MildInt: Deep Learning-Based Multimodal Longitudinal Data Integration Framework

As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary knowledge from multiple domains of sources. Recently, a deep learning approach has shown promising results in a variety of research areas. H...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in genetics Jg. 10; S. 617
Hauptverfasser: Lee, Garam, Kang, Byungkon, Nho, Kwangsik, Sohn, Kyung-Ah, Kim, Dokyoon
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland Frontiers Media S.A 28.06.2019
Schlagworte:
ISSN:1664-8021, 1664-8021
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary knowledge from multiple domains of sources. Recently, a deep learning approach has shown promising results in a variety of research areas. However, applying the deep learning approach requires expertise for constructing a deep architecture that can take multimodal longitudinal data. Thus, in this paper, a deep learning-based python package for data integration is developed. The python package deep learning-based ult modal ongitudinal ata egration framework (MildInt) provides the preconstructed deep learning architecture for a classification task. MildInt contains two learning phases: learning feature representation from each modality of data and training a classifier for the final decision. Adopting deep architecture in the first phase leads to learning more task-relevant feature representation than a linear model. In the second phase, linear regression classifier is used for detecting and investigating biomarkers from multimodal data. Thus, by combining the linear model and the deep learning model, higher accuracy and better interpretability can be achieved. We validated the performance of our package using simulation data and real data. For the real data, as a pilot study, we used clinical and multimodal neuroimaging datasets in Alzheimer's disease to predict the disease progression. MildInt is capable of integrating multiple forms of numerical data including time series and non-time series data for extracting complementary features from the multimodal dataset.
AbstractList As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary knowledge from multiple domains of sources. Recently, a deep learning approach has shown promising results in a variety of research areas. However, applying the deep learning approach requires expertise for constructing a deep architecture that can take multimodal longitudinal data. Thus, in this paper, a deep learning-based python package for data integration is developed. The python package deep learning-based multimodal longitudinal data integration framework (MildInt) provides the preconstructed deep learning architecture for a classification task. MildInt contains two learning phases: learning feature representation from each modality of data and training a classifier for the final decision. Adopting deep architecture in the first phase leads to learning more task-relevant feature representation than a linear model. In the second phase, linear regression classifier is used for detecting and investigating biomarkers from multimodal data. Thus, by combining the linear model and the deep learning model, higher accuracy and better interpretability can be achieved. We validated the performance of our package using simulation data and real data. For the real data, as a pilot study, we used clinical and multimodal neuroimaging datasets in Alzheimer’s disease to predict the disease progression. MildInt is capable of integrating multiple forms of numerical data including time series and non-time series data for extracting complementary features from the multimodal dataset.
As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary knowledge from multiple domains of sources. Recently, a deep learning approach has shown promising results in a variety of research areas. However, applying the deep learning approach requires expertise for constructing a deep architecture that can take multimodal longitudinal data. Thus, in this paper, a deep learning-based python package for data integration is developed. The python package deep learning-based multimodal longitudinal data integration framework (MildInt) provides the preconstructed deep learning architecture for a classification task. MildInt contains two learning phases: learning feature representation from each modality of data and training a classifier for the final decision. Adopting deep architecture in the first phase leads to learning more task-relevant feature representation than a linear model. In the second phase, linear regression classifier is used for detecting and investigating biomarkers from multimodal data. Thus, by combining the linear model and the deep learning model, higher accuracy and better interpretability can be achieved. We validated the performance of our package using simulation data and real data. For the real data, as a pilot study, we used clinical and multimodal neuroimaging datasets in Alzheimer's disease to predict the disease progression. MildInt is capable of integrating multiple forms of numerical data including time series and non-time series data for extracting complementary features from the multimodal dataset.As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary knowledge from multiple domains of sources. Recently, a deep learning approach has shown promising results in a variety of research areas. However, applying the deep learning approach requires expertise for constructing a deep architecture that can take multimodal longitudinal data. Thus, in this paper, a deep learning-based python package for data integration is developed. The python package deep learning-based multimodal longitudinal data integration framework (MildInt) provides the preconstructed deep learning architecture for a classification task. MildInt contains two learning phases: learning feature representation from each modality of data and training a classifier for the final decision. Adopting deep architecture in the first phase leads to learning more task-relevant feature representation than a linear model. In the second phase, linear regression classifier is used for detecting and investigating biomarkers from multimodal data. Thus, by combining the linear model and the deep learning model, higher accuracy and better interpretability can be achieved. We validated the performance of our package using simulation data and real data. For the real data, as a pilot study, we used clinical and multimodal neuroimaging datasets in Alzheimer's disease to predict the disease progression. MildInt is capable of integrating multiple forms of numerical data including time series and non-time series data for extracting complementary features from the multimodal dataset.
As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary knowledge from multiple domains of sources. Recently, a deep learning approach has shown promising results in a variety of research areas. However, applying the deep learning approach requires expertise for constructing a deep architecture that can take multimodal longitudinal data. Thus, in this paper, a deep learning-based python package for data integration is developed. The python package deep learning-based ult modal ongitudinal ata egration framework (MildInt) provides the preconstructed deep learning architecture for a classification task. MildInt contains two learning phases: learning feature representation from each modality of data and training a classifier for the final decision. Adopting deep architecture in the first phase leads to learning more task-relevant feature representation than a linear model. In the second phase, linear regression classifier is used for detecting and investigating biomarkers from multimodal data. Thus, by combining the linear model and the deep learning model, higher accuracy and better interpretability can be achieved. We validated the performance of our package using simulation data and real data. For the real data, as a pilot study, we used clinical and multimodal neuroimaging datasets in Alzheimer's disease to predict the disease progression. MildInt is capable of integrating multiple forms of numerical data including time series and non-time series data for extracting complementary features from the multimodal dataset.
Author Nho, Kwangsik
Lee, Garam
Kang, Byungkon
Kim, Dokyoon
Sohn, Kyung-Ah
AuthorAffiliation 1 Department of Software and Computer Engineering, Ajou University , Suwon , South Korea
3 Center for Computational Biology and Bioinformatics, Indiana University School of Medicine , Indianapolis, IN , United States
4 Center for Neuroimaging, Department of Radiology and Imaging Sciences, Indiana University School of Medicine , Indianapolis, IN , United States
5 Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA , United States
6 Institute for Biomedical Informatics, University of Pennsylvania , Philadelphia, PA , United States
2 Biomedical & Translational Informatics Institute, Geisinger , Danville, PA , United States
AuthorAffiliation_xml – name: 1 Department of Software and Computer Engineering, Ajou University , Suwon , South Korea
– name: 6 Institute for Biomedical Informatics, University of Pennsylvania , Philadelphia, PA , United States
– name: 5 Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania , Philadelphia, PA , United States
– name: 4 Center for Neuroimaging, Department of Radiology and Imaging Sciences, Indiana University School of Medicine , Indianapolis, IN , United States
– name: 2 Biomedical & Translational Informatics Institute, Geisinger , Danville, PA , United States
– name: 3 Center for Computational Biology and Bioinformatics, Indiana University School of Medicine , Indianapolis, IN , United States
Author_xml – sequence: 1
  givenname: Garam
  surname: Lee
  fullname: Lee, Garam
– sequence: 2
  givenname: Byungkon
  surname: Kang
  fullname: Kang, Byungkon
– sequence: 3
  givenname: Kwangsik
  surname: Nho
  fullname: Nho, Kwangsik
– sequence: 4
  givenname: Kyung-Ah
  surname: Sohn
  fullname: Sohn, Kyung-Ah
– sequence: 5
  givenname: Dokyoon
  surname: Kim
  fullname: Kim, Dokyoon
BackLink https://www.ncbi.nlm.nih.gov/pubmed/31316553$$D View this record in MEDLINE/PubMed
BookMark eNp1kUtvEzEUhS1UREvpnhWaJZsJfsdmgQR9QKRU3cDaumN7BpeJHTweEP--TtKiFglvrn19z3csn5foKKboEXpN8IIxpd_1g49-QTHRC4wlWT5DJ0RK3ipMydGj_TE6m6ZbXBfXjDH-Ah0zwogUgp2gm-swulUs75sL77fN2kOOIQ7tJ5i8a67nsYRNcjA26xSHUGYXYj1cQIGmqvyQoYQUm6sMG_875R-v0PMexsmf3ddT9O3q8uv5l3Z983l1_nHdWi5paZeWKtVzwNYR1QmHOaW8W-qed46LpZZSKcqt7a0i2uJOEMqgx0oyQUhnFTtFqwPXJbg12xw2kP-YBMHsGykPBnIJdvQGay0Vc9IBE9URQ6epla7XANWfisr6cGBt527jnfWxZBifQJ_exPDdDOmXkZIQgVkFvL0H5PRz9lMxmzBZP44QfZonQ6nQmmiudu9-89jrr8lDInVAHgZsTtOUfW9sKPtPrtZhNASbXfpmn77ZpW_26Vch_kf4wP6v5A4sC7KV
CitedBy_id crossref_primary_10_1016_j_cmpb_2022_106818
crossref_primary_10_1109_JBHI_2023_3268729
crossref_primary_10_3390_app13053352
crossref_primary_10_1073_pnas_2104559118
crossref_primary_10_1016_j_inffus_2022_12_010
crossref_primary_10_1038_s41568_021_00408_3
crossref_primary_10_1016_j_eswa_2021_115126
crossref_primary_10_1002_aisy_202200365
crossref_primary_10_1021_acs_jcim_4c00003
crossref_primary_10_3389_fcvm_2021_765693
crossref_primary_10_3390_neurolint16060098
crossref_primary_10_3389_fgene_2021_607471
crossref_primary_10_1093_bib_bbae339
crossref_primary_10_1186_s12859_021_04376_1
crossref_primary_10_1016_j_eswa_2023_120761
crossref_primary_10_1016_j_asoc_2022_109631
crossref_primary_10_1056_AIoa2400703
crossref_primary_10_1007_s10462_023_10561_w
crossref_primary_10_1007_s11571_023_09993_5
crossref_primary_10_1080_17460441_2023_2273839
crossref_primary_10_1186_s13040_024_00391_z
crossref_primary_10_1080_07853890_2025_2551819
crossref_primary_10_3389_fnins_2021_744190
crossref_primary_10_1016_j_procs_2021_03_074
crossref_primary_10_1016_j_bspc_2023_105773
crossref_primary_10_1016_j_cmpb_2022_107079
crossref_primary_10_3390_foods14101805
crossref_primary_10_1038_s41467_021_22188_y
crossref_primary_10_1016_j_eswa_2022_117006
crossref_primary_10_1016_j_bspc_2023_105669
crossref_primary_10_1111_apha_13951
crossref_primary_10_1016_j_media_2021_102189
Cites_doi 10.1093/bib/bbk007
10.1038/nature14539
10.1109/I2C2.2017.8321780
10.1109/TBME.2015.2404809
10.1155/2017/5485080
10.1038/s41598-018-22871-z
10.1016/j.neuroimage.2011.09.069
10.1109/72.279181
10.1038/srep39880
10.1016/j.nicl.2013.05.004
10.1158/1078-0432.CCR-17-0853
10.1093/jamia/ocw112
10.1038/s41598-018-37769-z
10.1101/114892
10.1371/journal.pone.0033182
ContentType Journal Article
Copyright Copyright © 2019 Lee, Kang, Nho, Sohn and Kim 2019 Lee, Kang, Nho, Sohn and Kim
Copyright_xml – notice: Copyright © 2019 Lee, Kang, Nho, Sohn and Kim 2019 Lee, Kang, Nho, Sohn and Kim
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.3389/fgene.2019.00617
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList

MEDLINE - Academic
PubMed
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals (ODIN)
  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 Biology
EISSN 1664-8021
ExternalDocumentID oai_doaj_org_article_099683d6da354a00ab92c6df9aaa0c25
PMC6611503
31316553
10_3389_fgene_2019_00617
Genre Journal Article
GrantInformation_xml – fundername: NIA NIH HHS
  grantid: R03 AG054936
GroupedDBID 53G
5VS
9T4
AAFWJ
AAKDD
AAYXX
ACGFS
ADBBV
ADRAZ
AFPKN
ALMA_UNASSIGNED_HOLDINGS
AOIJS
BAWUL
BCNDV
CITATION
DIK
EMOBN
GROUPED_DOAJ
GX1
HYE
KQ8
M48
M~E
OK1
PGMZT
RNS
RPM
ACXDI
IPNFZ
NPM
RIG
7X8
5PM
ID FETCH-LOGICAL-c462t-7c288f4a0cd18b5d04224b79f4bd4579668824ccfc819c0b5123af0863511bc83
IEDL.DBID DOA
ISICitedReferencesCount 41
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000473203000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1664-8021
IngestDate Fri Oct 03 12:50:14 EDT 2025
Tue Sep 30 16:20:37 EDT 2025
Thu Oct 02 06:07:21 EDT 2025
Mon Jul 21 05:58:27 EDT 2025
Sat Nov 29 01:51:36 EST 2025
Tue Nov 18 21:44:53 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords gated recurrent unit
python package
Alzheimer’s disease
data integration
multimodal deep learning
Language English
License 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-c462t-7c288f4a0cd18b5d04224b79f4bd4579668824ccfc819c0b5123af0863511bc83
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
This article was submitted to Bioinformatics and Computational Biology, a section of the journal Frontiers in Genetics
Edited by: Tao Zeng, Shanghai Institutes for Biological Sciences (CAS), China
Reviewed by: Min Chen, Hunan Institute of Technology, China; Liansheng Wang, Xiamen University, China
OpenAccessLink https://doaj.org/article/099683d6da354a00ab92c6df9aaa0c25
PMID 31316553
PQID 2259919488
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_099683d6da354a00ab92c6df9aaa0c25
pubmedcentral_primary_oai_pubmedcentral_nih_gov_6611503
proquest_miscellaneous_2259919488
pubmed_primary_31316553
crossref_citationtrail_10_3389_fgene_2019_00617
crossref_primary_10_3389_fgene_2019_00617
PublicationCentury 2000
PublicationDate 2019-06-28
PublicationDateYYYYMMDD 2019-06-28
PublicationDate_xml – month: 06
  year: 2019
  text: 2019-06-28
  day: 28
PublicationDecade 2010
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
PublicationTitle Frontiers in genetics
PublicationTitleAlternate Front Genet
PublicationYear 2019
Publisher Frontiers Media S.A
Publisher_xml – name: Frontiers Media S.A
References Chaudhary (B3) 2018; 24
Choi (B5) 2017; 24
Zhang (B15) 2012; 59
Lama (B8) 2017; 2017
Zhang (B16) 2012; 7
Chaudhary (B2) 2017; 853
Lee (B11) 2019; 9
Cheng (B4) 2015; 62
Deng (B6) 2013
LeCun (B10) 2015; 521
Huang (B7) 2017; 7
Bengio (B1) 1994; 5
Sandeep (B13) 2017; 1
Young (B14) 2013; 2
Lu (B12) 2018; 8
Larranaga (B9) 2006; 7
References_xml – volume: 7
  start-page: 86
  year: 2006
  ident: B9
  article-title: Machine learning in bioinformatics
  publication-title: Briefings Bioinf.
  doi: 10.1093/bib/bbk007
– volume: 521
  start-page: 436
  year: 2015
  ident: B10
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 1
  start-page: 35
  year: 2017
  ident: B13
  article-title: Feature extraction of MRI brain images for the early detection of alzheimer’s disease
  publication-title: Bioprocess Eng.
  doi: 10.1109/I2C2.2017.8321780
– volume: 62
  start-page: 1805
  year: 2015
  ident: B4
  article-title: Domain Transfer Learning for MCI Conversion Prediction
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2015.2404809
– volume: 2017
  start-page: 11
  year: 2017
  ident: B8
  article-title: Diagnosis of Alzheimer’s disease based on structural MRI images using a regularized extreme learning machine and PCA features
  publication-title: J. Healthcare Eng.
  doi: 10.1155/2017/5485080
– volume: 8
  start-page: 5697
  year: 2018
  ident: B12
  article-title: Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer’s disease using structural mr and fdg-pet images
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-018-22871-z
– volume: 59
  start-page: 895
  year: 2012
  ident: B15
  article-title: Initiative AsDN: multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer’s disease
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2011.09.069
– volume: 5
  start-page: 157
  year: 1994
  ident: B1
  article-title: Learning long-term dependencies with gradient descent is difficult
  publication-title: IEEE Trans. Neural Networks
  doi: 10.1109/72.279181
– volume: 7
  year: 2017
  ident: B7
  article-title: Longitudinal measurement and hierarchical classification framework for the prediction of Alzheimer’s disease
  publication-title: Sci. Rep.
  doi: 10.1038/srep39880
– volume: 2
  start-page: 735
  year: 2013
  ident: B14
  article-title: Initiative AsDN: accurate multimodal probabilistic prediction of conversion to Alzheimer’s disease in patients with mild cognitive impairment
  publication-title: NeuroImage Clin.
  doi: 10.1016/j.nicl.2013.05.004
– volume: 24
  start-page: 1248
  year: 2018
  ident: B3
  article-title: Deep learning–based multi-omics integration robustly predicts survival in liver cancer
  publication-title: Clin. Can. Res.
  doi: 10.1158/1078-0432.CCR-17-0853
– volume: 24
  start-page: 361
  year: 2017
  ident: B5
  article-title: Using recurrent neural network models for early detection of heart failure onset
  publication-title: J. Am. Med. Inf. Assoc.
  doi: 10.1093/jamia/ocw112
– volume: 9
  start-page: 1952
  year: 2019
  ident: B11
  article-title: Predicting Alzheimer's disease progression using multi-modal deep learning approach
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-018-37769-z
– start-page: 8599
  volume-title: IEEE International Conference on: 2013
  year: 2013
  ident: B6
  article-title: New types of deep neural network learning for speech recognition and related applications: An overview
– volume: 853
  start-page: 1246
  year: 2017
  ident: B2
  article-title: Deep learning based multi-omics integration robustly predicts survival in liver cancer
  publication-title: Clin. Can. Res.
  doi: 10.1101/114892
– volume: 7
  year: 2012
  ident: B16
  article-title: Initiative AsDN: predicting future clinical changes of MCI patients using longitudinal and multimodal biomarkers
  publication-title: PloS One
  doi: 10.1371/journal.pone.0033182
SSID ssj0000493334
Score 2.4212053
Snippet As large amounts of heterogeneous biomedical data become available, numerous methods for integrating such datasets have been developed to extract complementary...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 617
SubjectTerms Alzheimer’s disease
data integration
gated recurrent unit
Genetics
multimodal deep learning
python package
Title MildInt: Deep Learning-Based Multimodal Longitudinal Data Integration Framework
URI https://www.ncbi.nlm.nih.gov/pubmed/31316553
https://www.proquest.com/docview/2259919488
https://pubmed.ncbi.nlm.nih.gov/PMC6611503
https://doaj.org/article/099683d6da354a00ab92c6df9aaa0c25
Volume 10
WOSCitedRecordID wos000473203000001&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 (ODIN)
  customDbUrl:
  eissn: 1664-8021
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000493334
  issn: 1664-8021
  databaseCode: DOA
  dateStart: 20100101
  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: 1664-8021
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000493334
  issn: 1664-8021
  databaseCode: M~E
  dateStart: 20100101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwEB4V1EpcEPRBl5dSiUsP0Sax49jcoLAqEo8eWmlvlp-wFWQRZJG48NsZO9ntblXBpZccEidxvpl4PsvjbwD2LFOEcqJS4xlNqcpJqjwxqfA4XHJFSqajpU-r83M-HIofc6W-Qk5YKw_cAtdHBsM4sczifVRlmdKiMMx6oZTKTBHVS7NKzE2mfre8lxBC23VJnIWJvkd7BFnMPOhTslif7E8cinL9_-KYf6dKzsWewRqsdqQxOWg7uw5vXP0e3rVlJB8_wMXZ6Nqe1M1-cuTcbdJJpl6mhxihbBK32N6MLT7gdByqE01sqISVHKlGJSedWgRaJxlM87Q-wq_B8c9v39OuUEJqKCuatDIF5x7RMTbnurRB14vqSniqLQ2bTRnyaGqMNxj_TaYxyBPlcTITVhG14eQTLNfj2n2GhIq8KByvHAJFy7LUtNAlrbyzudeKkh70p7BJ06mIh2IW1xJnEwFoGYGWAWgZge7B19kdt62CxgttD4MlZu2C9nU8gR4hO4-Qr3lED75M7SjxXwkLIKp248m9xLEL6bDAMasHG61dZ68iOclZWeIHVgsWX-jL4pV6dBX1uJHiIK0mm_-j81uwEuAIyWgF34bl5m7iduCteWhG93e7sFQN-W50dTyePR0_A2amA_s
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=MildInt%3A+Deep+Learning-Based+Multimodal+Longitudinal+Data+Integration+Framework&rft.jtitle=Frontiers+in+genetics&rft.au=Lee%2C+Garam&rft.au=Kang%2C+Byungkon&rft.au=Nho%2C+Kwangsik&rft.au=Sohn%2C+Kyung-Ah&rft.date=2019-06-28&rft.issn=1664-8021&rft.eissn=1664-8021&rft.volume=10&rft.spage=617&rft_id=info:doi/10.3389%2Ffgene.2019.00617&rft_id=info%3Apmid%2F31316553&rft.externalDocID=31316553
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1664-8021&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1664-8021&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1664-8021&client=summon