Learning from small medical data—robust semi-supervised cancer prognosis classifier with Bayesian variational autoencoder

Abstract Motivation Cancer is one of the world’s leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data types. Numerous challenges, such as censorship, high dimensionality and small sample size, prevent researchers from usin...

Full description

Saved in:
Bibliographic Details
Published in:Bioinformatics advances Vol. 3; no. 1; p. vbac100
Main Authors: Hsu, Te-Cheng, Lin, Che
Format: Journal Article
Language:English
Published: England Oxford University Press 2023
Subjects:
Bayesian analysis
Bioinformatics
Breast cancer
Deep learning
Mathematical models
Medical prognosis
Neural networks
Non-small cell lung carcinoma
Original Paper
Precision medicine
Prognosis
Small cell lung carcinoma
ISSN:2635-0041, 2635-0041
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Abstract Motivation Cancer is one of the world’s leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data types. Numerous challenges, such as censorship, high dimensionality and small sample size, prevent researchers from using deep learning models for precise prediction. Results We propose a robust Semi-supervised Cancer prognosis classifier with bAyesian variational autoeNcoder (SCAN) as a structured machine-learning framework for cancer prognosis prediction. SCAN incorporates semi-supervised learning for predicting 5-year disease-specific survival and overall survival in breast and non-small cell lung cancer (NSCLC) patients, respectively. SCAN achieved significantly better AUROC scores than all existing benchmarks (81.73% for breast cancer; 80.46% for NSCLC), including our previously proposed bimodal neural network classifiers (77.71% for breast cancer; 78.67% for NSCLC). Independent validation results showed that SCAN still achieved better AUROC scores (74.74% for breast; 72.80% for NSCLC) than the bimodal neural network classifiers (64.13% for breast; 67.07% for NSCLC). SCAN is general and can potentially be trained on more patient data. This paves the foundation for personalized medicine for early cancer risk screening. Availability and implementation The source codes reproducing the main results are available on GitHub: https://gitfront.io/r/user-4316673/36e8714573f3fbfa0b24690af5d1a9d5ca159cf4/scan/. Supplementary information Supplementary data are available at Bioinformatics Advances online.
AbstractList Cancer is one of the world's leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data types. Numerous challenges, such as censorship, high dimensionality and small sample size, prevent researchers from using deep learning models for precise prediction. We propose a robust Semi-supervised Cancer prognosis classifier with bAyesian variational autoeNcoder ( ) as a structured machine-learning framework for cancer prognosis prediction. incorporates semi-supervised learning for predicting 5-year disease-specific survival and overall survival in breast and non-small cell lung cancer (NSCLC) patients, respectively. achieved significantly better AUROC scores than all existing benchmarks (81.73% for breast cancer; 80.46% for NSCLC), including our previously proposed bimodal neural network classifiers (77.71% for breast cancer; 78.67% for NSCLC). Independent validation results showed that still achieved better AUROC scores (74.74% for breast; 72.80% for NSCLC) than the bimodal neural network classifiers (64.13% for breast; 67.07% for NSCLC). is general and can potentially be trained on more patient data. This paves the foundation for personalized medicine for early cancer risk screening. The source codes reproducing the main results are available on GitHub: https://gitfront.io/r/user-4316673/36e8714573f3fbfa0b24690af5d1a9d5ca159cf4/scan/. Supplementary data are available at online.
Cancer is one of the world's leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data types. Numerous challenges, such as censorship, high dimensionality and small sample size, prevent researchers from using deep learning models for precise prediction.MotivationCancer is one of the world's leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data types. Numerous challenges, such as censorship, high dimensionality and small sample size, prevent researchers from using deep learning models for precise prediction.We propose a robust Semi-supervised Cancer prognosis classifier with bAyesian variational autoeNcoder (SCAN) as a structured machine-learning framework for cancer prognosis prediction. SCAN incorporates semi-supervised learning for predicting 5-year disease-specific survival and overall survival in breast and non-small cell lung cancer (NSCLC) patients, respectively. SCAN achieved significantly better AUROC scores than all existing benchmarks (81.73% for breast cancer; 80.46% for NSCLC), including our previously proposed bimodal neural network classifiers (77.71% for breast cancer; 78.67% for NSCLC). Independent validation results showed that SCAN still achieved better AUROC scores (74.74% for breast; 72.80% for NSCLC) than the bimodal neural network classifiers (64.13% for breast; 67.07% for NSCLC). SCAN is general and can potentially be trained on more patient data. This paves the foundation for personalized medicine for early cancer risk screening.ResultsWe propose a robust Semi-supervised Cancer prognosis classifier with bAyesian variational autoeNcoder (SCAN) as a structured machine-learning framework for cancer prognosis prediction. SCAN incorporates semi-supervised learning for predicting 5-year disease-specific survival and overall survival in breast and non-small cell lung cancer (NSCLC) patients, respectively. SCAN achieved significantly better AUROC scores than all existing benchmarks (81.73% for breast cancer; 80.46% for NSCLC), including our previously proposed bimodal neural network classifiers (77.71% for breast cancer; 78.67% for NSCLC). Independent validation results showed that SCAN still achieved better AUROC scores (74.74% for breast; 72.80% for NSCLC) than the bimodal neural network classifiers (64.13% for breast; 67.07% for NSCLC). SCAN is general and can potentially be trained on more patient data. This paves the foundation for personalized medicine for early cancer risk screening.The source codes reproducing the main results are available on GitHub: https://gitfront.io/r/user-4316673/36e8714573f3fbfa0b24690af5d1a9d5ca159cf4/scan/.Availability and implementationThe source codes reproducing the main results are available on GitHub: https://gitfront.io/r/user-4316673/36e8714573f3fbfa0b24690af5d1a9d5ca159cf4/scan/.Supplementary data are available at Bioinformatics Advances online.Supplementary informationSupplementary data are available at Bioinformatics Advances online.
Abstract Motivation Cancer is one of the world’s leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data types. Numerous challenges, such as censorship, high dimensionality and small sample size, prevent researchers from using deep learning models for precise prediction. Results We propose a robust Semi-supervised Cancer prognosis classifier with bAyesian variational autoeNcoder (SCAN) as a structured machine-learning framework for cancer prognosis prediction. SCAN incorporates semi-supervised learning for predicting 5-year disease-specific survival and overall survival in breast and non-small cell lung cancer (NSCLC) patients, respectively. SCAN achieved significantly better AUROC scores than all existing benchmarks (81.73% for breast cancer; 80.46% for NSCLC), including our previously proposed bimodal neural network classifiers (77.71% for breast cancer; 78.67% for NSCLC). Independent validation results showed that SCAN still achieved better AUROC scores (74.74% for breast; 72.80% for NSCLC) than the bimodal neural network classifiers (64.13% for breast; 67.07% for NSCLC). SCAN is general and can potentially be trained on more patient data. This paves the foundation for personalized medicine for early cancer risk screening. Availability and implementation The source codes reproducing the main results are available on GitHub: https://gitfront.io/r/user-4316673/36e8714573f3fbfa0b24690af5d1a9d5ca159cf4/scan/. Supplementary information Supplementary data are available at Bioinformatics Advances online.
Motivation Cancer is one of the world’s leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data types. Numerous challenges, such as censorship, high dimensionality and small sample size, prevent researchers from using deep learning models for precise prediction. Results We propose a robust Semi-supervised Cancer prognosis classifier with bAyesian variational autoeNcoder (SCAN) as a structured machine-learning framework for cancer prognosis prediction. SCAN incorporates semi-supervised learning for predicting 5-year disease-specific survival and overall survival in breast and non-small cell lung cancer (NSCLC) patients, respectively. SCAN achieved significantly better AUROC scores than all existing benchmarks (81.73% for breast cancer; 80.46% for NSCLC), including our previously proposed bimodal neural network classifiers (77.71% for breast cancer; 78.67% for NSCLC). Independent validation results showed that SCAN still achieved better AUROC scores (74.74% for breast; 72.80% for NSCLC) than the bimodal neural network classifiers (64.13% for breast; 67.07% for NSCLC). SCAN is general and can potentially be trained on more patient data. This paves the foundation for personalized medicine for early cancer risk screening. Availability and implementation The source codes reproducing the main results are available on GitHub: https://gitfront.io/r/user-4316673/36e8714573f3fbfa0b24690af5d1a9d5ca159cf4/scan/. Supplementary information Supplementary data are available at Bioinformatics Advances online.
Author Hsu, Te-Cheng
Lin, Che
Author_xml – sequence: 1
  givenname: Te-Cheng
  surname: Hsu
  fullname: Hsu, Te-Cheng
– sequence: 2
  givenname: Che
  orcidid: 0000-0002-4986-311X
  surname: Lin
  fullname: Lin, Che
  email: chelin@ntu.edu.tw
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36698767$$D View this record in MEDLINE/PubMed
BookMark eNqFUctu1TAQtVARLaVblsgSG1ik9SNx4g0SVLykK7GBtTV2JreuEjvYSVDFho_gC_kS0t5LVSohVh55zjkzZ85jchBiQEKecnbKmZZn1kdol7PFguOMPSBHQsmqYKzkB3fqQ3KS8yVjTNS14qV8RA6lUrqpVX1Evm8QUvBhS7sUB5oH6Hs6YOsd9LSFCX79-JminfNEMw6-yPOIafEZW-ogOEx0THEbYvaZuh5y9p1fP7_56YK-gSvMHgJdIHmYfAyrJsxTxOBii-kJedhBn_Fk_x6TL-_efj7_UGw-vf94_npTuLISUyF4pZVymnMrsbRNh13DmWhEZVtVlhzAWtdYixU60Tmo9OpTWGWZQw1SymPyaqc7zna15jBMCXozJj9AujIRvPm7E_yF2cbF6EYKrZpV4MVeIMWvM-bJDD477HsIGOdsRK201lV5M-v5PehlnNNqPBvJtZCCl8214LO7G92u8ieXFXC6A7gUc07Y3UI4M9fZm132Zp_9SijvEZyfbm6-OvL9v2kvd7Q4j_8b8Rvwr8lI
CitedBy_id crossref_primary_10_7759_cureus_82310
crossref_primary_10_1007_s10462_024_10768_5
crossref_primary_10_3390_info15050246
crossref_primary_10_3389_fgene_2023_1199087
crossref_primary_10_1002_wcms_70042
Cites_doi 10.1158/0008-5472.CAN-13-2775
10.1016/S0140-6736(16)30958-8
10.1158/1078-0432.CCR-06-3045
10.1172/JCI45014
10.1038/nature10983
10.1158/1078-0432.CCR-06-1109
10.3390/ht8010004
10.1023/A:1010933404324
10.3322/caac.21551
10.1007/s11704-020-0025-x
10.1016/j.patrec.2005.10.010
10.1016/S0304-3800(02)00064-9
10.1002/ijc.29210
10.1093/swr/30.1.19
10.3390/fi4030621
10.1038/sj.bjc.6603494
10.1002/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4
10.1145/1961189.1961199
10.1007/978-3-030-53352-6_8
10.1109/TCBB.2018.2806438
10.1186/bcr1639
10.1007/s11634-017-0285-y
10.2196/medinform.8960
10.4097/kjae.2013.64.5.402
10.1016/j.metabol.2015.10.007
10.1200/JCO.2007.12.0352
10.1038/bjc.2014.492
10.1038/ncomms11479
10.1093/bib/bbu003
10.1038/s41598-020-61588-w
10.1038/s41598-018-24271-9
10.1093/neuonc/noaa028
10.1371/journal.pone.0118432
10.1109/JBHI.2017.2767063
10.1038/s41598-021-92864-y
10.1109/JBHI.2016.2636665
10.1038/35021093
ContentType Journal Article
Copyright The Author(s) 2023. Published by Oxford University Press. 2023
The Author(s) 2023. Published by Oxford University Press.
The Author(s) 2023. Published by Oxford University Press. 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) 2023. Published by Oxford University Press. 2023
– notice: The Author(s) 2023. Published by Oxford University Press.
– notice: The Author(s) 2023. Published by Oxford University Press. 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 TOX
AAYXX
CITATION
NPM
8FE
8FH
ABUWG
AFKRA
AZQEC
BBNVY
BENPR
BHPHI
CCPQU
DWQXO
GNUQQ
HCIFZ
LK8
M7P
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
7X8
5PM
DOI 10.1093/bioadv/vbac100
DatabaseName Oxford Journals Open Access Collection
CrossRef
PubMed
ProQuest SciTech Collection
ProQuest Natural Science Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
Natural Science Collection
ProQuest One
ProQuest Central Korea
ProQuest Central Student
SciTech Premium Collection
ProQuest Biological Science Collection
Biological Science Database
ProQuest One Academic
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
PubMed
Publicly Available Content Database
ProQuest Central Student
ProQuest One Academic Middle East (New)
ProQuest Biological Science Collection
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Natural Science Collection
Biological Science Database
ProQuest SciTech Collection
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest One Academic UKI Edition
Natural Science Collection
ProQuest Central Korea
Biological Science Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic

Publicly Available Content Database
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: TOX
  name: Oxford Journals Open Access Collection
  url: https://academic.oup.com/journals/
  sourceTypes: Publisher
– sequence: 3
  dbid: PIMPY
  name: ProQuest - Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 2635-0041
ExternalDocumentID PMC9832968
36698767
10_1093_bioadv_vbac100
10.1093/bioadv/vbac100
Genre Journal Article
GrantInformation_xml – fundername: ;
– fundername: ;
  grantid: MOST 110-2221-E-002-112-MY3
GroupedDBID 0R~
ABDBF
ABEJV
ABGNP
ABXVV
ALMA_UNASSIGNED_HOLDINGS
AMNDL
GROUPED_DOAJ
M~E
OK1
RPM
TOX
ZCN
AAYXX
AFFHD
AFKRA
BBNVY
BENPR
BHPHI
CCPQU
CITATION
HCIFZ
M7P
PHGZM
PHGZT
PIMPY
PQGLB
NPM
8FE
8FH
ABUWG
AZQEC
DWQXO
GNUQQ
LK8
PKEHL
PQEST
PQQKQ
PQUKI
7X8
5PM
ID FETCH-LOGICAL-c452t-215966c911b3e4b8fef8102825bd6441aabbc8bbe5ec2fca597762b6b0ce9a333
IEDL.DBID M7P
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001124263600026&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2635-0041
IngestDate Tue Nov 04 02:06:34 EST 2025
Sun Nov 09 10:17:59 EST 2025
Fri Sep 19 20:58:16 EDT 2025
Wed Feb 19 02:25:46 EST 2025
Sat Nov 29 03:11:04 EST 2025
Tue Nov 18 21:03:46 EST 2025
Wed Apr 02 07:05:26 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
https://creativecommons.org/licenses/by/4.0
The Author(s) 2023. Published by Oxford University Press.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c452t-215966c911b3e4b8fef8102825bd6441aabbc8bbe5ec2fca597762b6b0ce9a333
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-4986-311X
OpenAccessLink https://www.proquest.com/docview/3192321488?pq-origsite=%requestingapplication%
PMID 36698767
PQID 3192321488
PQPubID 7215308
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_9832968
proquest_miscellaneous_2769995433
proquest_journals_3192321488
pubmed_primary_36698767
crossref_primary_10_1093_bioadv_vbac100
crossref_citationtrail_10_1093_bioadv_vbac100
oup_primary_10_1093_bioadv_vbac100
PublicationCentury 2000
PublicationDate 2023-00-00
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – year: 2023
  text: 2023-00-00
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
– name: Oxford
PublicationTitle Bioinformatics advances
PublicationTitleAlternate Bioinform Adv
PublicationYear 2023
Publisher Oxford University Press
Publisher_xml – name: Oxford University Press
References Dusenberry (2023011113332395000_vbac100-B16) 2020
Lehmann (2023011113332395000_vbac100-B38) 2011; 121
Papadaki (2023011113332395000_vbac100-B41) 2014; 111
Kingma (2023011113332395000_vbac100-B32) 2013
Che (2023011113332395000_vbac100-B10) 2018; 8
Carey (2023011113332395000_vbac100-B8) 2007; 13
Gao (2023011113332395000_vbac100-B21) 2020
Baeuerle (2023011113332395000_vbac100-B2) 2007; 96
AbuKhousa (2023011113332395000_vbac100-B1) 2012; 4
Shickel (2023011113332395000_vbac100-B49) 2018; 22
Ravì (2023011113332395000_vbac100-B46) 2017; 21
Kingma (2023011113332395000_vbac100-B33) 2014
Dent (2023011113332395000_vbac100-B14) 2007; 13
Siegel (2023011113332395000_vbac100-B50) 2019; 69
Olden (2023011113332395000_vbac100-B40) 2002; 154
Barron (2023011113332395000_vbac100-B3) 2016; 65
Beaulieu-Jones (2023011113332395000_vbac100-B4) 2018; 6
Hsu (2023011113332395000_vbac100-B26) 2020
Breiman (2023011113332395000_vbac100-B7) 2001; 45
Jahanian (2023011113332395000_vbac100-B30) 2021
Hastie (2023011113332395000_vbac100-B24) 2020
Sun (2023011113332395000_vbac100-B51) 2019; 16
Wei (2023011113332395000_vbac100-B53) 2022; 16
Zhao (2023011113332395000_vbac100-B57) 2015; 16
Ben Brahim (2023011113332395000_vbac100-B5) 2018; 12
Goldstein (2023011113332395000_vbac100-B22) 2015
Saito (2023011113332395000_vbac100-B47) 2015; 10
Fawcett (2023011113332395000_vbac100-B17) 2006; 27
Kingma (2023011113332395000_vbac100-B34) 2015
Ferlay (2023011113332395000_vbac100-B18) 2015; 136
Lai (2023011113332395000_vbac100-B35) 2020; 10
Zhu (2023011113332395000_vbac100-B58) 2004
Cheng (2023011113332395000_vbac100-B12) 2021; 11
Tomczak (2023011113332395000_vbac100-B52) 2015; 19
Perou (2023011113332395000_vbac100-B43) 2000; 406
Hügle (2023011113332395000_vbac100-B28) 2021
Saunders (2023011113332395000_vbac100-B48) 2006; 30
Powers (2023011113332395000_vbac100-B45) 2020
Wu (2023011113332395000_vbac100-B55) 2020; 2
Hirsch (2023011113332395000_vbac100-B25) 2017; 389
Chen (2023011113332395000_vbac100-B11) 2014; 74
Dunnwald (2023011113332395000_vbac100-B15) 2007; 9
Pignon (2023011113332395000_vbac100-B44) 2008
Wu (2023011113332395000_vbac100-B54) 2019; 8
Bishop (2023011113332395000_vbac100-B6) 2006
Chang (2023011113332395000_vbac100-B9) 2011; 2
Pereira (2023011113332395000_vbac100-B42) 2016; 7
Curtis (2023011113332395000_vbac100-B13) 2012; 486
Hsu (2023011113332395000_vbac100-B27) 2021
Indyk (2023011113332395000_vbac100-B29) 1998
Futoma (2023011113332395000_vbac100-B20) 2017
Münsterberg (2023011113332395000_vbac100-B39) 2020; 22
Zeng (2023011113332395000_vbac100-B56) 2015; 2016
Kang (2023011113332395000_vbac100-B31) 2013; 64
Harrell (2023011113332395000_vbac100-B23) 1996; 15
Lakshminarayanan (2023011113332395000_vbac100-B36) 2017
Fortuin (2023011113332395000_vbac100-B19) 2020
Lau (2023011113332395000_vbac100-B37) 2007; 25
References_xml – start-page: 243
  year: 2017
  ident: 2023011113332395000_vbac100-B20
– volume: 74
  start-page: 2892
  year: 2014
  ident: 2023011113332395000_vbac100-B11
  article-title: A meta-analysis of lung cancer gene expression identifies PTK7 as a survival gene in lung adenocarcinoma
  publication-title: Cancer Res
  doi: 10.1158/0008-5472.CAN-13-2775
– start-page: 1651
  year: 2020
  ident: 2023011113332395000_vbac100-B19
– start-page: 604
  year: 1998
  ident: 2023011113332395000_vbac100-B29
– volume: 389
  start-page: 299
  year: 2017
  ident: 2023011113332395000_vbac100-B25
  article-title: Lung cancer: current therapies and new targeted treatments
  publication-title: Lancet
  doi: 10.1016/S0140-6736(16)30958-8
– volume-title: arXiv preprint
  year: 2021
  ident: 2023011113332395000_vbac100-B30
– volume: 13
  start-page: 4429
  year: 2007
  ident: 2023011113332395000_vbac100-B14
  article-title: Triple-negative breast cancer: clinical features and patterns of recurrence
  publication-title: Clin. Cancer Res
  doi: 10.1158/1078-0432.CCR-06-3045
– volume: 121
  start-page: 2750
  year: 2011
  ident: 2023011113332395000_vbac100-B38
  article-title: Identification of human triple-negative breast cancer subtypes and preclinical models for selection of targeted therapies
  publication-title: J. Clin. Invest
  doi: 10.1172/JCI45014
– volume-title: Adv. Neural Inf. Process. Syst.
  year: 2014
  ident: 2023011113332395000_vbac100-B33
– start-page: 5669
  volume-title: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)
  year: 2020
  ident: 2023011113332395000_vbac100-B26
– volume-title: arXiv preprint arXiv:2010.16061
  year: 2020
  ident: 2023011113332395000_vbac100-B45
– volume: 486
  start-page: 346
  year: 2012
  ident: 2023011113332395000_vbac100-B13
  article-title: The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups
  publication-title: Nature
  doi: 10.1038/nature10983
– year: 2008
  ident: 2023011113332395000_vbac100-B44
– volume: 13
  start-page: 2329
  year: 2007
  ident: 2023011113332395000_vbac100-B8
  article-title: The triple negative paradox: primary tumor chemosensitivity of breast cancer subtypes
  publication-title: Clin. Cancer Res
  doi: 10.1158/1078-0432.CCR-06-1109
– volume: 8
  start-page: 4
  year: 2019
  ident: 2023011113332395000_vbac100-B54
  article-title: A selective review of multi-level omics data integration using variable selection
  publication-title: High Throughput
  doi: 10.3390/ht8010004
– volume: 45
  start-page: 5
  year: 2001
  ident: 2023011113332395000_vbac100-B7
  article-title: Random forests
  publication-title: Mach. Learn
  doi: 10.1023/A:1010933404324
– start-page: 2030
  volume-title: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC)
  year: 2021
  ident: 2023011113332395000_vbac100-B27
– volume: 69
  start-page: 7
  year: 2019
  ident: 2023011113332395000_vbac100-B50
  article-title: Cancer statistics, 2019
  publication-title: CA Cancer J. Clin
  doi: 10.3322/caac.21551
– volume-title: Adv. Neural Inf. Process. Syst.
  year: 2015
  ident: 2023011113332395000_vbac100-B34
– volume: 16
  start-page: 162601
  year: 2022
  ident: 2023011113332395000_vbac100-B53
  article-title: Cancer classification with data augmentation based on generative adversarial networks
  publication-title: Front. Comput. Sci
  doi: 10.1007/s11704-020-0025-x
– volume: 27
  start-page: 861
  year: 2006
  ident: 2023011113332395000_vbac100-B17
  article-title: An introduction to ROC analysis
  publication-title: Pattern Recognit. Lett
  doi: 10.1016/j.patrec.2005.10.010
– volume: 154
  start-page: 135
  year: 2002
  ident: 2023011113332395000_vbac100-B40
  article-title: Illuminating the ‘black box’: a randomization approach for understanding variable contributions in artificial neural networks
  publication-title: Ecol. Model
  doi: 10.1016/S0304-3800(02)00064-9
– volume: 136
  start-page: E359
  year: 2015
  ident: 2023011113332395000_vbac100-B18
  article-title: Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012
  publication-title: Int. J. Cancer
  doi: 10.1002/ijc.29210
– volume: 30
  start-page: 19
  year: 2006
  ident: 2023011113332395000_vbac100-B48
  article-title: Imputing missing data: a comparison of methods for social work researchers
  publication-title: Soc. Work Res
  doi: 10.1093/swr/30.1.19
– volume: 4
  start-page: 621
  year: 2012
  ident: 2023011113332395000_vbac100-B1
  article-title: e-Health cloud: opportunities and challenges
  publication-title: Future Internet
  doi: 10.3390/fi4030621
– volume: 96
  start-page: 417
  year: 2007
  ident: 2023011113332395000_vbac100-B2
  article-title: EpCAM (CD326) finding its role in cancer
  publication-title: Br. J. Cancer
  doi: 10.1038/sj.bjc.6603494
– volume: 15
  start-page: 361
  year: 1996
  ident: 2023011113332395000_vbac100-B23
  article-title: Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors
  publication-title: Stat. Med
  doi: 10.1002/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4
– volume: 2
  start-page: 1
  year: 2011
  ident: 2023011113332395000_vbac100-B9
  article-title: LIBSVM: a library for support vector machines
  publication-title: ACM Trans. Intell. Syst. Technol
  doi: 10.1145/1961189.1961199
– start-page: 1697
  year: 2020
  ident: 2023011113332395000_vbac100-B21
– start-page: 79
  volume-title: Explainable AI in Healthcare and Medicine: Building a Culture of Transparency and Accountability, Studies in Computational Intelligence
  year: 2021
  ident: 2023011113332395000_vbac100-B28
  doi: 10.1007/978-3-030-53352-6_8
– volume: 16
  start-page: 841
  year: 2019
  ident: 2023011113332395000_vbac100-B51
  article-title: A multimodal deep neural network for human breast cancer prognosis prediction by integrating multi-dimensional data
  publication-title: IEEE/ACM Trans. Comput. Biol. Bioinform
  doi: 10.1109/TCBB.2018.2806438
– volume: 9
  start-page: R6
  year: 2007
  ident: 2023011113332395000_vbac100-B15
  article-title: Hormone receptor status, tumor characteristics, and prognosis: a prospective cohort of breast cancer patients
  publication-title: Breast Cancer Res
  doi: 10.1186/bcr1639
– year: 2013
  ident: 2023011113332395000_vbac100-B32
– volume: 12
  start-page: 937
  year: 2018
  ident: 2023011113332395000_vbac100-B5
  article-title: Ensemble feature selection for high dimensional data: a new method and a comparative study
  publication-title: Adv. Data Anal. Classif
  doi: 10.1007/s11634-017-0285-y
– volume: 6
  start-page: e8960
  year: 2018
  ident: 2023011113332395000_vbac100-B4
  article-title: Characterizing and managing missing structured data in electronic health records: data analysis
  publication-title: JMIR Med. Inform
  doi: 10.2196/medinform.8960
– volume: 19
  start-page: A68
  year: 2015
  ident: 2023011113332395000_vbac100-B52
  article-title: The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge
  publication-title: Contemp. Oncol. (Pozn)
– volume: 64
  start-page: 402
  year: 2013
  ident: 2023011113332395000_vbac100-B31
  article-title: The prevention and handling of the missing data
  publication-title: Korean J. Anesthesiol
  doi: 10.4097/kjae.2013.64.5.402
– volume: 65
  start-page: 124
  year: 2016
  ident: 2023011113332395000_vbac100-B3
  article-title: Facilitative glucose transporters: implications for cancer detection, prognosis and treatment
  publication-title: Metabolism
  doi: 10.1016/j.metabol.2015.10.007
– volume-title: Adv. Neural Inf. Process. Syst.
  year: 2017
  ident: 2023011113332395000_vbac100-B36
– volume: 2016
  start-page: e6947623
  year: 2015
  ident: 2023011113332395000_vbac100-B56
  article-title: Loss of CADM1/TSLC1 expression is associated with poor clinical outcome in patients with esophageal squamous cell carcinoma
  publication-title: Gastroenterol. Res. Pract
– volume: 25
  start-page: 5562
  year: 2007
  ident: 2023011113332395000_vbac100-B37
  article-title: Three-gene prognostic classifier for early-stage non small-cell lung cancer
  publication-title: J. Clin. Oncol
  doi: 10.1200/JCO.2007.12.0352
– volume: 111
  start-page: 1757
  year: 2014
  ident: 2023011113332395000_vbac100-B41
  article-title: PKM2 as a biomarker for chemosensitivity to front-line platinum-based chemotherapy in patients with metastatic non-small-cell lung cancer
  publication-title: Br. J. Cancer
  doi: 10.1038/bjc.2014.492
– volume: 7
  start-page: 11479
  year: 2016
  ident: 2023011113332395000_vbac100-B42
  article-title: The somatic mutation profiles of 2,433 breast cancers refine their genomic and transcriptomic landscapes
  publication-title: Nat. Commun
  doi: 10.1038/ncomms11479
– start-page: 204
  year: 2020
  ident: 2023011113332395000_vbac100-B16
– volume: 2
  start-page: 307
  year: 2020
  ident: 2023011113332395000_vbac100-B55
  article-title: Attention-based learning for missing data imputation in HoloClean
  publication-title: Proc. Mach. Learn. Syst
– volume: 16
  start-page: 291
  year: 2015
  ident: 2023011113332395000_vbac100-B57
  article-title: Combining multidimensional genomic measurements for predicting cancer prognosis: observations from TCGA
  publication-title: Brief. Bioinform
  doi: 10.1093/bib/bbu003
– start-page: 426
  volume-title: Technometrics
  year: 2020
  ident: 2023011113332395000_vbac100-B24
– volume: 10
  start-page: 4679
  year: 2020
  ident: 2023011113332395000_vbac100-B35
  article-title: Overall survival prediction of non-small cell lung cancer by integrating microarray and clinical data with deep learning
  publication-title: Sci. Rep
  doi: 10.1038/s41598-020-61588-w
– volume: 8
  start-page: 6085
  year: 2018
  ident: 2023011113332395000_vbac100-B10
  article-title: Recurrent neural networks for multivariate time series with missing values
  publication-title: Sci. Rep
  doi: 10.1038/s41598-018-24271-9
– start-page: 44
  volume-title: J. Comput. Graph.
  year: 2015
  ident: 2023011113332395000_vbac100-B22
– volume: 22
  start-page: 955
  year: 2020
  ident: 2023011113332395000_vbac100-B39
  article-title: ALCAM contributes to brain metastasis formation in non-small-cell lung cancer through interaction with the vascular endothelium
  publication-title: Neuro Oncol
  doi: 10.1093/neuonc/noaa028
– volume: 10
  start-page: e0118432
  year: 2015
  ident: 2023011113332395000_vbac100-B47
  article-title: The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0118432
– volume: 22
  start-page: 1589
  year: 2018
  ident: 2023011113332395000_vbac100-B49
  article-title: Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis
  publication-title: IEEE J. Biomed. Health Inform
  doi: 10.1109/JBHI.2017.2767063
– year: 2006
  ident: 2023011113332395000_vbac100-B6
  publication-title: Pattern Recognition and Machine Learning (Information Science and Statistics)
– volume: 11
  start-page: 14914
  year: 2021
  ident: 2023011113332395000_vbac100-B12
  article-title: Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction
  publication-title: Sci. Rep
  doi: 10.1038/s41598-021-92864-y
– volume: 21
  start-page: 4
  year: 2017
  ident: 2023011113332395000_vbac100-B46
  article-title: Deep learning for health informatics
  publication-title: IEEE J. Biomed. Health Inform
  doi: 10.1109/JBHI.2016.2636665
– start-page: 6
  volume-title: Recall, precision and average precision
  year: 2004
  ident: 2023011113332395000_vbac100-B58
– volume: 406
  start-page: 747
  year: 2000
  ident: 2023011113332395000_vbac100-B43
  article-title: Molecular portraits of human breast tumours
  publication-title: Nature
  doi: 10.1038/35021093
SSID ssj0002776143
Score 2.271974
Snippet Abstract Motivation Cancer is one of the world’s leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions...
Cancer is one of the world's leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among heterogeneous data...
Motivation Cancer is one of the world’s leading mortality causes, and its prognosis is hard to predict due to complicated biological interactions among...
SourceID pubmedcentral
proquest
pubmed
crossref
oup
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage vbac100
SubjectTerms Bayesian analysis
Bioinformatics
Breast cancer
Deep learning
Mathematical models
Medical prognosis
Neural networks
Non-small cell lung carcinoma
Original Paper
Precision medicine
Prognosis
Small cell lung carcinoma
Title Learning from small medical data—robust semi-supervised cancer prognosis classifier with Bayesian variational autoencoder
URI https://www.ncbi.nlm.nih.gov/pubmed/36698767
https://www.proquest.com/docview/3192321488
https://www.proquest.com/docview/2769995433
https://pubmed.ncbi.nlm.nih.gov/PMC9832968
Volume 3
WOSCitedRecordID wos001124263600026&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: Open Access资源_DOAJ
  customDbUrl:
  eissn: 2635-0041
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002776143
  issn: 2635-0041
  databaseCode: DOA
  dateStart: 20210101
  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: 2635-0041
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002776143
  issn: 2635-0041
  databaseCode: M~E
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVASL
  databaseName: Oxford Journals Open Access Collection
  customDbUrl:
  eissn: 2635-0041
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002776143
  issn: 2635-0041
  databaseCode: TOX
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://academic.oup.com/journals/
  providerName: Oxford University Press
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 2635-0041
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002776143
  issn: 2635-0041
  databaseCode: M7P
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest - Publicly Available Content Database
  customDbUrl:
  eissn: 2635-0041
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002776143
  issn: 2635-0041
  databaseCode: PIMPY
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2635-0041
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002776143
  issn: 2635-0041
  databaseCode: BENPR
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwEB6xuyBx4f0ILJVBSJyitrHrJCfEol3BgRKhRSqnyHacJVKblDiptOLCj-AX8kvwJG5okYADxySWEmXGM5_n8Q3Ac8YnOsy59nOeMZ8xe0CJp2riW11RYSSZ9TKsGzYRzufRYhEnLuBmXFnl1iZ2hjqrFMbIxxShSGDBe_Ry_cXHqVGYXXUjNA7gCFkSgq50LxliLEFoD-mMDlyNdCyLSmSb8UYKNcWmth1ftNfftgMzf6-W3HE_Zzf_98NvwQ0HPMmrXlNuwxVd3oFr_SjKy7vw1RGtXhBsOCFmJZZLsuqzOATLSH98-15XsjUNMXpV-KZdo5UxOiMKFacmWOlVVqYwRCEiL3LrcAmGecmJuNTYq0k29mDugo9EtE2FJJqZru_Bx7PT89dvfDeYwVdsFjS-_dX2lKSsnZRUMxnlOo-mXReszBBfCSGliqTUM62CXAnkuOOB5HKidCwopffhsKxK_RDITEsVC64tLqEsU0Gkc4twZpkSmLIUuQf-VkSpcqzlODxjmfbZc5r2Ik2dSD14Maxf93wdf1z5zEr8n4uOt0JN3eY26S-JevB0eGy3JeZaRKmr1qRByGOk2qPUgwe9_gyvopzH1gmFHoR7mjUsQMrv_Sdl8bmj_o6tAY559Ojvn_UYrgcWi_WRomM4bOpWP4GratMUph7BQbiIRnB0cjpPPoy6IMSo2zf2XvL2XfLJXp2_X_wEKW4qZQ
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwEB6tuiC48H4EFjAIxClq67hOckCI12qr3a16WKTlFGzHgUhtUuKkqOLCj-B38KP4JXiaBy0ScNoD54yU1-eZz-OZbwAeMz7QfsK1m_CYuYzZDUo4VAPXYkX5gWQ2yrD1sAl_MglOT8PpDnxve2GwrLL1iWtHHecKc-R9D6kIteQ9eL745OLUKDxdbUdo1LA41KvPdstmno1f2__7hNL9NyevDtxmqoCr2IiWrr27pfjKLnLpaSaDRCfBcN3CKWMkB0JIqQIp9UgrmiiBAm2cSi4HSofCwwSodfm7DMHeg93p-Hj6rsvqUGtrGUinDun1ZZqLeNlfSqGG2Ea3Ef22Ouo2iO3v9ZkbAW__8v_2qa7ApYZakxf1WrgKOzq7BufrYZur6_ClkZL9QLClhpi5mM3IvD6nIlgo--PrtyKXlSmJ0fPUNdUC_ajRMVG4NAqCtWxZblJDFO450sRSCoKJbPJSrDR2o5KlKNImvUpEVeYoExrr4ga8PZM3vwm9LM_0bSAjLVUouLbMy2OxooFOLIcbxUrgoaxIHHBbSESq0WXH8SCzqK4P8KIaQlEDIQeedvaLWpHkj5aPLML-abTXgihq3JeJfiHIgYfdZet48DRJZDqvTER9HqKYoOc5cKvGa3crj_PQhlnfAX8LyZ0BippvX8nSj2tx89CGmJAHd_7-WA_gwsHJ8VF0NJ4c3oWL1DLPOi-2B72yqPQ9OKeWZWqK-80KJfD-rJH-E8Mbg9A
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=Learning+from+small+medical+data%E2%80%94robust+semi-supervised+cancer+prognosis+classifier+with+Bayesian+variational+autoencoder&rft.jtitle=Bioinformatics+advances&rft.au=Te-Cheng%2C+Hsu&rft.au=Lin%2C+Che&rft.date=2023&rft.pub=Oxford+University+Press&rft.eissn=2635-0041&rft.volume=3&rft.issue=1&rft_id=info:doi/10.1093%2Fbioadv%2Fvbac100
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2635-0041&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2635-0041&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2635-0041&client=summon