cardiac anatomy and ECG morphology. Furthermore, our CVD risk prediction model achieves a C-index of 0.65, indicating that ECG signals, together with demographic and anatomical information, contain valuable prognostic information for stratifying subjects based on future cardiovascular risk.ResultsOur model is trained and validated on the UK Biobank dataset and in silico simulation data. By incorporating heart position and electrodes' positions, the generated ECGs demonstrate strong consistency with in silico simulations, providing insights into the relationship between cardiac anatomy and ECG morphology. Furthermore, our CVD risk prediction model achieves a C-index of 0.65, indicating that ECG signals, together with demographic and anatomical information, contain valuable prognostic information for stratifying subjects based on future cardiovascular risk.This work marks a significant advancement in ECG analysis by providing a conditional VAE framework that not only improves ECG generation but also enriches our understanding of the relationship between ECG patterns and subject-specific information. Importantly, our approach enables clinically significant information to be extracted from 12-lead ECGs, providing valuable insights for predicting future CVD risks.ConclusionThis work marks a significant advancement in ECG analysis by providing a conditional VAE framework that not only improves ECG generation but also enriches our understanding of the relationship between ECG patterns and subject-specific information. Importantly, our approach enables clinically significant information to be extracted from 12-lead ECGs, providing valuable insights for predicting future CVD risks.
Background12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting abnormalities such as arrhythmias and myocardial infarction, enabling early intervention and risk stratification. However, traditional analysis relies heavily on manual interpretation, which is time-consuming and expertise-dependent. Moreover, existing machine learning models often lack personalization, as they fail to integrate subject-specific anatomical and demographic information. Advances in deep generative models offer an opportunity to overcome these challenges by synthesizing personalized ECGs and extracting clinically relevant features for improved risk assessment.MethodsWe propose a conditional Variational Autoencoder (cVAE) framework to generate realistic, subject-specific 12-lead ECGs by incorporating demographic metadata, anatomical heart features, and ECG electrodes’ positions as conditioning factors. This allows for physiologically consistent and personalized ECG synthesis. Furthermore, we introduce a revised Cox proportional-hazards regression model that utilizes the latent embeddings learned by the cVAE to predict future CVD risk. This approach not only enhances the interpretability of ECG-derived risk factors but also demonstrates the potential of deep generative models in personalized cardiac assessment.ResultsOur model is trained and validated on the UK Biobank dataset and in silico simulation data. By incorporating heart position and electrodes’ positions, the generated ECGs demonstrate strong consistency with in silico simulations, providing insights into the relationship between cardiac anatomy and ECG morphology. Furthermore, our CVD risk prediction model achieves a C-index of 0.65, indicating that ECG signals, together with demographic and anatomical information, contain valuable prognostic information for stratifying subjects based on future cardiovascular risk.ConclusionThis work marks a significant advancement in ECG analysis by providing a conditional VAE framework that not only improves ECG generation but also enriches our understanding of the relationship between ECG patterns and subject-specific information. Importantly, our approach enables clinically significant information to be extracted from 12-lead ECGs, providing valuable insights for predicting future CVD risks.
Author Sang, Yuling
Beetz, Marcel
Grau, Vicente
Banerjee, Abhirup
AuthorAffiliation 2 Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford , Oxford , United Kingdom
3 Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford , Oxford , United Kingdom
1 Centre for Computational Biology, Duke-NUS Medical School , Singapore , Singapore
AuthorAffiliation_xml – name: 1 Centre for Computational Biology, Duke-NUS Medical School , Singapore , Singapore
– name: 2 Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford , Oxford , United Kingdom
– name: 3 Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford , Oxford , United Kingdom
Author_xml – sequence: 1
  givenname: Yuling
  surname: Sang
  fullname: Sang, Yuling
– sequence: 2
  givenname: Abhirup
  surname: Banerjee
  fullname: Banerjee, Abhirup
– sequence: 3
  givenname: Marcel
  surname: Beetz
  fullname: Beetz, Marcel
– sequence: 4
  givenname: Vicente
  surname: Grau
  fullname: Grau, Vicente
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40309320$$D View this record in MEDLINE/PubMed
BookMark eNpVkk1v1DAQhiNURD_oH-CAfOSSZWzHiX1CqECpVIkLSNysiT1JXZJ4sbMrwa8n6S5Ve7I98-gZjfyeFydTnKgo3nDYSKnN-873891GgFAbrpRW2rwozkTdyFIo-fPkyf20uMz5HmBBuRCgXhWnFUgwUsBZsf9EtGUuTj7MIU44sJ4mSjiHPbExehpYFxPbUsprN_zFFWOxY1yUA6FnNJCbU3SYfIh9wjEznDw7vPeY3W7AxFLIv9g2kQ9uFbwuXnY4ZLo8nhfFjy-fv199LW-_Xd9cfbwtXSXEXKKH2htVtUprboyWnaRu2UNITxwQgAQ0pm51rbDuTFV5WbcNKK5aqBQIeVHcHLw-4r3dpjBi-mMjBvtQiKm3mObgBrICORjBW66pqUzjjXbYNprq2pm2gmZxfTi4trt2JO9omhMOz6TPO1O4s33cWy6gAqP0Ynh3NKT4e0d5tmPIjoYBJ4q7bCVfVuSNkvWCvn067HHK_59bAHEAXIo5J-oeEQ52TYh9SIhdE2KPCZH_ABGWsGI
Cites_doi 10.1002/sim.1802
10.1007/s10916-010-9551-7
10.1371/journal.pone.0213653
10.1109/TMI.2024.3367409
10.1109/ISBI52829.2022.9761590
10.1098/rsta.2020.0257
10.3389/fcvm.2023.1110424
10.1136/bmj.h7013
10.1093/ije/dyz212
10.1371/journal.pmed.1001779
10.1007/978-3-031-23443-9_34
10.3389/fphys.2022.886723
10.3389/fphys.2021.811029
10.1186/s12968-016-0227-4
10.1109/TBDATA.2025.3536922
10.1093/eurheartj/ehad655.2380
10.1109/WCSP.2010.5633782
10.1109/ICHI.2016.83
10.1109/EMBC48229.2022.9871643
10.22489/CinC.2020.107
10.1002/sim.4780030207
10.1038/s41598-019-42516-z
10.3389/fphys.2019.01103
10.1113/jphysiol.1887.sp000257
10.1177/0091270011430505
10.1109/TITB.2008.2003323
10.1109/ISBI52829.2022.9761431
ContentType Journal Article
Copyright 2025 Sang, Banerjee, Beetz and Grau.
2025 Sang, Banerjee, Beetz and Grau. 2025 Sang, Banerjee, Beetz and Grau
Copyright_xml – notice: 2025 Sang, Banerjee, Beetz and Grau.
– notice: 2025 Sang, Banerjee, Beetz and Grau. 2025 Sang, Banerjee, Beetz and Grau
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3389/fdgth.2025.1558589
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: DOA
  name: Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2673-253X
ExternalDocumentID oai_doaj_org_article_2a10921b18e7497d98cab78e66c9b407
PMC12040958
40309320
10_3389_fdgth_2025_1558589
Genre Journal Article
GroupedDBID 53G
9T4
AAFWJ
AAYXX
AFPKN
ALMA_UNASSIGNED_HOLDINGS
CITATION
EIHBH
GROUPED_DOAJ
M~E
OK1
PGMZT
RPM
ACXDI
NPM
7X8
5PM
ID FETCH-LOGICAL-c422t-ad06d954b58819983f3ef02523de10a00e20796b865a6f944d36b70515b045023
IEDL.DBID DOA
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001478746300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2673-253X
IngestDate Fri Oct 03 12:52:53 EDT 2025
Thu Aug 21 18:26:31 EDT 2025
Fri Sep 05 17:19:33 EDT 2025
Sat May 03 02:04:38 EDT 2025
Sat Nov 29 08:01:04 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords cardiovascular disease
ECG generation
cardiovascular risk prediction
cardiac MRI
ECG electrodes
variational autoencoder
Language English
License 2025 Sang, Banerjee, Beetz and Grau.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c422t-ad06d954b58819983f3ef02523de10a00e20796b865a6f944d36b70515b045023
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Reviewed by: Heyam A. Marzog, Al-Furat Al-Awsat Technical University, Iraq
Edited by: Xiaofeng Li, Heilongjiang International University, China
Katya Arquilla, University of Colorado Boulder, United States
OpenAccessLink https://doaj.org/article/2a10921b18e7497d98cab78e66c9b407
PMID 40309320
PQID 3198317536
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_2a10921b18e7497d98cab78e66c9b407
pubmedcentral_primary_oai_pubmedcentral_nih_gov_12040958
proquest_miscellaneous_3198317536
pubmed_primary_40309320
crossref_primary_10_3389_fdgth_2025_1558589
PublicationCentury 2000
PublicationDate 2025-04-16
PublicationDateYYYYMMDD 2025-04-16
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-16
  day: 16
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Frontiers in digital health
PublicationTitleAlternate Front Digit Health
PublicationYear 2025
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Kuznetsov (B13)
Beetz (B3) 2022; 13
Wu (B23) 2023; 10
Strain (B27) 2020; 49
Esteban (B12)
Zhang (B9)
Smith (B19)
Sudlow (B24) 2015; 12
George (B2) 2012; 52
Li (B7)
Natarajan (B25)
Beetz (B4)
Zhu (B14) 2019; 9
Petersen (B26) 2015; 18
Waller (B1) 1887; 8
Alaa (B20) 2019; 14
Emdin (B21) 2016; 352
Harrell Jr (B30) 1984; 3
Benali (B5) 2012; 36
Pencina (B31) 2004; 23
Li (B8) 2024; 43
Jæger (B16) 2022; 12
Mincholé (B15) 2019; 10
Chen (B10)
Kingma (B29)
Banerjee (B28) 2021; 379
Kampouraki (B6) 2008; 13
Smith (B18)
McLachlan (B11)
Turnbull (B22) 2023; 44
Sang (B17)
References_xml – volume: 23
  start-page: 2109
  year: 2004
  ident: B31
  article-title: Overall c as a measure of discrimination in survival analysis: model specific population value and confidence interval estimation
  publication-title: Stat Med
  doi: 10.1002/sim.1802
– ident: B13
  article-title: Electrocardiogram generation and feature extraction using a variational autoencoder
– ident: B29
  article-title: Adam: a method for stochastic optimization
– volume: 36
  start-page: 883
  year: 2012
  ident: B5
  article-title: Automatic classification of heartbeats using wavelet neural network
  publication-title: J Med Syst
  doi: 10.1007/s10916-010-9551-7
– volume: 14
  start-page: e0213653
  year: 2019
  ident: B20
  article-title: Cardiovascular disease risk prediction using automated machine learning: a prospective study of 423,604 UK Biobank participants
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0213653
– ident: B12
  article-title: Real-valued (medical) time series generation with recurrent conditional gans
– volume: 43
  start-page: 2466
  year: 2024
  ident: B8
  article-title: Toward enabling cardiac digital twins of myocardial infarction using deep computational models for inverse inference
  publication-title: IEEE Trans Med Imaging
  doi: 10.1109/TMI.2024.3367409
– ident: B4
  article-title: Combined generation of electrocardiogram and cardiac anatomy models using multi-modal variational autoencoders
  doi: 10.1109/ISBI52829.2022.9761590
– volume: 379
  start-page: 20200257
  year: 2021
  ident: B28
  article-title: A completely automated pipeline for 3D reconstruction of human heart from 2D cine magnetic resonance slices
  publication-title: Philos Trans R Soc A
  doi: 10.1098/rsta.2020.0257
– volume: 10
  start-page: 1110424
  year: 2023
  ident: B23
  article-title: Association between cardiovascular risk factors and atrial fibrillation
  publication-title: Front Cardiovasc Med
  doi: 10.3389/fcvm.2023.1110424
– volume: 352
  start-page: h7013
  year: 2016
  ident: B21
  article-title: Atrial fibrillation as risk factor for cardiovascular disease and death in women compared with men: systematic review and meta-analysis of cohort studies
  publication-title: BMJ
  doi: 10.1136/bmj.h7013
– volume: 49
  start-page: 162
  year: 2020
  ident: B27
  article-title: Impact of follow-up time and analytical approaches to account for reverse causality on the association between physical activity and health outcomes in UK Biobank
  publication-title: Int J Epidemiol
  doi: 10.1093/ije/dyz212
– volume: 12
  start-page: e1001779
  year: 2015
  ident: B24
  article-title: UK Biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age
  publication-title: PLoS Med
  doi: 10.1371/journal.pmed.1001779
– ident: B19
  article-title: Anatomical basis of sex differences in human post-myocardial infarction ECG phenotypes identified by novel automated torso-cardiac 3D reconstruction
– ident: B7
  article-title: Deep computational model for the inference of ventricular activation properties
  doi: 10.1007/978-3-031-23443-9_34
– volume: 13
  start-page: 886723
  year: 2022
  ident: B3
  article-title: Multi-domain variational autoencoders for combined modeling of MRI-based biventricular anatomy and ECG-based cardiac electrophysiology
  publication-title: Front Physiol
  doi: 10.3389/fphys.2022.886723
– volume: 12
  start-page: 811029
  year: 2022
  ident: B16
  article-title: Deriving the bidomain model of cardiac electrophysiology from a cell-based model; properties and comparisons
  publication-title: Front Physiol
  doi: 10.3389/fphys.2021.811029
– volume: 18
  start-page: 1
  year: 2015
  ident: B26
  article-title: UK Biobank’s cardiovascular magnetic resonance protocol
  publication-title: J Cardiovasc Magn Reson
  doi: 10.1186/s12968-016-0227-4
– ident: B10
  article-title: Large language model-informed ECG dual attention network for heart failure risk prediction
  doi: 10.1109/TBDATA.2025.3536922
– volume: 44
  start-page: ehad655–2380
  year: 2023
  ident: B22
  article-title: Population prevalence of ECG abnormalities and risk of incident CVD outcomes: 5-year follow-up of 25,000 Chinese adults
  publication-title: Eur Heart J
  doi: 10.1093/eurheartj/ehad655.2380
– ident: B9
  article-title: An approach for ECG classification based on wavelet feature extraction and decision tree
  doi: 10.1109/WCSP.2010.5633782
– ident: B11
  article-title: Using the caremap with health incidents statistics for generating the realistic synthetic electronic healthcare record
  doi: 10.1109/ICHI.2016.83
– ident: B18
  article-title: Automated torso contour extraction from clinical cardiac MR slices for 3D torso reconstruction
  doi: 10.1109/EMBC48229.2022.9871643
– ident: B25
  article-title: A wide and deep transformer neural network for 12-lead ECG classification
  doi: 10.22489/CinC.2020.107
– volume: 3
  start-page: 143
  year: 1984
  ident: B30
  article-title: Regression modelling strategies for improved prognostic prediction
  publication-title: Stat Med
  doi: 10.1002/sim.4780030207
– volume: 9
  start-page: 6734
  year: 2019
  ident: B14
  article-title: Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network
  publication-title: Sci Rep
  doi: 10.1038/s41598-019-42516-z
– volume: 10
  start-page: 458916
  year: 2019
  ident: B15
  article-title: MRI-based computational torso/biventricular multiscale models to investigate the impact of anatomical variability on the ECG QRS complex
  publication-title: Front Physiol
  doi: 10.3389/fphys.2019.01103
– volume: 8
  start-page: 229
  year: 1887
  ident: B1
  article-title: A demonstration on man of electromotive changes accompanying the heart’s beat
  publication-title: J Physiol (Lond)
  doi: 10.1113/jphysiol.1887.sp000257
– volume: 52
  start-page: 1891
  year: 2012
  ident: B2
  article-title: Computerized extraction of electrocardiograms from continuous 12-lead holter recordings reduces measurement variability in a thorough QT study
  publication-title: J Clin Pharmacol
  doi: 10.1177/0091270011430505
– volume: 13
  start-page: 512
  year: 2008
  ident: B6
  article-title: Heartbeat time series classification with support vector machines
  publication-title: IEEE Trans Inf Technol Biomed
  doi: 10.1109/TITB.2008.2003323
– ident: B17
  article-title: Generation of 12-lead electrocardiogram with subject-specific, image-derived characteristics using a conditional variational autoencoder
  doi: 10.1109/ISBI52829.2022.9761431
SSID ssj0002512205
Score 2.2889807
Snippet 12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting...
Background12-lead electrocardiograms (ECGs) are a cornerstone for diagnosing and monitoring cardiovascular diseases (CVDs). They play a key role in detecting...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
StartPage 1558589
SubjectTerms cardiac MRI
cardiovascular disease
cardiovascular risk prediction
Digital Health
ECG electrodes
ECG generation
variational autoencoder
Title Deep conditional generative model for personalization of 12-lead electrocardiograms and cardiovascular risk prediction
URI https://www.ncbi.nlm.nih.gov/pubmed/40309320
https://www.proquest.com/docview/3198317536
https://pubmed.ncbi.nlm.nih.gov/PMC12040958
https://doaj.org/article/2a10921b18e7497d98cab78e66c9b407
Volume 7
WOSCitedRecordID wos001478746300001&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: Directory of Open Access Journals
  customDbUrl:
  eissn: 2673-253X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002512205
  issn: 2673-253X
  databaseCode: DOA
  dateStart: 20200101
  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: 2673-253X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002512205
  issn: 2673-253X
  databaseCode: M~E
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Jb9QwFLZKVSEuCMoWlspI3FCo7diJfWRp1UsrDiDNzfLyXEZCmdHMtEd-O352pppBSFy45BBHsfW-l7fkbYS86yIHn1dapkG1EhMItUqyBZc6FkUAAa4MmxiurvRsZr7ujPrCnLDaHrgS7lQ4zozgnmsYpBmi0cH5QUPfB-NlrSPPVs-OM4UyGLW2YKpWyWQvzJymeL3B4INQH7IK1Qrnuu9ootKw_29W5p_Jkjva5_wReTiZjfRjPe5jcgDjMbl_OQXGn5DbLwBLmn3bOK8_9-h16SeNwoyWaTc0W6d0uTW9a_ElXSTKRfsz40yneTih5KdiytaaujHSsJevSjETnS5XuC--4Cn5fn727fNFO41UaIMUYtO6yPpolPRKa6yu61IHKdNEdBE4c4yBYIPpve6V65ORMna9H3AOjM-2X9bvz8jhuBjhBaGAvpkB5mXqZDLeZH0IAYaQeIiBh4a835LXLmvnDJs9DgTDFjAsgmEnMBryCRG4exK7XpcbmRfsxAv2X7zQkLdb_Gz-SjD04UZY3KxtFjQaLaWub8jziufdVrJEgwVriN5Deu8s-yvj_EfpxM1FloFG6Zf_4_SvyAOkCIaqeP-aHG5WN_CGHIXbzXy9OiH3hpk-KVyer5e_zn4DPBsEIw
linkProvider Directory of Open Access Journals
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+conditional+generative+model+for+personalization+of+12-lead+electrocardiograms+and+cardiovascular+risk+prediction&rft.jtitle=Frontiers+in+digital+health&rft.au=Yuling+Sang&rft.au=Yuling+Sang&rft.au=Abhirup+Banerjee&rft.au=Abhirup+Banerjee&rft.date=2025-04-16&rft.pub=Frontiers+Media+S.A&rft.eissn=2673-253X&rft.volume=7&rft_id=info:doi/10.3389%2Ffdgth.2025.1558589&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_2a10921b18e7497d98cab78e66c9b407
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2673-253X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2673-253X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2673-253X&client=summon