Automated Detection of Glaucoma With Interpretable Machine Learning Using Clinical Data and Multimodal Retinal Images

To develop a multimodal model to automate glaucoma detection Development of a machine-learning glaucoma detection model We selected a study cohort from the UK Biobank data set with 1193 eyes of 863 healthy subjects and 1283 eyes of 771 subjects with glaucoma. We trained a multimodal model that combi...

Full description

Saved in:
Bibliographic Details
Published inAmerican journal of ophthalmology Vol. 231; pp. 154 - 169
Main Authors Mehta, Parmita, Petersen, Christine A., Wen, Joanne C., Banitt, Michael R., Chen, Philip P., Bojikian, Karine D., Egan, Catherine, Lee, Su-In, Balazinska, Magdalena, Lee, Aaron Y., Rokem, Ariel
Format Journal Article
LanguageEnglish
Published United States Elsevier Inc 01.11.2021
Elsevier Limited
Subjects
Online AccessGet full text
ISSN0002-9394
1879-1891
1879-1891
DOI10.1016/j.ajo.2021.04.021

Cover

Abstract To develop a multimodal model to automate glaucoma detection Development of a machine-learning glaucoma detection model We selected a study cohort from the UK Biobank data set with 1193 eyes of 863 healthy subjects and 1283 eyes of 771 subjects with glaucoma. We trained a multimodal model that combines multiple deep neural nets, trained on macular optical coherence tomography volumes and color fundus photographs, with demographic and clinical data. We performed an interpretability analysis to identify features the model relied on to detect glaucoma. We determined the importance of different features in detecting glaucoma using interpretable machine learning methods. We also evaluated the model on subjects who did not have a diagnosis of glaucoma on the day of imaging but were later diagnosed (progress-to-glaucoma [PTG]). Results show that a multimodal model that combines imaging with demographic and clinical features is highly accurate (area under the curve 0.97). Interpretation of this model highlights biological features known to be related to the disease, such as age, intraocular pressure, and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary function and retinal outer layers. Accurate prediction in PTG highlights variables that change with progression to glaucoma—age and pulmonary function. The accuracy of our model suggests distinct sources of information in each imaging modality and in the different clinical and demographic variables. Interpretable machine learning methods elucidate subject-level prediction and help uncover the factors that lead to accurate predictions, pointing to potential disease mechanisms or variables related to the disease.
AbstractList To develop a multimodal model to automate glaucoma detection DESIGN: Development of a machine-learning glaucoma detection model METHODS: We selected a study cohort from the UK Biobank data set with 1193 eyes of 863 healthy subjects and 1283 eyes of 771 subjects with glaucoma. We trained a multimodal model that combines multiple deep neural nets, trained on macular optical coherence tomography volumes and color fundus photographs, with demographic and clinical data. We performed an interpretability analysis to identify features the model relied on to detect glaucoma. We determined the importance of different features in detecting glaucoma using interpretable machine learning methods. We also evaluated the model on subjects who did not have a diagnosis of glaucoma on the day of imaging but were later diagnosed (progress-to-glaucoma [PTG]).PURPOSETo develop a multimodal model to automate glaucoma detection DESIGN: Development of a machine-learning glaucoma detection model METHODS: We selected a study cohort from the UK Biobank data set with 1193 eyes of 863 healthy subjects and 1283 eyes of 771 subjects with glaucoma. We trained a multimodal model that combines multiple deep neural nets, trained on macular optical coherence tomography volumes and color fundus photographs, with demographic and clinical data. We performed an interpretability analysis to identify features the model relied on to detect glaucoma. We determined the importance of different features in detecting glaucoma using interpretable machine learning methods. We also evaluated the model on subjects who did not have a diagnosis of glaucoma on the day of imaging but were later diagnosed (progress-to-glaucoma [PTG]).Results show that a multimodal model that combines imaging with demographic and clinical features is highly accurate (area under the curve 0.97). Interpretation of this model highlights biological features known to be related to the disease, such as age, intraocular pressure, and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary function and retinal outer layers. Accurate prediction in PTG highlights variables that change with progression to glaucoma-age and pulmonary function.RESULTSResults show that a multimodal model that combines imaging with demographic and clinical features is highly accurate (area under the curve 0.97). Interpretation of this model highlights biological features known to be related to the disease, such as age, intraocular pressure, and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary function and retinal outer layers. Accurate prediction in PTG highlights variables that change with progression to glaucoma-age and pulmonary function.The accuracy of our model suggests distinct sources of information in each imaging modality and in the different clinical and demographic variables. Interpretable machine learning methods elucidate subject-level prediction and help uncover the factors that lead to accurate predictions, pointing to potential disease mechanisms or variables related to the disease.CONCLUSIONSThe accuracy of our model suggests distinct sources of information in each imaging modality and in the different clinical and demographic variables. Interpretable machine learning methods elucidate subject-level prediction and help uncover the factors that lead to accurate predictions, pointing to potential disease mechanisms or variables related to the disease.
PurposeTo develop a multimodal model to automate glaucoma detectionDesignDevelopment of a machine-learning glaucoma detection modelMethodsWe selected a study cohort from the UK Biobank data set with 1193 eyes of 863 healthy subjects and 1283 eyes of 771 subjects with glaucoma. We trained a multimodal model that combines multiple deep neural nets, trained on macular optical coherence tomography volumes and color fundus photographs, with demographic and clinical data. We performed an interpretability analysis to identify features the model relied on to detect glaucoma. We determined the importance of different features in detecting glaucoma using interpretable machine learning methods. We also evaluated the model on subjects who did not have a diagnosis of glaucoma on the day of imaging but were later diagnosed (progress-to-glaucoma [PTG]).ResultsResults show that a multimodal model that combines imaging with demographic and clinical features is highly accurate (area under the curve 0.97). Interpretation of this model highlights biological features known to be related to the disease, such as age, intraocular pressure, and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary function and retinal outer layers. Accurate prediction in PTG highlights variables that change with progression to glaucoma—age and pulmonary function.ConclusionsThe accuracy of our model suggests distinct sources of information in each imaging modality and in the different clinical and demographic variables. Interpretable machine learning methods elucidate subject-level prediction and help uncover the factors that lead to accurate predictions, pointing to potential disease mechanisms or variables related to the disease.
To develop a multimodal model to automate glaucoma detection Development of a machine-learning glaucoma detection model We selected a study cohort from the UK Biobank data set with 1193 eyes of 863 healthy subjects and 1283 eyes of 771 subjects with glaucoma. We trained a multimodal model that combines multiple deep neural nets, trained on macular optical coherence tomography volumes and color fundus photographs, with demographic and clinical data. We performed an interpretability analysis to identify features the model relied on to detect glaucoma. We determined the importance of different features in detecting glaucoma using interpretable machine learning methods. We also evaluated the model on subjects who did not have a diagnosis of glaucoma on the day of imaging but were later diagnosed (progress-to-glaucoma [PTG]). Results show that a multimodal model that combines imaging with demographic and clinical features is highly accurate (area under the curve 0.97). Interpretation of this model highlights biological features known to be related to the disease, such as age, intraocular pressure, and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary function and retinal outer layers. Accurate prediction in PTG highlights variables that change with progression to glaucoma—age and pulmonary function. The accuracy of our model suggests distinct sources of information in each imaging modality and in the different clinical and demographic variables. Interpretable machine learning methods elucidate subject-level prediction and help uncover the factors that lead to accurate predictions, pointing to potential disease mechanisms or variables related to the disease.
To develop a multimodal model to automate glaucoma detection DESIGN: Development of a machine-learning glaucoma detection model METHODS: We selected a study cohort from the UK Biobank data set with 1193 eyes of 863 healthy subjects and 1283 eyes of 771 subjects with glaucoma. We trained a multimodal model that combines multiple deep neural nets, trained on macular optical coherence tomography volumes and color fundus photographs, with demographic and clinical data. We performed an interpretability analysis to identify features the model relied on to detect glaucoma. We determined the importance of different features in detecting glaucoma using interpretable machine learning methods. We also evaluated the model on subjects who did not have a diagnosis of glaucoma on the day of imaging but were later diagnosed (progress-to-glaucoma [PTG]). Results show that a multimodal model that combines imaging with demographic and clinical features is highly accurate (area under the curve 0.97). Interpretation of this model highlights biological features known to be related to the disease, such as age, intraocular pressure, and optic disc morphology. Our model also points to previously unknown or disputed features, such as pulmonary function and retinal outer layers. Accurate prediction in PTG highlights variables that change with progression to glaucoma-age and pulmonary function. The accuracy of our model suggests distinct sources of information in each imaging modality and in the different clinical and demographic variables. Interpretable machine learning methods elucidate subject-level prediction and help uncover the factors that lead to accurate predictions, pointing to potential disease mechanisms or variables related to the disease.
Author Lee, Aaron Y.
Chen, Philip P.
Bojikian, Karine D.
Petersen, Christine A.
Wen, Joanne C.
Lee, Su-In
Balazinska, Magdalena
Mehta, Parmita
Rokem, Ariel
Banitt, Michael R.
Egan, Catherine
Author_xml – sequence: 1
  givenname: Parmita
  surname: Mehta
  fullname: Mehta, Parmita
  organization: From the Paul G. Allen School of Computer Science and Engineering, Seattle, Washington, USA (PM, S-IL, MB)
– sequence: 2
  givenname: Christine A.
  orcidid: 0000-0002-8400-3721
  surname: Petersen
  fullname: Petersen, Christine A.
  organization: Department of Ophthalmology, Seattle, Washington, USA (CAP, JCW, MRB, PPC, KDB, AYL)
– sequence: 3
  givenname: Joanne C.
  surname: Wen
  fullname: Wen, Joanne C.
  organization: Department of Ophthalmology, Seattle, Washington, USA (CAP, JCW, MRB, PPC, KDB, AYL)
– sequence: 4
  givenname: Michael R.
  surname: Banitt
  fullname: Banitt, Michael R.
  organization: Department of Ophthalmology, Seattle, Washington, USA (CAP, JCW, MRB, PPC, KDB, AYL)
– sequence: 5
  givenname: Philip P.
  surname: Chen
  fullname: Chen, Philip P.
  organization: Department of Ophthalmology, Seattle, Washington, USA (CAP, JCW, MRB, PPC, KDB, AYL)
– sequence: 6
  givenname: Karine D.
  surname: Bojikian
  fullname: Bojikian, Karine D.
  organization: Department of Ophthalmology, Seattle, Washington, USA (CAP, JCW, MRB, PPC, KDB, AYL)
– sequence: 7
  givenname: Catherine
  surname: Egan
  fullname: Egan, Catherine
  organization: Moorfields Eye Hospital, NHS Trust, UK (C.E.)
– sequence: 8
  givenname: Su-In
  surname: Lee
  fullname: Lee, Su-In
  organization: From the Paul G. Allen School of Computer Science and Engineering, Seattle, Washington, USA (PM, S-IL, MB)
– sequence: 9
  givenname: Magdalena
  surname: Balazinska
  fullname: Balazinska, Magdalena
  organization: From the Paul G. Allen School of Computer Science and Engineering, Seattle, Washington, USA (PM, S-IL, MB)
– sequence: 10
  givenname: Aaron Y.
  surname: Lee
  fullname: Lee, Aaron Y.
  organization: Department of Ophthalmology, Seattle, Washington, USA (CAP, JCW, MRB, PPC, KDB, AYL)
– sequence: 11
  givenname: Ariel
  orcidid: 0000-0003-0679-1985
  surname: Rokem
  fullname: Rokem, Ariel
  email: arokem@uw.edu
  organization: eScience Institute, Seattle, Washington, USA (MB, AR)
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33945818$$D View this record in MEDLINE/PubMed
BookMark eNqNks1uEzEUhS1URNPCA7BBlth0k2B7JjNjsapSKJFSISEqlpZ_7rQOHjvYHlDeHo8SWGRR2PjI19-xrs_1BTrzwQNCrylZUEKbd9uF3IYFI4wuSL0o8gzNaNfyOe04PUMzQgib84rX5-gipW3ZNm3dvkDnVaktO9rN0Hg95jDIDAbfQAadbfA49PjWyVGXA_zN5ke89hniLkKWygG-k_rResAbkNFb_4Dv07SunPVWS4dvZJZYeoPvRpftEEypfYFsfdH1IB8gvUTPe-kSvDrqJbr_-OHr6tN88_l2vbrezHXd1nmujWKaqb6jqpNd3StKNG-XVHJulOo5ZUaqHqhq-rY2VQ-K9EsFhuiurqCh1SVih3tHv5P7X9I5sYt2kHEvKBFThmIrSoZiylCQWhQppquDaRfDjxFSFoNNGpyTHsKYBFsyVpVUW1bQtyfoNoyxvHOiOCdN0_Flod4cqVENYP628GcKBWgPgI4hpQi90DbLaRQ5Suue7JWeOP_nfe8PHijJ_7QQRdIWvAZjY_kAwgT7pJufuPVx7t9h_w_vb2wv1Xw
CitedBy_id crossref_primary_10_1088_1741_2552_ad310f
crossref_primary_10_3389_fmed_2024_1489139
crossref_primary_10_1186_s40662_024_00405_1
crossref_primary_10_1007_s00417_022_05738_y
crossref_primary_10_1155_2024_8053117
crossref_primary_10_1007_s11831_023_09989_8
crossref_primary_10_1016_j_knosys_2025_113333
crossref_primary_10_4015_S1016237224500303
crossref_primary_10_1016_j_artmed_2024_103050
crossref_primary_10_1097_APO_0000000000000596
crossref_primary_10_1038_s43856_024_00496_w
crossref_primary_10_1063_5_0082179
crossref_primary_10_1109_ACCESS_2024_3477420
crossref_primary_10_1007_s11042_024_19989_w
crossref_primary_10_1016_j_clinimag_2023_05_011
crossref_primary_10_1016_j_cmpb_2024_108253
crossref_primary_10_1016_j_preteyeres_2024_101291
crossref_primary_10_3389_fmed_2022_891369
crossref_primary_10_1016_j_preteyeres_2021_101034
crossref_primary_10_14801_jkiit_2024_22_6_13
crossref_primary_10_1097_ICU_0000000000000846
crossref_primary_10_3390_bioengineering11060577
crossref_primary_10_1002_hbm_26267
crossref_primary_10_1016_j_eswa_2024_124888
crossref_primary_10_12968_opti_2024_269_6945_25
crossref_primary_10_3389_fpubh_2022_971943
crossref_primary_10_1038_s41598_025_87219_w
crossref_primary_10_3390_diagnostics12040935
crossref_primary_10_1186_s12938_023_01187_8
crossref_primary_10_4103_ijo_IJO_2566_21
crossref_primary_10_4103_tjo_TJO_D_24_00044
crossref_primary_10_1038_s41597_022_01695_7
crossref_primary_10_1088_2057_1976_ada8ad
crossref_primary_10_1016_j_xops_2025_100703
crossref_primary_10_1088_2632_2153_ad0798
crossref_primary_10_1080_08839514_2021_1993003
crossref_primary_10_1097_ICU_0000000000000781
crossref_primary_10_3389_fdata_2023_1017420
crossref_primary_10_3390_math11030707
crossref_primary_10_3390_diagnostics12030734
crossref_primary_10_1016_j_jfo_2021_11_002
crossref_primary_10_1097_IJG_0000000000002267
crossref_primary_10_1038_s41598_024_62411_6
crossref_primary_10_1016_j_compbiomed_2022_106283
crossref_primary_10_1080_08164622_2023_2235346
crossref_primary_10_1038_s41433_023_02622_9
crossref_primary_10_1167_tvst_13_9_3
crossref_primary_10_3389_fphar_2022_930520
crossref_primary_10_1109_LSP_2025_3526094
crossref_primary_10_1167_tvst_11_10_24
Cites_doi 10.1038/s42256-019-0138-9
10.1001/jamaophthalmol.2019.3501
10.4093/dmj.2019.0048
10.1371/journal.pone.0196112
10.1097/01.ijg.0000212268.42606.97
10.1016/j.ophtha.2014.05.013
10.1001/jamaophthalmol.2013.7974
10.1080/00401706.1964.10490181
10.1001/jamadermatol.2019.1735
10.1111/j.1442-9071.2011.02530.x
10.1371/journal.pmed.1001779
10.1001/archopht.120.6.701
10.1016/j.ophtha.2019.07.024
10.1001/archopht.120.10.1268
10.1038/eye.2017.1
10.1016/j.ophtha.2004.01.025
10.1016/j.ophtha.2018.01.023
10.1001/archopht.118.8.1105
10.1016/j.ophtha.2019.08.015
10.1016/j.media.2009.12.006
10.1167/tvst.4.2.1
10.1609/aaai.v31i1.11231
10.1016/j.ophtha.2014.01.003
10.1007/s10916-008-9195-z
10.1073/pnas.1900654116
10.2105/AJPH.2006.098202
10.1016/j.ophtha.2016.07.033
10.1016/j.puhe.2003.09.009
10.1097/IJG.0000000000000771
10.1136/bjo.2010.183756
10.1007/978-3-540-88690-7_6
10.23915/distill.00010
10.1186/1471-2415-12-52
10.2174/1874609811104020110
10.1097/IJG.0000000000000765
10.1371/journal.pone.0219126
10.1001/archopht.122.4.532
10.1038/s41746-019-0105-1
10.1001/archopht.1979.01020020117005
10.1001/jamaophthalmol.2019.5983
10.1155/2017/9787450
10.1167/iovs.08-1759
10.5301/ejo.5000678
10.1214/aos/1013203451
10.1097/00061198-199902000-00004
10.1001/jama.2017.18152
10.1109/STSIVA.2019.8730250
10.1167/iovs.11-7962
10.1097/IJG.0000000000000867
10.1136/thx.41.4.301
10.1016/j.ajo.2016.10.020
10.1001/archopht.1994.01090170088028
10.1167/tvst.8.2.10
10.1038/s41598-017-09421-9
10.1007/s11356-017-9812-9
10.1038/s41551-018-0195-0
10.1038/s41598-019-56337-7
10.2147/OPTH.S162023
10.1109/TKDE.2009.191
10.23915/distill.00007
10.1136/bjo.57.3.179
10.1016/j.envres.2020.109161
10.1371/journal.pone.0209610
10.1167/tvst.9.2.11
10.1371/journal.pone.0176894
10.1080/00039896.1991.9937440
10.1016/j.ajo.2018.04.025
10.1016/S0161-6420(94)31090-6
10.1001/archopht.118.2.235
10.1001/jama.1991.03470030069026
10.1586/17469899.2014.967218
10.1001/archopht.1990.01070040074034
10.1001/archopht.1980.01020041015002
10.1016/j.preteyeres.2007.08.001
10.1038/s41591-018-0107-6
10.1167/iovs.19-28346
10.1093/aje/kwx246
10.1038/s41598-019-42042-y
10.4258/hir.2018.24.1.53
10.1016/S0161-6420(96)30449-1
ContentType Journal Article
Copyright 2021 Elsevier Inc.
Copyright © 2021 Elsevier Inc. All rights reserved.
2021. Elsevier Inc.
Copyright_xml – notice: 2021 Elsevier Inc.
– notice: Copyright © 2021 Elsevier Inc. All rights reserved.
– notice: 2021. Elsevier Inc.
CorporateAuthor UK Biobank Eye and Vision Consortium
CorporateAuthor_xml – name: UK Biobank Eye and Vision Consortium
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
K9.
NAPCQ
7X8
ADTOC
UNPAY
DOI 10.1016/j.ajo.2021.04.021
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Premium
MEDLINE - Academic
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Premium
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
ProQuest Health & Medical Complete (Alumni)


MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1879-1891
EndPage 169
ExternalDocumentID oai:pubmedcentral.nih.gov:8560651
33945818
10_1016_j_ajo_2021_04_021
S0002939421002208
Genre Research Support, U.S. Gov't, Non-P.H.S
Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GeographicLocations United Kingdom--UK
GeographicLocations_xml – name: United Kingdom--UK
GrantInformation_xml – fundername: NEI NIH HHS
  grantid: K23 EY029246
– fundername: NIGMS NIH HHS
  grantid: R35 GM128638
GroupedDBID ---
--K
--M
-~X
.1-
.55
.FO
.GJ
.~1
0R~
1B1
1CY
1P~
1~.
1~5
23M
4.4
457
4G.
53G
5GY
5RE
5VS
6J9
7-5
71M
8P~
AABNK
AAEDT
AAEDW
AAHTB
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQQT
AAQXK
AATTM
AAWTL
AAXKI
AAXUO
AAYWO
ABBQC
ABCQX
ABDPE
ABFNM
ABFRF
ABJNI
ABLJU
ABMAC
ABMZM
ABOCM
ABPEJ
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACIEU
ACIUM
ACLOT
ACNCT
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADFRT
ADMUD
ADNMO
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AEVXI
AFFNX
AFJKZ
AFPUW
AFRHN
AFTJW
AFXIZ
AGHFR
AGQPQ
AGUBO
AGYEJ
AHMBA
AI.
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJRQY
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ANZVX
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BKEYQ
BKOJK
BLXMC
BNPGV
BPHCQ
BVXVI
CS3
EBS
EFJIC
EFKBS
EFLBG
EJD
EMOBN
EO8
EO9
EP2
EP3
EX3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HVGLF
HZ~
IHE
J1W
J5H
K-O
KOM
L7B
M41
MO0
N4W
N9A
O-L
O9-
OAUVE
OF-
OPF
OQ~
OZT
P-8
P-9
P2P
PC.
PQQKQ
PROAC
Q38
R2-
ROL
RPZ
SCC
SDF
SDG
SDP
SEL
SES
SPCBC
SSH
SSZ
SV3
T5K
UNMZH
UV1
VH1
WH7
WOW
X7M
XPP
Z5R
ZGI
ZXP
~G-
~HD
3V.
7RV
7X7
8FI
AACTN
AAIAV
ABLVK
ABYKQ
AFCTW
AFKRA
AFKWA
AHPSJ
AJBFU
AJOXV
AMFUW
AZQEC
BENPR
FYUFA
G8K
GUQSH
LCYCR
M1P
M2O
RIG
ZA5
AAYXX
CITATION
AGCQF
AGRNS
CGR
CUY
CVF
ECM
EIF
NPM
K9.
NAPCQ
7X8
ADTOC
UNPAY
ID FETCH-LOGICAL-c474t-cdb2c2bf81b8a84fb10c9751a99dbbf912dabfe1b6f74d3feb0f5bed0c843e613
IEDL.DBID UNPAY
ISSN 0002-9394
1879-1891
IngestDate Sun Oct 26 04:09:20 EDT 2025
Sun Sep 28 03:54:36 EDT 2025
Tue Oct 07 05:33:17 EDT 2025
Mon Jul 21 05:13:52 EDT 2025
Wed Oct 01 05:17:48 EDT 2025
Thu Apr 24 23:08:52 EDT 2025
Fri Feb 23 02:43:07 EST 2024
Tue Oct 14 19:30:39 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License Copyright © 2021 Elsevier Inc. All rights reserved.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c474t-cdb2c2bf81b8a84fb10c9751a99dbbf912dabfe1b6f74d3feb0f5bed0c843e613
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-0679-1985
0000-0002-8400-3721
OpenAccessLink https://proxy.k.utb.cz/login?url=https://www.ncbi.nlm.nih.gov/pmc/articles/8560651
PMID 33945818
PQID 2599066895
PQPubID 41749
PageCount 16
ParticipantIDs unpaywall_primary_10_1016_j_ajo_2021_04_021
proquest_miscellaneous_2522393972
proquest_journals_2599066895
pubmed_primary_33945818
crossref_citationtrail_10_1016_j_ajo_2021_04_021
crossref_primary_10_1016_j_ajo_2021_04_021
elsevier_sciencedirect_doi_10_1016_j_ajo_2021_04_021
elsevier_clinicalkey_doi_10_1016_j_ajo_2021_04_021
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate November 2021
2021-11-00
20211101
PublicationDateYYYYMMDD 2021-11-01
PublicationDate_xml – month: 11
  year: 2021
  text: November 2021
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Chicago
PublicationTitle American journal of ophthalmology
PublicationTitleAlternate Am J Ophthalmol
PublicationYear 2021
Publisher Elsevier Inc
Elsevier Limited
Publisher_xml – name: Elsevier Inc
– name: Elsevier Limited
References Choi, Zawadzki, Lim (bib0096) 2011; 95
Dirani, Crowston, Taylor (bib0006) 2011; 39
Mwanza, Oakley, Budenz, Chang, Knight, Feuer (bib0021) 2011; 52
Lundberg, Erion, Chen (bib0052) 2020; 2
Huang, Liu, Pleiss, Van Der Maaten, Weinberger (bib0032) 2019
Roth (bib0061) 1988
Fry, Littlejohns, Sudlow (bib0105) 2017; 186
Yanagihara, Lee, Ting, Lee (bib0034) 2020; 9
Gasser, Stümpfig, Schötzau, Ackermann-Liebrich, Flammer (bib0057) 1999; 8
Sundararajan M, Taly A, Yan Q. Axiomatic attribution for deep networks.
Varma, Ying-Lai, Francis (bib0074) 2004; 111
Gao, Huang, Kim (bib0076) 2019; 8
2017;1703.01365.
Perkins (bib0068) 1973; 57
Liu, Li, Wormstone (bib0019) 2019; 137
Wang, Li, Guo, Song, Wang, Ma (bib0081) 2017; 24
Sudlow, Gallacher, Allen (bib0031) 2015; 12
.
Foster, Oen, Machin (bib0005) 2000; 118
Thompson, Jammal, Berchuck, Mariottoni, Medeiros (bib0100) 2020; 138
Tielsch, Sommer, Katz, Royall, Quigley, Javitt (bib0104) 1991; 266
Ahmed A, Yu K, Xu W, Gong Y, Xing E. Training hierarchical feed-forward visual recognition models using transfer learning from pseudo-tasks. In: Forsyth D, Torr P, Zisserman A, eds.
Olah, Mordvintsev, Schubert (bib0065) 2017; 2
Glaucoma Research Foundation: Glaucoma Facts and Stats. Accessed December 2019.
Poplin, Varadarajan, Blumer (bib0072) 2018; 2
Ignacio Orlando, Prokofyeva, del Fresno, Blaschko (bib0016) 2017
Hart, Yablonski, Kass, Becker (bib0069) 1979; 97
ImageNet. Accessed XXXX.
Carrillo J, Bautista L, Villamizar J, Rueda J, Sanchez M, Rueda D. Glaucoma detection using fundus. 2019. Images of the eye. Paper presented at: 2019 XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA); April 24-26, 2019; Bucaramanga, Colombia. doi: 10.1109/STSIVA.2019.8730250.
Murdoch, Singh, Kumbier, Abbasi-Asl, Yu (bib0030) 2019; 116
Bonovas, Filioussi, Tsantes, Peponis (bib0048) 2004; 118
Newman-Casey, Verkade, Oren, Robin (bib0062) 2014; 9
Panda, Jonas (bib0094) 1992; 33
Cifuentes-Canorea, Ruiz-Medrano, Gutierrez-Bonet (bib0088) 2018; 13
Shen, Wong, Foster (bib0004) 2008; 49
Dunn (bib0054) 1964; 6
Muhammad, Fuchs, De Cuir (bib0022) 2017; 26
Ryskulova, Turczyn, Makuc, Cotch, Klein, Janiszewski (bib0073) 2008; 98
Ting, Cheung, Lim (bib0018) 2017; 318
Efron, Tibshirani (bib0053) 1986; 1
He, Zhang, Ren, Sun (bib0033) 2015
UK Biobank. Accessed September 2019.
Pan, Yang (bib0039) 2009; 22
Li, Pang, Xiong, Liu, Liang, Wang (bib0041) 2017
Lin, Pasquale, Singh, Lin (bib0078) 2018; 27
Olah, Satyanarayan, Johnson, Carter, Schubert, Ye, Mordvintsev (bib0064) 2018; 3
Badgeley, Zech, Oakden-Rayner (bib0029) 2019; 2
Friedman (bib0044) 2001; 29
Lee, Kim, Kim (bib0058) 2017; 12
Holopigian, Seiple, Mayron, Koty, Lorenzo (bib0092) 1990; 31
Maetschke, Antony, Ishikawa, Wollstein, Schuman, Garnavi (bib0026) 2019; 14
Müller, Kornblith, Hinton (bib0036) 2019; 14
Ko, Foster, Strouthidis (bib0090) 2017; 124
Nork, Ver Hoeve, Poulsen (bib0095) 2000; 118
Heijl, Leske, Bengtsson (bib0008) 2002; 120
Klein, Lee, Gangnon, Klein (bib0059) 2014; 121
Chen, Xu, Wong, Wong, Liu (bib0015) 2015; 2015
Guedes, Tsai, Loewen (bib0055) 2011; 4
Friedman, Wolfs, O'Colmain (bib0075) 2004; 122
Hood, Kardon (bib0010) 2007; 26
vol 5304. Berlin: Springer; 2008. https://doi.org/10.1007/978-3-540-88690-7_6
Lee, Tyring, Wu (bib0099) 2019; 9
Foreman, Xie, Keel, van Wijngaarden, Taylor, Dirani (bib0101) 2017; 7
Li, He, Keel, Meng, Chang, He (bib0020) 2018; 125
Khawaja, Chua, Hysi (bib0086) 2020; 127
Foot, MacEwen (bib0002) 2017; 31
Lundberg, Lee (bib0060) 2017
Nayak, Acharya, Bhat, Shetty, Lim (bib0014) 2009; 33
Miki, Kumoi, Usui (bib0024) 2017; 26
Pavia, Bateman, Lennard-Jones, Agnew, Clarke (bib0083) 1986; 41
Asrani, Essaid, Alder, Santiago-Turla (bib0025) 2014; 132
De Fauw, Ledsam, Romera-Paredes (bib0035) 2018; 24
Septiarini, Khairina, Kridalaksana, Hamdani (bib0013) 2018; 24
Ha, Sun, Kim, Jeoung, Kim, Park (bib0098) 2019; 9
Wood M. How sure are we? Two approaches to statistical inference.
Ha, Kim, Jeoung, Park (bib0097) 2018; 192
Szegedy, Ioffe, Vanhoucke, Alemi (bib0042) 2017
Patel, Reddy, Lin, Whitson (bib0085) 2018; 12
Jung, Han, Park, Lee, Park (bib0056) 2020; 44
Dielemans, Vingerling, Wolfs, Hofman, Grobbee, de Jong (bib0103) 1994; 101
Quigley, Enger, Katz, Sommer, Scott, Gilbert (bib0071) 1994; 112
Kendell, Quigley, Kerrigan, Pease, Quigley (bib0091) 1995; 36
Kingma, Adam (bib0038) 2014
Kass, Heuer, Higginbotham (bib0067) 2002; 120
Szegedy, Liu, Jia (bib0063) 2015
Shrikumar, Greenside, Kundaje (bib0066) 2017; 70
Smilkov D, Thorat N, Kim B, Viégas F, Wattenberg M. Smoothgrad: removing noise by adding noise.
2018;1803.06214.
Kita, Anraku, Kita, Goldberg (bib0089) 2016; 26
Susanna, De Moraes, Cioffi, Ritch (bib0007) 2015; 4
Boland, Ervin, Friedman (bib0009) April 2012
Armaly (bib0084) 1970; 9
Chestnut, Schwartz, Savitz, Burchfiel (bib0080) 1991; 46
Winkler, Fink, Toberer (bib0028) 2019; 155
Havet, Hulo, Cuny (bib0082) 2020; 183
Mitchell, Smith, Attebo, Healey (bib0102) 1996; 103
Phene, Dunn, Hammel (bib0017) 2019; 126
Tham, Li, Wong, Quigley, Aung, Cheng (bib0001) 2014; 121
2017;1706.03825.
Chen, XGBoost (bib0045) 2016
Liu, Ling, Chen, Wu, Lu (bib0077) 2017; 2017
Odom, Feghali, Jin, Weinstein (bib0093) 1990; 108
Unterlauft, Rehak, Böhm, Rauscher (bib0087) 2018; 13
Ehrlich, Radcliffe, Shimmyo (bib0047) 2012; 12
Abadi, Agarwal, Barham (bib0037) 2016
Mansberger, Menda, Fortune, Gardiner, Demirel (bib0023) 2017; 174
Armaly, Krueger, Maunder (bib0070) 1980; 98
Chua, Khawaja, Morgan (bib0079) 2019; 60
Bock, Meier, Nyúl, Hornegger, Michelson (bib0011) 2010; 14
Medeiros, Weinreb (bib0046) 2006; 15
Klein (10.1016/j.ajo.2021.04.021_bib0059) 2014; 121
Ha (10.1016/j.ajo.2021.04.021_bib0097) 2018; 192
Gasser (10.1016/j.ajo.2021.04.021_bib0057) 1999; 8
Tielsch (10.1016/j.ajo.2021.04.021_bib0104) 1991; 266
Murdoch (10.1016/j.ajo.2021.04.021_bib0030) 2019; 116
Dirani (10.1016/j.ajo.2021.04.021_bib0006) 2011; 39
Lundberg (10.1016/j.ajo.2021.04.021_bib0060) 2017
Newman-Casey (10.1016/j.ajo.2021.04.021_bib0062) 2014; 9
Huang (10.1016/j.ajo.2021.04.021_bib0032) 2019
Dielemans (10.1016/j.ajo.2021.04.021_bib0103) 1994; 101
Olah (10.1016/j.ajo.2021.04.021_bib0064) 2018; 3
Li (10.1016/j.ajo.2021.04.021_bib0020) 2018; 125
Pan (10.1016/j.ajo.2021.04.021_bib0039) 2009; 22
Müller (10.1016/j.ajo.2021.04.021_bib0036) 2019; 14
Lin (10.1016/j.ajo.2021.04.021_bib0078) 2018; 27
10.1016/j.ajo.2021.04.021_bib0040
10.1016/j.ajo.2021.04.021_bib0043
Tham (10.1016/j.ajo.2021.04.021_bib0001) 2014; 121
10.1016/j.ajo.2021.04.021_bib0049
Roth (10.1016/j.ajo.2021.04.021_bib0061) 1988
Mitchell (10.1016/j.ajo.2021.04.021_bib0102) 1996; 103
Miki (10.1016/j.ajo.2021.04.021_bib0024) 2017; 26
Shen (10.1016/j.ajo.2021.04.021_bib0004) 2008; 49
Lee (10.1016/j.ajo.2021.04.021_bib0099) 2019; 9
Jung (10.1016/j.ajo.2021.04.021_bib0056) 2020; 44
Szegedy (10.1016/j.ajo.2021.04.021_bib0063) 2015
Maetschke (10.1016/j.ajo.2021.04.021_bib0026) 2019; 14
Boland (10.1016/j.ajo.2021.04.021_bib0009) 2012
10.1016/j.ajo.2021.04.021_bib0050
Muhammad (10.1016/j.ajo.2021.04.021_bib0022) 2017; 26
10.1016/j.ajo.2021.04.021_bib0051
Heijl (10.1016/j.ajo.2021.04.021_bib0008) 2002; 120
Hood (10.1016/j.ajo.2021.04.021_bib0010) 2007; 26
Ha (10.1016/j.ajo.2021.04.021_bib0098) 2019; 9
Armaly (10.1016/j.ajo.2021.04.021_bib0084) 1970; 9
Mwanza (10.1016/j.ajo.2021.04.021_bib0021) 2011; 52
Holopigian (10.1016/j.ajo.2021.04.021_bib0092) 1990; 31
Septiarini (10.1016/j.ajo.2021.04.021_bib0013) 2018; 24
Sudlow (10.1016/j.ajo.2021.04.021_bib0031) 2015; 12
Wang (10.1016/j.ajo.2021.04.021_bib0081) 2017; 24
Winkler (10.1016/j.ajo.2021.04.021_bib0028) 2019; 155
Foreman (10.1016/j.ajo.2021.04.021_bib0101) 2017; 7
Susanna (10.1016/j.ajo.2021.04.021_bib0007) 2015; 4
Foot (10.1016/j.ajo.2021.04.021_bib0002) 2017; 31
Asrani (10.1016/j.ajo.2021.04.021_bib0025) 2014; 132
Medeiros (10.1016/j.ajo.2021.04.021_bib0046) 2006; 15
Ryskulova (10.1016/j.ajo.2021.04.021_bib0073) 2008; 98
Badgeley (10.1016/j.ajo.2021.04.021_bib0029) 2019; 2
Chua (10.1016/j.ajo.2021.04.021_bib0079) 2019; 60
Kass (10.1016/j.ajo.2021.04.021_bib0067) 2002; 120
Fry (10.1016/j.ajo.2021.04.021_bib0105) 2017; 186
Chen (10.1016/j.ajo.2021.04.021_bib0045) 2016
Perkins (10.1016/j.ajo.2021.04.021_bib0068) 1973; 57
Gao (10.1016/j.ajo.2021.04.021_bib0076) 2019; 8
Li (10.1016/j.ajo.2021.04.021_bib0041) 2017
Quigley (10.1016/j.ajo.2021.04.021_bib0071) 1994; 112
Olah (10.1016/j.ajo.2021.04.021_bib0065) 2017; 2
Thompson (10.1016/j.ajo.2021.04.021_bib0100) 2020; 138
Foster (10.1016/j.ajo.2021.04.021_bib0005) 2000; 118
Ting (10.1016/j.ajo.2021.04.021_bib0018) 2017; 318
Chestnut (10.1016/j.ajo.2021.04.021_bib0080) 1991; 46
Hart (10.1016/j.ajo.2021.04.021_bib0069) 1979; 97
Kita (10.1016/j.ajo.2021.04.021_bib0089) 2016; 26
Kendell (10.1016/j.ajo.2021.04.021_bib0091) 1995; 36
Abadi (10.1016/j.ajo.2021.04.021_bib0037) 2016
Szegedy (10.1016/j.ajo.2021.04.021_bib0042) 2017
De Fauw (10.1016/j.ajo.2021.04.021_bib0035) 2018; 24
Ko (10.1016/j.ajo.2021.04.021_bib0090) 2017; 124
Shrikumar (10.1016/j.ajo.2021.04.021_bib0066) 2017; 70
Yanagihara (10.1016/j.ajo.2021.04.021_bib0034) 2020; 9
10.1016/j.ajo.2021.04.021_bib0003
Guedes (10.1016/j.ajo.2021.04.021_bib0055) 2011; 4
Varma (10.1016/j.ajo.2021.04.021_bib0074) 2004; 111
Armaly (10.1016/j.ajo.2021.04.021_bib0070) 1980; 98
Liu (10.1016/j.ajo.2021.04.021_bib0077) 2017; 2017
Lee (10.1016/j.ajo.2021.04.021_bib0058) 2017; 12
Lundberg (10.1016/j.ajo.2021.04.021_bib0052) 2020; 2
Ignacio Orlando (10.1016/j.ajo.2021.04.021_bib0016) 2017
Bock (10.1016/j.ajo.2021.04.021_bib0011) 2010; 14
Havet (10.1016/j.ajo.2021.04.021_bib0082) 2020; 183
Liu (10.1016/j.ajo.2021.04.021_bib0019) 2019; 137
10.1016/j.ajo.2021.04.021_bib0012
Dunn (10.1016/j.ajo.2021.04.021_bib0054) 1964; 6
Friedman (10.1016/j.ajo.2021.04.021_bib0075) 2004; 122
Patel (10.1016/j.ajo.2021.04.021_bib0085) 2018; 12
Panda (10.1016/j.ajo.2021.04.021_bib0094) 1992; 33
Bonovas (10.1016/j.ajo.2021.04.021_bib0048) 2004; 118
Unterlauft (10.1016/j.ajo.2021.04.021_bib0087) 2018; 13
Mansberger (10.1016/j.ajo.2021.04.021_bib0023) 2017; 174
Khawaja (10.1016/j.ajo.2021.04.021_bib0086) 2020; 127
Poplin (10.1016/j.ajo.2021.04.021_bib0072) 2018; 2
Choi (10.1016/j.ajo.2021.04.021_bib0096) 2011; 95
Chen (10.1016/j.ajo.2021.04.021_bib0015) 2015; 2015
Phene (10.1016/j.ajo.2021.04.021_bib0017) 2019; 126
Pavia (10.1016/j.ajo.2021.04.021_bib0083) 1986; 41
Ehrlich (10.1016/j.ajo.2021.04.021_bib0047) 2012; 12
Nork (10.1016/j.ajo.2021.04.021_bib0095) 2000; 118
Nayak (10.1016/j.ajo.2021.04.021_bib0014) 2009; 33
Friedman (10.1016/j.ajo.2021.04.021_bib0044) 2001; 29
10.1016/j.ajo.2021.04.021_bib0027
Efron (10.1016/j.ajo.2021.04.021_bib0053) 1986; 1
Odom (10.1016/j.ajo.2021.04.021_bib0093) 1990; 108
Kingma (10.1016/j.ajo.2021.04.021_bib0038) 2014
Cifuentes-Canorea (10.1016/j.ajo.2021.04.021_bib0088) 2018; 13
He (10.1016/j.ajo.2021.04.021_bib0033) 2015
References_xml – reference: Wood M. How sure are we? Two approaches to statistical inference.
– year: 2017
  ident: bib0016
  article-title: Convolutional neural network transfer for automated glaucoma identification
  publication-title: , 101600U; January 26, 2017
– volume: 60
  start-page: 4915
  year: 2019
  end-page: 4923
  ident: bib0079
  article-title: The relationship between ambient atmospheric fine particulate matter (PM2.5) and glaucoma in a large community cohort
  publication-title: Invest Ophthalmol Vis Sci
– volume: 26
  start-page: 688
  year: 2007
  end-page: 710
  ident: bib0010
  article-title: A framework for comparing structural and functional measures of glaucomatous damage
  publication-title: Prog Retin Eye Res
– volume: 118
  start-page: 256
  year: 2004
  end-page: 261
  ident: bib0048
  article-title: Epidemiological association between cigarette smoking and primary open-angle glaucoma: a meta-analysis
  publication-title: Public Health
– volume: 97
  start-page: 1455
  year: 1979
  end-page: 1458
  ident: bib0069
  article-title: Multivariate analysis of the risk of glaucomatous visual field loss
  publication-title: Arch Ophthalmol
– volume: 14
  start-page: 471
  year: 2010
  end-page: 481
  ident: bib0011
  article-title: Glaucoma risk index: automated glaucoma detection from color fundus images
  publication-title: Med Image Anal
– volume: 122
  start-page: 532
  year: 2004
  end-page: 538
  ident: bib0075
  article-title: Prevalence of open-angle glaucoma among adults in the United States
  publication-title: Arch Ophthalmol
– volume: 33
  start-page: 337
  year: 2009
  end-page: 346
  ident: bib0014
  article-title: Automated diagnosis of glaucoma using digital fundus images
  publication-title: J Med Syst
– volume: 112
  start-page: 644
  year: 1994
  end-page: 649
  ident: bib0071
  article-title: Risk factors for the development of glaucomatous visual field loss in ocular hypertension
  publication-title: Arch Ophthalmol
– start-page: 785
  year: 2016
  end-page: 794
  ident: bib0045
  article-title: A scalable tree boosting system
  publication-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16)
– volume: 118
  start-page: 235
  year: 2000
  end-page: 245
  ident: bib0095
  article-title: Swelling and loss of photoreceptors in chronic human and experimental glaucomas
  publication-title: Arch Ophthalmol
– volume: 12
  year: 2015
  ident: bib0031
  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
– volume: 2
  start-page: 158
  year: 2018
  end-page: 164
  ident: bib0072
  article-title: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning
  publication-title: Nat Biomed Eng
– volume: 44
  start-page: 414
  year: 2020
  end-page: 425
  ident: bib0056
  article-title: Metabolic health, obesity, and the risk of developing open-angle glaucoma: metabolically healthy obese patients versus metabolically unhealthy but normal weight patients
  publication-title: Diabetes Metab J
– reference: Carrillo J, Bautista L, Villamizar J, Rueda J, Sanchez M, Rueda D. Glaucoma detection using fundus. 2019. Images of the eye. Paper presented at: 2019 XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA); April 24-26, 2019; Bucaramanga, Colombia. doi: 10.1109/STSIVA.2019.8730250.
– volume: 70
  start-page: 3145
  year: 2017
  end-page: 3153
  ident: bib0066
  article-title: Learning important features through propagating activation differences
  publication-title: Proc Machine Learn Res
– volume: 12
  start-page: 52
  year: 2012
  ident: bib0047
  article-title: Goldmann applanation tonometry compared with corneal-compensated intraocular pressure in the evaluation of primary open-angle Glaucoma
  publication-title: BMC Ophthalmol
– start-page: 1
  year: 2015
  end-page: 9
  ident: bib0063
  article-title: Going deeper with convolutions
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: 266
  start-page: 369
  year: 1991
  end-page: 374
  ident: bib0104
  article-title: Racial variations in the prevalence of primary open-angle glaucoma. The Baltimore Eye Survey
  publication-title: JAMA
– year: 2016
  ident: bib0037
  article-title: TensorFlow: Large-scale machine learning on heterogeneous distributed systems
  publication-title: arXiv
– volume: 155
  start-page: 1135
  year: 2019
  end-page: 1141
  ident: bib0028
  article-title: Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition
  publication-title: JAMA Dermatol
– volume: 9
  start-page: 11
  year: 2020
  ident: bib0034
  article-title: Methodological challenges of deep learning in optical coherence tomography for retinal diseases: a review
  publication-title: Transl Vis Sci Technol
– reference: Glaucoma Research Foundation: Glaucoma Facts and Stats. Accessed December 2019.
– volume: 111
  start-page: 1439
  year: 2004
  end-page: 1448
  ident: bib0074
  article-title: Prevalence of open-angle glaucoma and ocular hypertension in Latinos: the Los Angeles Latino Eye Study
  publication-title: Ophthalmology
– year: April 2012
  ident: bib0009
  article-title: Treatment for Glaucoma: Comparative Effectiveness
– volume: 174
  start-page: 1
  year: 2017
  end-page: 8
  ident: bib0023
  article-title: Automated segmentation errors when using optical coherence tomography to measure retinal nerve fiber layer thickness in glaucoma
  publication-title: Am J Ophthalmol
– reference: Smilkov D, Thorat N, Kim B, Viégas F, Wattenberg M. Smoothgrad: removing noise by adding noise.
– volume: 14
  year: 2019
  ident: bib0026
  article-title: A feature agnostic approach for glaucoma detection in OCT volumes
  publication-title: PLoS One
– volume: 126
  start-page: 1627
  year: 2019
  end-page: 1639
  ident: bib0017
  article-title: Deep learning and glaucoma specialists: the relative importance of optic disc features to predict glaucoma referral in fundus photographs
  publication-title: Ophthalmology
– volume: 127
  start-page: 62
  year: 2020
  end-page: 71
  ident: bib0086
  article-title: Comparison of associations with different macular inner retinal thickness parameters in a large cohort: The UK Biobank
  publication-title: Ophthalmology
– volume: 4
  start-page: 1
  year: 2015
  ident: bib0007
  article-title: Why do people (still) go blind from glaucoma?
  publication-title: Transl Vis Sci Technol
– volume: 7
  start-page: 8757
  year: 2017
  ident: bib0101
  article-title: The validity of self-report of eye diseases in participants with vision loss in the National Eye Health Survey
  publication-title: Sci Rep
– reference: 2017;1703.01365.
– volume: 46
  start-page: 135
  year: 1991
  end-page: 144
  ident: bib0080
  article-title: Pulmonary function and ambient particulate matter: epidemiological evidence from NHANES I
  publication-title: Arch Environ Health
– volume: 137
  start-page: 1353
  year: 2019
  end-page: 1360
  ident: bib0019
  article-title: Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs
  publication-title: JAMA Ophthalmol
– reference: , vol 5304. Berlin: Springer; 2008. https://doi.org/10.1007/978-3-540-88690-7_6
– reference: 2017;1706.03825.
– year: 2017
  ident: bib0041
  article-title: Convolutional neural networks based transfer learning for diabetic retinopathy fundus image classification
  publication-title: Paper presented at: 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI); October 14-16
– volume: 6
  start-page: 241
  year: 1964
  end-page: 252
  ident: bib0054
  article-title: Multiple comparisons using rank sums
  publication-title: Technometrics
– volume: 33
  start-page: 2532
  year: 1992
  end-page: 2536
  ident: bib0094
  article-title: Decreased photoreceptor count in human eyes with secondary angle-closure glaucoma
  publication-title: Invest Ophthalmol Vis Sci
– volume: 125
  start-page: 1199
  year: 2018
  end-page: 1206
  ident: bib0020
  article-title: Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs
  publication-title: Ophthalmology
– volume: 98
  start-page: 454
  year: 2008
  end-page: 461
  ident: bib0073
  article-title: Self-reported age-related eye diseases and visual impairment in the United States: results of the 2002 national health interview survey
  publication-title: Am J Public Health
– volume: 31
  start-page: 771
  year: 2017
  end-page: 775
  ident: bib0002
  article-title: Surveillance of sight loss due to delay in ophthalmic treatment or review: frequency, cause and outcome
  publication-title: Eye (Lond)
– volume: 2
  start-page: 31
  year: 2019
  ident: bib0029
  article-title: Deep learning predicts hip fracture using confounding patient and healthcare variables
  publication-title: NPJ Digit Med
– volume: 8
  start-page: 8
  year: 1999
  end-page: 11
  ident: bib0057
  article-title: Body mass index in glaucoma
  publication-title: J Glaucoma
– volume: 183
  year: 2020
  ident: bib0082
  article-title: Residential exposure to outdoor air pollution and adult lung function, with focus on small airway obstruction
  publication-title: Environ Res
– year: 2019
  ident: bib0032
  article-title: Convolutional networks with dense connectivity
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 31
  start-page: 1863
  year: 1990
  end-page: 1868
  ident: bib0092
  article-title: Electrophysiological and psychophysical flicker sensitivity in patients with primary open-angle glaucoma and ocular hypertension
  publication-title: Invest Ophthalmol Vis Sci
– volume: 4
  start-page: 110
  year: 2011
  end-page: 117
  ident: bib0055
  article-title: Glaucoma and aging
  publication-title: Curr Aging Sci
– start-page: 4765
  year: 2017
  end-page: 4774
  ident: bib0060
  article-title: A unified approach to interpreting model predictions
  publication-title: . Red Hook
– volume: 22
  start-page: 1345
  year: 2009
  end-page: 1359
  ident: bib0039
  article-title: A survey on transfer learning
  publication-title: IEEE Trans Knowledge Data Eng
– volume: 9
  start-page: 19771
  year: 2019
  ident: bib0098
  article-title: Automated quantification of macular ellipsoid zone intensity in glaucoma patients: the method and its comparison with manual quantification
  publication-title: Sci Rep
– year: 1988
  ident: bib0061
  article-title: The Shapley Value: Essays in Honor of LloydS. Shapley
– volume: 118
  start-page: 1105
  year: 2000
  end-page: 1111
  ident: bib0005
  article-title: The prevalence of glaucoma in Chinese residents of Singapore: a cross-sectional population survey of the Tanjong Pagar district
  publication-title: Arch Ophthalmol
– volume: 101
  start-page: 1851
  year: 1994
  end-page: 1855
  ident: bib0103
  article-title: The prevalence of primary open-angle glaucoma in a population-based study in the Netherlands. The Rotterdam Study
  publication-title: Ophthalmology
– volume: 24
  start-page: 53
  year: 2018
  end-page: 60
  ident: bib0013
  article-title: Automatic glaucoma detection method applying a statistical approach to fundus images
  publication-title: Healthc Inform Res
– volume: 24
  start-page: 1342
  year: 2018
  end-page: 1350
  ident: bib0035
  article-title: Clinically applicable deep learning for diagnosis and referral in retinal disease
  publication-title: Nat Med
– volume: 98
  start-page: 2163
  year: 1980
  end-page: 2171
  ident: bib0070
  article-title: Biostatistical analysis of the collaborative glaucoma study. I. Summary report of the risk factors for glaucomatous visual-field defects
  publication-title: Arch Ophthalmol
– volume: 13
  year: 2018
  ident: bib0088
  article-title: Analysis of inner and outer retinal layers using spectral domain optical coherence tomography automated segmentation software in ocular hypertensive and glaucoma patients
  publication-title: PLoS One
– volume: 124
  start-page: 105
  year: 2017
  end-page: 117
  ident: bib0090
  article-title: Associations with retinal pigment epithelium thickness measures in a large cohort: results from the UK Biobank
  publication-title: Ophthalmology
– volume: 15
  start-page: 364
  year: 2006
  end-page: 370
  ident: bib0046
  article-title: Evaluation of the influence of corneal biomechanical properties on intraocular pressure measurements using the ocular response analyzer
  publication-title: J Glaucoma
– volume: 8
  start-page: 10
  year: 2019
  ident: bib0076
  article-title: Polygenic risk score is associated with intraocular pressure and improves glaucoma prediction in the UK Biobank Cohort
  publication-title: Transl Vis Sci Technol
– volume: 14
  start-page: 4696
  year: 2019
  end-page: 4705
  ident: bib0036
  article-title: When does label smoothing help?
  publication-title: Adv Neural Inform Proc Syst
– year: 2017
  ident: bib0042
  article-title: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
  publication-title: AAAI
– volume: 29
  start-page: 1189
  year: 2001
  end-page: 1232
  ident: bib0044
  article-title: Greedy function approximation: a gradient boosting machine
  publication-title: Ann Stat
– reference: UK Biobank. Accessed September 2019.
– volume: 2
  start-page: 56
  year: 2020
  end-page: 67
  ident: bib0052
  article-title: From local explanations to global understanding with explainable AI for trees
  publication-title: Nat Mach Intell
– volume: 3
  start-page: e10
  year: 2018
  ident: bib0064
  article-title: The building blocks of interpretability
  publication-title: Distill
– volume: 41
  start-page: 301
  year: 1986
  end-page: 305
  ident: bib0083
  article-title: Effect of selective and non-selective beta blockade on pulmonary function and tracheobronchial mucociliary clearance in healthy subjects
  publication-title: Thorax
– start-page: 1026
  year: 2015
  end-page: 1034
  ident: bib0033
  article-title: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification
  publication-title: Proceedings of the IEEE International Conference on Computer Vision; December 7-13, 2015
– volume: 26
  start-page: 118
  year: 2016
  end-page: 123
  ident: bib0089
  article-title: The clinical utility of measuring the macular outer retinal thickness in patients with glaucoma
  publication-title: Eur J Ophthalmol
– volume: 138
  start-page: 333
  year: 2020
  end-page: 339
  ident: bib0100
  article-title: Assessment of a segmentation-free deep learning algorithm for diagnosing glaucoma from optical coherence tomography scans
  publication-title: JAMA Ophthalmol
– reference: Ahmed A, Yu K, Xu W, Gong Y, Xing E. Training hierarchical feed-forward visual recognition models using transfer learning from pseudo-tasks. In: Forsyth D, Torr P, Zisserman A, eds.
– volume: 52
  start-page: 8323
  year: 2011
  end-page: 8329
  ident: bib0021
  article-title: Macular ganglion cell-inner plexiform layer: automated detection and thickness reproducibility with spectral domain-optical coherence tomography in glaucoma
  publication-title: Invest Ophthalmol Vis Sci
– year: 2014
  ident: bib0038
  article-title: A method for stochastic optimization
  publication-title: arXiv
– volume: 121
  start-page: 1220
  year: 2014
  end-page: 1228
  ident: bib0059
  article-title: Relation of smoking, drinking, and physical activity to changes in vision over a 20-year period: the Beaver Dam Eye Study
  publication-title: Ophthalmology
– volume: 39
  start-page: 623
  year: 2011
  end-page: 632
  ident: bib0006
  article-title: Economic impact of primary open-angle glaucoma in Australia
  publication-title: Clin Exp Ophthalmol
– volume: 9
  start-page: 467
  year: 2014
  end-page: 474
  ident: bib0062
  article-title: Gaps in glaucoma care: A systematic review of monoscopic disc photos to screen for glaucoma
  publication-title: Expert Rev Ophthalmol
– volume: 192
  start-page: 1
  year: 2018
  end-page: 9
  ident: bib0097
  article-title: Ellipsoid zone change according to glaucoma stage advancement
  publication-title: Am J Ophthalmol
– volume: 103
  start-page: 1661
  year: 1996
  end-page: 1669
  ident: bib0102
  article-title: Prevalence of open-angle glaucoma in Australia. The Blue Mountains Eye Study
  publication-title: Ophthalmology
– volume: 9
  start-page: 5694
  year: 2019
  ident: bib0099
  article-title: Generating retinal flow maps from structural optical coherence tomography with artificial intelligence
  publication-title: Sci Rep
– volume: 13
  year: 2018
  ident: bib0087
  article-title: Analyzing the impact of glaucoma on the macular architecture using spectral-domain optical coherence tomography
  publication-title: PLoS One
– volume: 121
  start-page: 2081
  year: 2014
  end-page: 2090
  ident: bib0001
  article-title: Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis
  publication-title: Ophthalmology
– volume: 2017
  year: 2017
  ident: bib0077
  article-title: The association between adiposity and the risk of glaucoma: a meta-analysis
  publication-title: J Ophthalmol
– volume: 2015
  start-page: 715
  year: 2015
  end-page: 718
  ident: bib0015
  article-title: Glaucoma detection based on deep convolutional neural network
  publication-title: Annu Int Conf IEEE Eng Med Biol Soc
– volume: 26
  start-page: 1086
  year: 2017
  end-page: 1094
  ident: bib0022
  article-title: Hybrid deep learning on single wide-field optical coherence tomography scans accurately classifies glaucoma suspects
  publication-title: J Glaucoma
– reference: 2018;1803.06214.
– volume: 36
  start-page: 200
  year: 1995
  end-page: 205
  ident: bib0091
  article-title: Primary open-angle glaucoma is not associated with photoreceptor loss
  publication-title: Invest Ophthalmol Vis Sci
– volume: 27
  start-page: 239
  year: 2018
  end-page: 245
  ident: bib0078
  article-title: The association between body mass index and open-angle glaucoma in a South Korean population-based sample
  publication-title: J Glaucoma
– volume: 108
  start-page: 222
  year: 1990
  end-page: 227
  ident: bib0093
  article-title: Visual function deficits in glaucoma. Electroretinogram pattern and luminance nonlinearities
  publication-title: Arch Ophthalmol
– volume: 2
  start-page: e7
  year: 2017
  ident: bib0065
  article-title: Feature visualization
  publication-title: Distill
– volume: 9
  start-page: 425
  year: 1970
  end-page: 429
  ident: bib0084
  article-title: Optic cup in normal and glaucomatous eyes
  publication-title: Invest Ophthalmol
– volume: 49
  start-page: 3846
  year: 2008
  end-page: 3851
  ident: bib0004
  article-title: The prevalence and types of glaucoma in Malay people: the Singapore Malay eye study
  publication-title: Invest Ophthalmol Vis Sci
– volume: 26
  start-page: 995
  year: 2017
  end-page: 1000
  ident: bib0024
  article-title: Prevalence and associated factors of segmentation errors in the peripapillary retinal nerve fiber layer and macular ganglion cell complex in spectral-domain optical coherence tomography images
  publication-title: J Glaucoma
– volume: 120
  start-page: 1268
  year: 2002
  end-page: 1279
  ident: bib0008
  article-title: Reduction of intraocular pressure and glaucoma progression: results from the Early Manifest Glaucoma Trial
  publication-title: Arch Ophthalmol
– volume: 95
  start-page: 131
  year: 2011
  end-page: 141
  ident: bib0096
  article-title: Evidence of outer retinal changes in glaucoma patients as revealed by ultrahigh-resolution in vivo retinal imaging
  publication-title: Br J Ophthalmol
– volume: 186
  start-page: 1026
  year: 2017
  end-page: 1034
  ident: bib0105
  article-title: Comparison of sociodemographic and health-related characteristics of UK Biobank participants with those of the general population
  publication-title: Am J Epidemiol
– volume: 120
  start-page: 701
  year: 2002
  end-page: 830
  ident: bib0067
  article-title: The Ocular Hypertension Treatment Study: a randomized trial determines that topical ocular hypotensive medication delays or prevents the onset of primary open-angle glaucoma
  publication-title: Arch Ophthalmol
– volume: 57
  start-page: 179
  year: 1973
  end-page: 185
  ident: bib0068
  article-title: The Bedford glaucoma survey. I. Long-term follow-up of borderline cases
  publication-title: Br J Ophthalmol
– reference: ImageNet. Accessed XXXX.
– volume: 24
  start-page: 22442
  year: 2017
  end-page: 22449
  ident: bib0081
  article-title: Geographic variation in Chinese children's forced vital capacity and its association with long-term exposure to local PM
  publication-title: Environ Sci Pollut Res Int
– volume: 12
  start-page: 827
  year: 2018
  end-page: 832
  ident: bib0085
  article-title: Optical coherence tomography retinal nerve fiber layer analysis in eyes with long axial lengths
  publication-title: Clin Ophthalmol
– reference: .
– volume: 1
  start-page: 54
  year: 1986
  end-page: 75
  ident: bib0053
  article-title: Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy
  publication-title: Stat Sci
– reference: Sundararajan M, Taly A, Yan Q. Axiomatic attribution for deep networks.
– volume: 318
  start-page: 2211
  year: 2017
  end-page: 2223
  ident: bib0018
  article-title: Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes
  publication-title: JAMA
– volume: 116
  start-page: 22071
  year: 2019
  end-page: 22080
  ident: bib0030
  article-title: Definitions, methods, and applications in interpretable machine learning
  publication-title: Proc Natl Acad Sci U S A
– volume: 132
  start-page: 396
  year: 2014
  end-page: 402
  ident: bib0025
  article-title: Artifacts in spectral-domain optical coherence tomography measurements in glaucoma
  publication-title: JAMA Ophthalmol
– volume: 12
  year: 2017
  ident: bib0058
  article-title: Relationship between anthropometric parameters and open angle glaucoma: The Korea National Health and Nutrition Examination Survey
  publication-title: PLoS One
– volume: 2
  start-page: 56
  issue: 1
  year: 2020
  ident: 10.1016/j.ajo.2021.04.021_bib0052
  article-title: From local explanations to global understanding with explainable AI for trees
  publication-title: Nat Mach Intell
  doi: 10.1038/s42256-019-0138-9
– start-page: 1
  year: 2015
  ident: 10.1016/j.ajo.2021.04.021_bib0063
  article-title: Going deeper with convolutions
– volume: 137
  start-page: 1353
  issue: 12
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0019
  article-title: Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs
  publication-title: JAMA Ophthalmol
  doi: 10.1001/jamaophthalmol.2019.3501
– ident: 10.1016/j.ajo.2021.04.021_bib0027
– volume: 44
  start-page: 414
  issue: 3
  year: 2020
  ident: 10.1016/j.ajo.2021.04.021_bib0056
  article-title: Metabolic health, obesity, and the risk of developing open-angle glaucoma: metabolically healthy obese patients versus metabolically unhealthy but normal weight patients
  publication-title: Diabetes Metab J
  doi: 10.4093/dmj.2019.0048
– volume: 13
  issue: 4
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0088
  article-title: Analysis of inner and outer retinal layers using spectral domain optical coherence tomography automated segmentation software in ocular hypertensive and glaucoma patients
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0196112
– volume: 15
  start-page: 364
  issue: 5
  year: 2006
  ident: 10.1016/j.ajo.2021.04.021_bib0046
  article-title: Evaluation of the influence of corneal biomechanical properties on intraocular pressure measurements using the ocular response analyzer
  publication-title: J Glaucoma
  doi: 10.1097/01.ijg.0000212268.42606.97
– volume: 121
  start-page: 2081
  issue: 11
  year: 2014
  ident: 10.1016/j.ajo.2021.04.021_bib0001
  article-title: Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2014.05.013
– volume: 132
  start-page: 396
  issue: 4
  year: 2014
  ident: 10.1016/j.ajo.2021.04.021_bib0025
  article-title: Artifacts in spectral-domain optical coherence tomography measurements in glaucoma
  publication-title: JAMA Ophthalmol
  doi: 10.1001/jamaophthalmol.2013.7974
– volume: 6
  start-page: 241
  issue: 3
  year: 1964
  ident: 10.1016/j.ajo.2021.04.021_bib0054
  article-title: Multiple comparisons using rank sums
  publication-title: Technometrics
  doi: 10.1080/00401706.1964.10490181
– volume: 155
  start-page: 1135
  issue: 10
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0028
  article-title: Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition
  publication-title: JAMA Dermatol
  doi: 10.1001/jamadermatol.2019.1735
– volume: 39
  start-page: 623
  issue: 7
  year: 2011
  ident: 10.1016/j.ajo.2021.04.021_bib0006
  article-title: Economic impact of primary open-angle glaucoma in Australia
  publication-title: Clin Exp Ophthalmol
  doi: 10.1111/j.1442-9071.2011.02530.x
– volume: 12
  issue: 3
  year: 2015
  ident: 10.1016/j.ajo.2021.04.021_bib0031
  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
– volume: 120
  start-page: 701
  issue: 6
  year: 2002
  ident: 10.1016/j.ajo.2021.04.021_bib0067
  article-title: The Ocular Hypertension Treatment Study: a randomized trial determines that topical ocular hypotensive medication delays or prevents the onset of primary open-angle glaucoma
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.120.6.701
– volume: 126
  start-page: 1627
  issue: 12
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0017
  article-title: Deep learning and glaucoma specialists: the relative importance of optic disc features to predict glaucoma referral in fundus photographs
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2019.07.024
– start-page: 785
  year: 2016
  ident: 10.1016/j.ajo.2021.04.021_bib0045
  article-title: A scalable tree boosting system
– volume: 120
  start-page: 1268
  issue: 10
  year: 2002
  ident: 10.1016/j.ajo.2021.04.021_bib0008
  article-title: Reduction of intraocular pressure and glaucoma progression: results from the Early Manifest Glaucoma Trial
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.120.10.1268
– volume: 31
  start-page: 771
  issue: 5
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0002
  article-title: Surveillance of sight loss due to delay in ophthalmic treatment or review: frequency, cause and outcome
  publication-title: Eye (Lond)
  doi: 10.1038/eye.2017.1
– ident: 10.1016/j.ajo.2021.04.021_bib0051
– volume: 111
  start-page: 1439
  issue: 8
  year: 2004
  ident: 10.1016/j.ajo.2021.04.021_bib0074
  article-title: Prevalence of open-angle glaucoma and ocular hypertension in Latinos: the Los Angeles Latino Eye Study
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2004.01.025
– volume: 125
  start-page: 1199
  issue: 8
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0020
  article-title: Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2018.01.023
– year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0041
  article-title: Convolutional neural networks based transfer learning for diabetic retinopathy fundus image classification
– volume: 14
  start-page: 4696
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0036
  article-title: When does label smoothing help?
  publication-title: Adv Neural Inform Proc Syst
– volume: 118
  start-page: 1105
  issue: 8
  year: 2000
  ident: 10.1016/j.ajo.2021.04.021_bib0005
  article-title: The prevalence of glaucoma in Chinese residents of Singapore: a cross-sectional population survey of the Tanjong Pagar district
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.118.8.1105
– volume: 127
  start-page: 62
  issue: 1
  year: 2020
  ident: 10.1016/j.ajo.2021.04.021_bib0086
  article-title: Comparison of associations with different macular inner retinal thickness parameters in a large cohort: The UK Biobank
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2019.08.015
– volume: 14
  start-page: 471
  issue: 3
  year: 2010
  ident: 10.1016/j.ajo.2021.04.021_bib0011
  article-title: Glaucoma risk index: automated glaucoma detection from color fundus images
  publication-title: Med Image Anal
  doi: 10.1016/j.media.2009.12.006
– volume: 4
  start-page: 1
  issue: 2
  year: 2015
  ident: 10.1016/j.ajo.2021.04.021_bib0007
  article-title: Why do people (still) go blind from glaucoma?
  publication-title: Transl Vis Sci Technol
  doi: 10.1167/tvst.4.2.1
– year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0042
  article-title: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
  publication-title: AAAI
  doi: 10.1609/aaai.v31i1.11231
– volume: 121
  start-page: 1220
  issue: 6
  year: 2014
  ident: 10.1016/j.ajo.2021.04.021_bib0059
  article-title: Relation of smoking, drinking, and physical activity to changes in vision over a 20-year period: the Beaver Dam Eye Study
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2014.01.003
– volume: 33
  start-page: 337
  issue: 5
  year: 2009
  ident: 10.1016/j.ajo.2021.04.021_bib0014
  article-title: Automated diagnosis of glaucoma using digital fundus images
  publication-title: J Med Syst
  doi: 10.1007/s10916-008-9195-z
– volume: 116
  start-page: 22071
  issue: 44
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0030
  article-title: Definitions, methods, and applications in interpretable machine learning
  publication-title: Proc Natl Acad Sci U S A
  doi: 10.1073/pnas.1900654116
– start-page: 1026
  year: 2015
  ident: 10.1016/j.ajo.2021.04.021_bib0033
  article-title: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification
– volume: 1
  start-page: 54
  issue: 1
  year: 1986
  ident: 10.1016/j.ajo.2021.04.021_bib0053
  article-title: Bootstrap methods for standard errors, confidence intervals, and other measures of statistical accuracy
  publication-title: Stat Sci
– volume: 98
  start-page: 454
  issue: 3
  year: 2008
  ident: 10.1016/j.ajo.2021.04.021_bib0073
  article-title: Self-reported age-related eye diseases and visual impairment in the United States: results of the 2002 national health interview survey
  publication-title: Am J Public Health
  doi: 10.2105/AJPH.2006.098202
– volume: 124
  start-page: 105
  issue: 1
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0090
  article-title: Associations with retinal pigment epithelium thickness measures in a large cohort: results from the UK Biobank
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2016.07.033
– volume: 118
  start-page: 256
  issue: 4
  year: 2004
  ident: 10.1016/j.ajo.2021.04.021_bib0048
  article-title: Epidemiological association between cigarette smoking and primary open-angle glaucoma: a meta-analysis
  publication-title: Public Health
  doi: 10.1016/j.puhe.2003.09.009
– volume: 26
  start-page: 995
  issue: 11
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0024
  article-title: Prevalence and associated factors of segmentation errors in the peripapillary retinal nerve fiber layer and macular ganglion cell complex in spectral-domain optical coherence tomography images
  publication-title: J Glaucoma
  doi: 10.1097/IJG.0000000000000771
– volume: 95
  start-page: 131
  issue: 1
  year: 2011
  ident: 10.1016/j.ajo.2021.04.021_bib0096
  article-title: Evidence of outer retinal changes in glaucoma patients as revealed by ultrahigh-resolution in vivo retinal imaging
  publication-title: Br J Ophthalmol
  doi: 10.1136/bjo.2010.183756
– ident: 10.1016/j.ajo.2021.04.021_bib0040
  doi: 10.1007/978-3-540-88690-7_6
– volume: 3
  start-page: e10
  issue: 3
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0064
  article-title: The building blocks of interpretability
  publication-title: Distill
  doi: 10.23915/distill.00010
– volume: 12
  start-page: 52
  year: 2012
  ident: 10.1016/j.ajo.2021.04.021_bib0047
  article-title: Goldmann applanation tonometry compared with corneal-compensated intraocular pressure in the evaluation of primary open-angle Glaucoma
  publication-title: BMC Ophthalmol
  doi: 10.1186/1471-2415-12-52
– volume: 4
  start-page: 110
  issue: 2
  year: 2011
  ident: 10.1016/j.ajo.2021.04.021_bib0055
  article-title: Glaucoma and aging
  publication-title: Curr Aging Sci
  doi: 10.2174/1874609811104020110
– ident: 10.1016/j.ajo.2021.04.021_bib0050
– year: 2016
  ident: 10.1016/j.ajo.2021.04.021_bib0037
  article-title: TensorFlow: Large-scale machine learning on heterogeneous distributed systems
  publication-title: arXiv
– volume: 26
  start-page: 1086
  issue: 12
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0022
  article-title: Hybrid deep learning on single wide-field optical coherence tomography scans accurately classifies glaucoma suspects
  publication-title: J Glaucoma
  doi: 10.1097/IJG.0000000000000765
– volume: 14
  issue: 7
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0026
  article-title: A feature agnostic approach for glaucoma detection in OCT volumes
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0219126
– volume: 70
  start-page: 3145
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0066
  article-title: Learning important features through propagating activation differences
  publication-title: Proc Machine Learn Res
– volume: 122
  start-page: 532
  issue: 4
  year: 2004
  ident: 10.1016/j.ajo.2021.04.021_bib0075
  article-title: Prevalence of open-angle glaucoma among adults in the United States
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.122.4.532
– volume: 2
  start-page: 31
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0029
  article-title: Deep learning predicts hip fracture using confounding patient and healthcare variables
  publication-title: NPJ Digit Med
  doi: 10.1038/s41746-019-0105-1
– volume: 97
  start-page: 1455
  issue: 8
  year: 1979
  ident: 10.1016/j.ajo.2021.04.021_bib0069
  article-title: Multivariate analysis of the risk of glaucomatous visual field loss
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.1979.01020020117005
– volume: 138
  start-page: 333
  issue: 4
  year: 2020
  ident: 10.1016/j.ajo.2021.04.021_bib0100
  article-title: Assessment of a segmentation-free deep learning algorithm for diagnosing glaucoma from optical coherence tomography scans
  publication-title: JAMA Ophthalmol
  doi: 10.1001/jamaophthalmol.2019.5983
– volume: 2015
  start-page: 715
  year: 2015
  ident: 10.1016/j.ajo.2021.04.021_bib0015
  article-title: Glaucoma detection based on deep convolutional neural network
  publication-title: Annu Int Conf IEEE Eng Med Biol Soc
– volume: 2017
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0077
  article-title: The association between adiposity and the risk of glaucoma: a meta-analysis
  publication-title: J Ophthalmol
  doi: 10.1155/2017/9787450
– volume: 49
  start-page: 3846
  issue: 9
  year: 2008
  ident: 10.1016/j.ajo.2021.04.021_bib0004
  article-title: The prevalence and types of glaucoma in Malay people: the Singapore Malay eye study
  publication-title: Invest Ophthalmol Vis Sci
  doi: 10.1167/iovs.08-1759
– volume: 26
  start-page: 118
  issue: 2
  year: 2016
  ident: 10.1016/j.ajo.2021.04.021_bib0089
  article-title: The clinical utility of measuring the macular outer retinal thickness in patients with glaucoma
  publication-title: Eur J Ophthalmol
  doi: 10.5301/ejo.5000678
– volume: 29
  start-page: 1189
  year: 2001
  ident: 10.1016/j.ajo.2021.04.021_bib0044
  article-title: Greedy function approximation: a gradient boosting machine
  publication-title: Ann Stat
  doi: 10.1214/aos/1013203451
– volume: 8
  start-page: 8
  issue: 1
  year: 1999
  ident: 10.1016/j.ajo.2021.04.021_bib0057
  article-title: Body mass index in glaucoma
  publication-title: J Glaucoma
  doi: 10.1097/00061198-199902000-00004
– year: 1988
  ident: 10.1016/j.ajo.2021.04.021_bib0061
– volume: 318
  start-page: 2211
  issue: 22
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0018
  article-title: Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes
  publication-title: JAMA
  doi: 10.1001/jama.2017.18152
– ident: 10.1016/j.ajo.2021.04.021_bib0012
  doi: 10.1109/STSIVA.2019.8730250
– volume: 52
  start-page: 8323
  issue: 11
  year: 2011
  ident: 10.1016/j.ajo.2021.04.021_bib0021
  article-title: Macular ganglion cell-inner plexiform layer: automated detection and thickness reproducibility with spectral domain-optical coherence tomography in glaucoma
  publication-title: Invest Ophthalmol Vis Sci
  doi: 10.1167/iovs.11-7962
– volume: 27
  start-page: 239
  issue: 3
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0078
  article-title: The association between body mass index and open-angle glaucoma in a South Korean population-based sample
  publication-title: J Glaucoma
  doi: 10.1097/IJG.0000000000000867
– volume: 41
  start-page: 301
  issue: 4
  year: 1986
  ident: 10.1016/j.ajo.2021.04.021_bib0083
  article-title: Effect of selective and non-selective beta blockade on pulmonary function and tracheobronchial mucociliary clearance in healthy subjects
  publication-title: Thorax
  doi: 10.1136/thx.41.4.301
– year: 2014
  ident: 10.1016/j.ajo.2021.04.021_bib0038
  article-title: A method for stochastic optimization
  publication-title: arXiv
– volume: 174
  start-page: 1
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0023
  article-title: Automated segmentation errors when using optical coherence tomography to measure retinal nerve fiber layer thickness in glaucoma
  publication-title: Am J Ophthalmol
  doi: 10.1016/j.ajo.2016.10.020
– volume: 112
  start-page: 644
  issue: 5
  year: 1994
  ident: 10.1016/j.ajo.2021.04.021_bib0071
  article-title: Risk factors for the development of glaucomatous visual field loss in ocular hypertension
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.1994.01090170088028
– volume: 8
  start-page: 10
  issue: 2
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0076
  article-title: Polygenic risk score is associated with intraocular pressure and improves glaucoma prediction in the UK Biobank Cohort
  publication-title: Transl Vis Sci Technol
  doi: 10.1167/tvst.8.2.10
– volume: 7
  start-page: 8757
  issue: 1
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0101
  article-title: The validity of self-report of eye diseases in participants with vision loss in the National Eye Health Survey
  publication-title: Sci Rep
  doi: 10.1038/s41598-017-09421-9
– volume: 24
  start-page: 22442
  issue: 28
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0081
  article-title: Geographic variation in Chinese children's forced vital capacity and its association with long-term exposure to local PM10: a national cross-sectional study
  publication-title: Environ Sci Pollut Res Int
  doi: 10.1007/s11356-017-9812-9
– ident: 10.1016/j.ajo.2021.04.021_bib0043
– volume: 9
  start-page: 425
  issue: 6
  year: 1970
  ident: 10.1016/j.ajo.2021.04.021_bib0084
  article-title: Optic cup in normal and glaucomatous eyes
  publication-title: Invest Ophthalmol
– volume: 2
  start-page: 158
  issue: 3
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0072
  article-title: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning
  publication-title: Nat Biomed Eng
  doi: 10.1038/s41551-018-0195-0
– volume: 9
  start-page: 19771
  issue: 1
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0098
  article-title: Automated quantification of macular ellipsoid zone intensity in glaucoma patients: the method and its comparison with manual quantification
  publication-title: Sci Rep
  doi: 10.1038/s41598-019-56337-7
– volume: 12
  start-page: 827
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0085
  article-title: Optical coherence tomography retinal nerve fiber layer analysis in eyes with long axial lengths
  publication-title: Clin Ophthalmol
  doi: 10.2147/OPTH.S162023
– ident: 10.1016/j.ajo.2021.04.021_bib0049
– volume: 22
  start-page: 1345
  issue: 10
  year: 2009
  ident: 10.1016/j.ajo.2021.04.021_bib0039
  article-title: A survey on transfer learning
  publication-title: IEEE Trans Knowledge Data Eng
  doi: 10.1109/TKDE.2009.191
– ident: 10.1016/j.ajo.2021.04.021_bib0003
– year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0016
  article-title: Convolutional neural network transfer for automated glaucoma identification
– volume: 31
  start-page: 1863
  issue: 9
  year: 1990
  ident: 10.1016/j.ajo.2021.04.021_bib0092
  article-title: Electrophysiological and psychophysical flicker sensitivity in patients with primary open-angle glaucoma and ocular hypertension
  publication-title: Invest Ophthalmol Vis Sci
– year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0032
  article-title: Convolutional networks with dense connectivity
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 2
  start-page: e7
  issue: 11
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0065
  article-title: Feature visualization
  publication-title: Distill
  doi: 10.23915/distill.00007
– volume: 57
  start-page: 179
  issue: 3
  year: 1973
  ident: 10.1016/j.ajo.2021.04.021_bib0068
  article-title: The Bedford glaucoma survey. I. Long-term follow-up of borderline cases
  publication-title: Br J Ophthalmol
  doi: 10.1136/bjo.57.3.179
– volume: 183
  year: 2020
  ident: 10.1016/j.ajo.2021.04.021_bib0082
  article-title: Residential exposure to outdoor air pollution and adult lung function, with focus on small airway obstruction
  publication-title: Environ Res
  doi: 10.1016/j.envres.2020.109161
– volume: 13
  issue: 12
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0087
  article-title: Analyzing the impact of glaucoma on the macular architecture using spectral-domain optical coherence tomography
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0209610
– volume: 9
  start-page: 11
  issue: 2
  year: 2020
  ident: 10.1016/j.ajo.2021.04.021_bib0034
  article-title: Methodological challenges of deep learning in optical coherence tomography for retinal diseases: a review
  publication-title: Transl Vis Sci Technol
  doi: 10.1167/tvst.9.2.11
– volume: 12
  issue: 5
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0058
  article-title: Relationship between anthropometric parameters and open angle glaucoma: The Korea National Health and Nutrition Examination Survey
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0176894
– volume: 46
  start-page: 135
  issue: 3
  year: 1991
  ident: 10.1016/j.ajo.2021.04.021_bib0080
  article-title: Pulmonary function and ambient particulate matter: epidemiological evidence from NHANES I
  publication-title: Arch Environ Health
  doi: 10.1080/00039896.1991.9937440
– volume: 192
  start-page: 1
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0097
  article-title: Ellipsoid zone change according to glaucoma stage advancement
  publication-title: Am J Ophthalmol
  doi: 10.1016/j.ajo.2018.04.025
– volume: 33
  start-page: 2532
  issue: 8
  year: 1992
  ident: 10.1016/j.ajo.2021.04.021_bib0094
  article-title: Decreased photoreceptor count in human eyes with secondary angle-closure glaucoma
  publication-title: Invest Ophthalmol Vis Sci
– year: 2012
  ident: 10.1016/j.ajo.2021.04.021_bib0009
– volume: 101
  start-page: 1851
  issue: 11
  year: 1994
  ident: 10.1016/j.ajo.2021.04.021_bib0103
  article-title: The prevalence of primary open-angle glaucoma in a population-based study in the Netherlands. The Rotterdam Study
  publication-title: Ophthalmology
  doi: 10.1016/S0161-6420(94)31090-6
– volume: 118
  start-page: 235
  issue: 2
  year: 2000
  ident: 10.1016/j.ajo.2021.04.021_bib0095
  article-title: Swelling and loss of photoreceptors in chronic human and experimental glaucomas
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.118.2.235
– volume: 266
  start-page: 369
  issue: 3
  year: 1991
  ident: 10.1016/j.ajo.2021.04.021_bib0104
  article-title: Racial variations in the prevalence of primary open-angle glaucoma. The Baltimore Eye Survey
  publication-title: JAMA
  doi: 10.1001/jama.1991.03470030069026
– volume: 36
  start-page: 200
  issue: 1
  year: 1995
  ident: 10.1016/j.ajo.2021.04.021_bib0091
  article-title: Primary open-angle glaucoma is not associated with photoreceptor loss
  publication-title: Invest Ophthalmol Vis Sci
– volume: 9
  start-page: 467
  issue: 6
  year: 2014
  ident: 10.1016/j.ajo.2021.04.021_bib0062
  article-title: Gaps in glaucoma care: A systematic review of monoscopic disc photos to screen for glaucoma
  publication-title: Expert Rev Ophthalmol
  doi: 10.1586/17469899.2014.967218
– volume: 108
  start-page: 222
  issue: 2
  year: 1990
  ident: 10.1016/j.ajo.2021.04.021_bib0093
  article-title: Visual function deficits in glaucoma. Electroretinogram pattern and luminance nonlinearities
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.1990.01070040074034
– volume: 98
  start-page: 2163
  issue: 12
  year: 1980
  ident: 10.1016/j.ajo.2021.04.021_bib0070
  article-title: Biostatistical analysis of the collaborative glaucoma study. I. Summary report of the risk factors for glaucomatous visual-field defects
  publication-title: Arch Ophthalmol
  doi: 10.1001/archopht.1980.01020041015002
– volume: 26
  start-page: 688
  issue: 6
  year: 2007
  ident: 10.1016/j.ajo.2021.04.021_bib0010
  article-title: A framework for comparing structural and functional measures of glaucomatous damage
  publication-title: Prog Retin Eye Res
  doi: 10.1016/j.preteyeres.2007.08.001
– volume: 24
  start-page: 1342
  issue: 9
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0035
  article-title: Clinically applicable deep learning for diagnosis and referral in retinal disease
  publication-title: Nat Med
  doi: 10.1038/s41591-018-0107-6
– start-page: 4765
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0060
  article-title: A unified approach to interpreting model predictions
– volume: 60
  start-page: 4915
  issue: 14
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0079
  article-title: The relationship between ambient atmospheric fine particulate matter (PM2.5) and glaucoma in a large community cohort
  publication-title: Invest Ophthalmol Vis Sci
  doi: 10.1167/iovs.19-28346
– volume: 186
  start-page: 1026
  issue: 9
  year: 2017
  ident: 10.1016/j.ajo.2021.04.021_bib0105
  article-title: Comparison of sociodemographic and health-related characteristics of UK Biobank participants with those of the general population
  publication-title: Am J Epidemiol
  doi: 10.1093/aje/kwx246
– volume: 9
  start-page: 5694
  issue: 1
  year: 2019
  ident: 10.1016/j.ajo.2021.04.021_bib0099
  article-title: Generating retinal flow maps from structural optical coherence tomography with artificial intelligence
  publication-title: Sci Rep
  doi: 10.1038/s41598-019-42042-y
– volume: 24
  start-page: 53
  issue: 1
  year: 2018
  ident: 10.1016/j.ajo.2021.04.021_bib0013
  article-title: Automatic glaucoma detection method applying a statistical approach to fundus images
  publication-title: Healthc Inform Res
  doi: 10.4258/hir.2018.24.1.53
– volume: 103
  start-page: 1661
  issue: 10
  year: 1996
  ident: 10.1016/j.ajo.2021.04.021_bib0102
  article-title: Prevalence of open-angle glaucoma in Australia. The Blue Mountains Eye Study
  publication-title: Ophthalmology
  doi: 10.1016/S0161-6420(96)30449-1
SSID ssj0006747
Score 2.5775769
Snippet To develop a multimodal model to automate glaucoma detection Development of a machine-learning glaucoma detection model We selected a study cohort from the UK...
To develop a multimodal model to automate glaucoma detection DESIGN: Development of a machine-learning glaucoma detection model METHODS: We selected a study...
PurposeTo develop a multimodal model to automate glaucoma detectionDesignDevelopment of a machine-learning glaucoma detection modelMethodsWe selected a study...
SourceID unpaywall
proquest
pubmed
crossref
elsevier
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 154
SubjectTerms Asymptomatic
Biobanks
Cataracts
Datasets
Diabetes
Diabetic retinopathy
Glaucoma
Glaucoma - diagnosis
Human subjects
Humans
Intraocular Pressure
Machine Learning
Macular degeneration
Optic Disk
Questionnaires
Tomography, Optical Coherence
SummonAdditionalLinks – databaseName: ScienceDirect (Elsevier)
  dbid: .~1
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELaqHngcEG8CBRmJEyjU9jqb-Fi1lIK0HBAVvVl2PIat0mRFEyEu_HbGjpOCEK3EyYrjkTKe8cwXzcOEvHCV9BZYiBku6lwKKHLlmMp9zcEDqApiK6XVh-XRsXx_Upxskf2pFiakVSbbP9r0aK3TzG7azd3Neh1qfBn6KiVF6CIqYsGvlGW4xeD1z4s0j2UpywkCh9VTZDPmeJnTUP8neOx2Kvi_fNPf2PMmuT60G_Pju2ma3_zR4W1yKwFJujd-6x2yBe1dcm2VQuX3yLA39B3CUXD0APqYcNXSztO3jRmQWUM_r_uv9CLn0DZAVzGzEmhquvqFxoQCmnqHNvTA9Iaa1tFYtnvWOZz7GGqmcXx3hpbp_D45Pnzzaf8oT3cs5LUsZZ_XzopaWI_otTJBbpzVqiy4UcpZ6xUXzlgP3C59Kd3Cg2W-sOBYXckFIBZ4QLbbroVHhLLKGUSLlUMZIww0ihtXucJ7B7x0TGaETbur69SAPNyD0egp0-xUo0B0EIhmUuOQkZczyWbsvnHZYjGJTE9lpWgINfqGy4jkTPSH3l1FtjPphE6H_lzjn6RCBFepIiPP59d4XEMMxrTQDWGNCE3nVCky8nDUpZmzBapngQAqI69m5bqa7cf_x8ETciM8jWWVO2S7_zbAU8RXvX0WD9Av0p8iyQ
  priority: 102
  providerName: Elsevier
Title Automated Detection of Glaucoma With Interpretable Machine Learning Using Clinical Data and Multimodal Retinal Images
URI https://www.clinicalkey.com/#!/content/1-s2.0-S0002939421002208
https://dx.doi.org/10.1016/j.ajo.2021.04.021
https://www.ncbi.nlm.nih.gov/pubmed/33945818
https://www.proquest.com/docview/2599066895
https://www.proquest.com/docview/2522393972
https://www.ncbi.nlm.nih.gov/pmc/articles/8560651
UnpaywallVersion submittedVersion
Volume 231
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier)
  customDbUrl:
  eissn: 1879-1891
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0006747
  issn: 1879-1891
  databaseCode: GBLVA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Complete Freedom Collection
  customDbUrl:
  eissn: 1879-1891
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0006747
  issn: 1879-1891
  databaseCode: ACRLP
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals [SCFCJ]
  customDbUrl:
  eissn: 1879-1891
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0006747
  issn: 1879-1891
  databaseCode: AIKHN
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: ScienceDirect (Elsevier)
  customDbUrl:
  eissn: 1879-1891
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0006747
  issn: 1879-1891
  databaseCode: .~1
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  customDbUrl:
  mediaType: online
  eissn: 1879-1891
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0006747
  issn: 1879-1891
  databaseCode: AKRWK
  dateStart: 19950101
  isFulltext: true
  providerName: Library Specific Holdings
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEB_qHSg--K2N1GMFn5Sk2Xxcso-HtV6VO6R4WJ_Cftprc8lhE0Qf_NudzZei2NKnhewOyTKzO78wv5kBeKHSyAjt25hhKN0o0LHLlM9cI6k2WrNUN6WUFsvpfBW9O4lPdoD2uTANaV-KtVfkG69Ynzbcyu1G7vc8sf0UffTUJk2PpzHC7xGMV8sPs889zGVh0_zQNtHG9zPaRzIbThc_s_l-AW2qmwb0f77oX6x5G27VxZZ__8bz_A__c3gXjvsvb2kn515dCU_--Kuo47W2dg_udGiUzNqp-7Cjiwdwc9HF2x9CPaurEjGtVuRAVw1rqyClIW9zXqOpcvJpXZ2S38RFkWuyaOiZmnSVW7-QhpVAugKkOTngFSe8UKTJ_d2UCp8d28RrHI82eL1dPILV4ZuPr-du16jBlVESVa5UIpCBMAiBU26VT33JkphyxpQQhtFAcWE0FVOTRCo0WvgmFlr5Mo1CjYDiMYyKstC7QPxUcYScqUJDQSzJGeUqVbExStNE-ZEDfq-yTHZVzG0zjTzr6WpnGWo5s1rO_CjDwYGXg8i2LeFx2eKgt4Osz03F2zRDB3OZUDQIdcClBSRXie31hpZ1N8dFhr-jDGFgymIHng_TeOZtIIcXuqztmsBWrmNJ4MCT1kCHnYVo_zGiMAdeDRZ79bafXmv1Hoyqr7V-hnCsEhO44f2kExjPjt7Pl5PuOP4CX3Y4oA
linkProvider Unpaywall
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEB5VRaJwQOVVAi0YiRMo1PE6m_hY9cEWuj2gVvRm2bENW6XJiiZCXPjtHSdOCkK0EqdItkfKeMYznzUPA7wxOXfaUh8znBQxZzaNhaEidkVinbUit10rpfnxdHbKP56lZyuwO9TC-LTKYPt7m95Z6zCyHXZze7lY-Bpfir5KcOa7iDJf8HuHpyzzN7D3v67zPKYZzwYM7JcPoc0uyUud-wJAlnTtTlnyL-f0N_i8D2tttVQ_f6iy_M0hHazDg4AkyU7_sw9hxVaP4O48xMofQ7vTNjXiUWvInm26jKuK1I58KFWL3CryZdF8I9dJh7q0ZN6lVloSuq5-JV1GAQnNQ0uypxpFVGVIV7d7URsc--yLpvF7eIGm6fIJnB7sn-zO4vDIQlzwjDdxYTQrmHYIX3PlBZfQQmRpooQwWjuRMKO0s4meuoybibOaulRbQ4ucTyyCgaewWtWVfQaE5kYhXMwNChlxoBKJMrlJnTM2yQzlEdBhd2UROpD7hzBKOaSanUsUiPQCkZRL_ETwdiRZ9u03blrMBpHJoa4ULaFE53ATER-J_lC828g2B52Q4dRfSrxKCoRwuUgjeD1O43n1QRhV2br1a5jvOicyFsFGr0sjZxNUzxQRVATvRuW6ne3n_8fBK1ibncyP5NHh8acXcM_P9DWWm7DafG_tFoKtRr_sDtMVd24l7A
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEF_KFRQf_P5IqbKCT0qu2WRzyT4e1lqFK1I8rE_LfrZXc8nRJoj-9c5uslEUW_q0kN0hWWZ25xfmNzMIvdIltdIkLmaYqZimJo-ZTlhsFTHWGFYaX0ppcTQ7XNKPJ_nJFiIhF8aT9pVcTetqPa1XZ55buVmrvcAT2yvBR89c0vT2LAf4PUHby6NP868B5rLMNz90TbTh_YyESKbndIlzl--XEl_dNCX_80X_Ys076HZXb8SP76Kq_vA_B_fQcfjynnbybdq1cqp-_lXU8UZbu4_uDmgUz_upB2jL1A_RrcUQb3-EunnXNoBpjcb7pvWsrRo3Fr-vRAemKvCXVXuGfxMXZWXwwtMzDR4qt55iz0rAQwHSCu-LVmBRa-xzf9eNhmfHLvEaxg9ruN4uH6PlwbvPbw_joVFDrGhB21hpmapUWoDApXDKJ4liRU4EY1pKy0iqhbSGyJktqM6skYnNpdGJKmlmAFA8QZO6qc0zhJNSC4CcpQZDASwpGBG61Lm12pBCJzRCSVAZV0MVc9dMo-KBrnbOQcvcaZknlMMQodejyKYv4XHV4jTYAQ-5qXCbcnAwVwnRUWgALj0guU5sNxgaH26OSw6_owxgYMnyCL0cp-HMu0COqE3TuTWpq1zHijRCT3sDHXeWgf3ngMIi9Ga02Ou3vXOj1bto0l505jnAsVa-GA7gL13UNhQ
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=Automated+Detection+of+Glaucoma+With+Interpretable+Machine+Learning+Using+Clinical+Data+and+Multimodal+Retinal+Images&rft.jtitle=American+journal+of+ophthalmology&rft.au=Mehta%2C+Parmita&rft.au=Petersen%2C+Christine+A&rft.au=Wen%2C+Joanne+C&rft.au=Banitt%2C+Michael+R&rft.date=2021-11-01&rft.issn=1879-1891&rft.eissn=1879-1891&rft.volume=231&rft.spage=154&rft_id=info:doi/10.1016%2Fj.ajo.2021.04.021&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0002-9394&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0002-9394&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0002-9394&client=summon