Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients

Background/aimsHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the En...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	British journal of ophthalmology Ročník 105; číslo 5; s. 723 - 728
Hlavní autoři:	Heydon, Peter, Egan, Catherine, Bolter, Louis, Chambers, Ryan, Anderson, John, Aldington, Steve, Stratton, Irene M, Scanlon, Peter Henry, Webster, Laura, Mann, Samantha, du Chemin, Alain, Owen, Christopher G, Tufail, Adnan, Rudnicka, Alicja Regina
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	England BMJ Publishing Group LTD 01.05.2021 BMJ Publishing Group
Témata:	Algorithms Artificial intelligence Automation Clinical Science Cost analysis Diabetes Diabetic retinopathy Epidemiology Machine learning Medical diagnosis Patient care planning Public health Software upgrading Telemedicine United Kingdom > UK Treatment Medical Clinical Trial Telemedicine Imaging Diagnostic tests/Investigation Retina Degeneration Medical Education Epidemiology Public health
ISSN:	0007-1161, 1468-2079, 1468-2079
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Background/aimsHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard.MethodsRetinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard.ResultsSensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy.ConclusionThe algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed.
AbstractList	Human grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard.BACKGROUND/AIMSHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard.Retinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard.METHODSRetinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard.Sensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy.RESULTSSensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy.The algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed.CONCLUSIONThe algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed. Background/aimsHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard.MethodsRetinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard.ResultsSensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy.ConclusionThe algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed. Background/aimsHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard.MethodsRetinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard.ResultsSensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy.ConclusionThe algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed. Human grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard. Retinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard. Sensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy. The algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed.
Author	Bolter, Louis Mann, Samantha Stratton, Irene M Scanlon, Peter Henry Tufail, Adnan Aldington, Steve Rudnicka, Alicja Regina Owen, Christopher G du Chemin, Alain Anderson, John Chambers, Ryan Heydon, Peter Webster, Laura Egan, Catherine
AuthorAffiliation	3 Homerton University Hospital NHS Trust , London , UK 5 Guy’s and Saint Thomas’ NHS Foundation Trust , London , UK 6 Population Health Research Institute, St George’s, University of London , London , UK 1 Moorfields Biomedical Research Centre, Moorfields Eye Hospital , London , UK 2 Institute of Ophthalmology, UCL , London , UK 4 Gloucestershire Hospitals NHS Foundation Trust , Cheltenham , UK
AuthorAffiliation_xml	– name: 5 Guy’s and Saint Thomas’ NHS Foundation Trust , London , UK – name: 3 Homerton University Hospital NHS Trust , London , UK – name: 2 Institute of Ophthalmology, UCL , London , UK – name: 1 Moorfields Biomedical Research Centre, Moorfields Eye Hospital , London , UK – name: 4 Gloucestershire Hospitals NHS Foundation Trust , Cheltenham , UK – name: 6 Population Health Research Institute, St George’s, University of London , London , UK
Author_xml	– sequence: 1 givenname: Peter orcidid: 0000-0001-7029-4188 surname: Heydon fullname: Heydon, Peter email: arudnick@sgul.ac.uk organization: Moorfields Biomedical Research Centre, Moorfields Eye Hospital, London, UK – sequence: 2 givenname: Catherine surname: Egan fullname: Egan, Catherine email: arudnick@sgul.ac.uk organization: Institute of Ophthalmology, UCL, London, UK – sequence: 3 givenname: Louis surname: Bolter fullname: Bolter, Louis email: arudnick@sgul.ac.uk organization: Homerton University Hospital NHS Trust, London, UK – sequence: 4 givenname: Ryan surname: Chambers fullname: Chambers, Ryan email: arudnick@sgul.ac.uk organization: Homerton University Hospital NHS Trust, London, UK – sequence: 5 givenname: John surname: Anderson fullname: Anderson, John email: arudnick@sgul.ac.uk organization: Homerton University Hospital NHS Trust, London, UK – sequence: 6 givenname: Steve surname: Aldington fullname: Aldington, Steve email: arudnick@sgul.ac.uk organization: Gloucestershire Hospitals NHS Foundation Trust, Cheltenham, UK – sequence: 7 givenname: Irene M surname: Stratton fullname: Stratton, Irene M email: arudnick@sgul.ac.uk organization: Gloucestershire Hospitals NHS Foundation Trust, Cheltenham, UK – sequence: 8 givenname: Peter Henry orcidid: 0000-0001-8513-710X surname: Scanlon fullname: Scanlon, Peter Henry email: arudnick@sgul.ac.uk organization: Gloucestershire Hospitals NHS Foundation Trust, Cheltenham, UK – sequence: 9 givenname: Laura surname: Webster fullname: Webster, Laura email: arudnick@sgul.ac.uk organization: Guy’s and Saint Thomas’ NHS Foundation Trust, London, UK – sequence: 10 givenname: Samantha surname: Mann fullname: Mann, Samantha email: arudnick@sgul.ac.uk organization: Guy’s and Saint Thomas’ NHS Foundation Trust, London, UK – sequence: 11 givenname: Alain surname: du Chemin fullname: du Chemin, Alain email: arudnick@sgul.ac.uk organization: Guy’s and Saint Thomas’ NHS Foundation Trust, London, UK – sequence: 12 givenname: Christopher G orcidid: 0000-0003-1135-5977 surname: Owen fullname: Owen, Christopher G email: arudnick@sgul.ac.uk organization: Population Health Research Institute, St George’s, University of London, London, UK – sequence: 13 givenname: Adnan surname: Tufail fullname: Tufail, Adnan email: arudnick@sgul.ac.uk organization: Institute of Ophthalmology, UCL, London, UK – sequence: 14 givenname: Alicja Regina orcidid: 0000-0003-0369-8574 surname: Rudnicka fullname: Rudnicka, Alicja Regina email: arudnick@sgul.ac.uk organization: Population Health Research Institute, St George’s, University of London, London, UK
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32606081$$D View this record in MEDLINE/PubMed
BookMark	eNqNUsFu1DAQtVAR3RZ-AVniwiVgO4njXJBQRQGpEkhwt8bOZNcrx14cZ6V-Ab_Bt_Bl9bItlJ56seWZN2_eeN4ZOQkxICGUszec1_Kt2cbdJm_AT9FXgglW1Vy2ffOErHgjVQl1_QlZMca6inPJT8nZPG_LU0jePSOntZBMMsVX5OfXFOcd2uz2SHEPfoHsYqBxpBAopOxGZx146kJG790ag8UKAxiPAwW_jsnlzUTHmCgsOU6QS3xwYDA7S1M5Q9xB3lzT2SbE4ML6QF6z37-KHlpSDkOen5OnI_gZX9ze5-Tb5YfvF5-qqy8fP1-8v6pM04tcDaaDtjZW9HYclVVtVys7CuzN0I-ybQRC147cDIDD2ABCbRBb26uG8U7U5-TdkXW3mAkHWzon8HqX3ATpWkdw-v9McBu9jnutWNcJLgvB61uCFH8sOGc9udmWj4GAcZm1aHjfcKkUK9BXD6DbuKRQhtOi5VJ2nDNVUC_vK_or5W5D_yTbsqg54aity392VAQ6rznTB0vo-5bQB0vooyUKgXpAcNfjEaX1sdRM28dX3QB9odbD
CitedBy_id	crossref_primary_10_1038_s41433_024_03085_2 crossref_primary_10_3390_jcm14145150 crossref_primary_10_1016_j_ajo_2024_02_012 crossref_primary_10_1007_s11042_023_14963_4 crossref_primary_10_2196_53741 crossref_primary_10_1089_tmj_2022_0113 crossref_primary_10_1007_s11596_021_2474_3 crossref_primary_10_1038_s41746_024_01032_9 crossref_primary_10_4103_tjo_TJO_D_24_00064 crossref_primary_10_1007_s00125_021_05617_x crossref_primary_10_4103_ijo_IJO_1569_22 crossref_primary_10_1016_j_landig_2024_12_004 crossref_primary_10_1038_s41433_023_02717_3 crossref_primary_10_1111_aos_17591 crossref_primary_10_1007_s00592_022_01941_9 crossref_primary_10_1136_bmjopen_2023_075558 crossref_primary_10_1186_s12938_025_01336_1 crossref_primary_10_3389_fendo_2022_1079217 crossref_primary_10_3390_jcm14134810 crossref_primary_10_5662_wjm_v15_i4_107166 crossref_primary_10_1038_s41598_023_38610_y crossref_primary_10_2337_dci23_0032 crossref_primary_10_1186_s13098_024_01447_0 crossref_primary_10_1038_s41598_021_94178_5 crossref_primary_10_1186_s40942_024_00547_3 crossref_primary_10_1111_opo_13435 crossref_primary_10_3389_fendo_2022_1032144 crossref_primary_10_5114_amsad_183420 crossref_primary_10_1080_07853890_2024_2352018 crossref_primary_10_1002_ima_23213 crossref_primary_10_1007_s12530_022_09427_3 crossref_primary_10_1093_jamia_ocad094 crossref_primary_10_3389_fcell_2024_1473176 crossref_primary_10_3389_fdgth_2025_1608266 crossref_primary_10_1136_bjo_2023_324097 crossref_primary_10_3389_fpubh_2022_1025271 crossref_primary_10_1007_s40123_023_00688_y crossref_primary_10_1177_24741264241247602 crossref_primary_10_1177_09691413221144382 crossref_primary_10_1080_1061186X_2024_2448711 crossref_primary_10_1002_pdi_2505 crossref_primary_10_3390_jcm11174945 crossref_primary_10_4103_ojo_ojo_27_22 crossref_primary_10_1016_j_cjca_2024_07_028 crossref_primary_10_1007_s40123_024_01086_8 crossref_primary_10_1038_s43856_024_00590_z crossref_primary_10_1080_09286586_2024_2434738 crossref_primary_10_4103_sjopt_sjopt_153_23 crossref_primary_10_2196_52073 crossref_primary_10_3389_fmed_2025_1567159 crossref_primary_10_1111_ceo_14173 crossref_primary_10_1111_dme_15055 crossref_primary_10_3389_fcell_2025_1576465 crossref_primary_10_3390_ijtm1030020 crossref_primary_10_1136_bmjophth_2023_001491 crossref_primary_10_1177_11795514241235514 crossref_primary_10_1186_s12886_024_03306_y crossref_primary_10_2147_OPTH_S267521 crossref_primary_10_2196_50568 crossref_primary_10_1177_11206721211023725 crossref_primary_10_1007_s11892_022_01467_y crossref_primary_10_1177_19322968231194644 crossref_primary_10_1001_jamaophthalmol_2022_1175 crossref_primary_10_1016_j_compbiomed_2021_104599 crossref_primary_10_1136_bjo_2023_323395 crossref_primary_10_3928_1081597X_20240131_01 crossref_primary_10_1167_iovs_65_10_10 crossref_primary_10_1038_s41433_022_02217_w crossref_primary_10_1016_j_xops_2025_100707 crossref_primary_10_1007_s40123_023_00691_3 crossref_primary_10_1007_s00125_025_06379_6 crossref_primary_10_2337_dci24_0001 crossref_primary_10_4103_ijo_IJO_1075_21 crossref_primary_10_1016_j_diabres_2024_111964 crossref_primary_10_1016_j_bspc_2024_106885 crossref_primary_10_1080_00051144_2023_2251231 crossref_primary_10_1007_s42600_023_00320_9 crossref_primary_10_1016_j_asoc_2022_109462 crossref_primary_10_1089_tmj_2022_0489 crossref_primary_10_1177_19322968211042665 crossref_primary_10_2196_52506 crossref_primary_10_3390_jcm11206199 crossref_primary_10_1001_jamaophthalmol_2023_4508 crossref_primary_10_3390_jcm12041284 crossref_primary_10_7759_cureus_55745 crossref_primary_10_1136_bmj_n1872 crossref_primary_10_3390_medicina60020243 crossref_primary_10_1136_bmjopen_2024_094343 crossref_primary_10_1038_s41433_022_02190_4
Cites_doi	10.1089/dia.2019.0164 10.1007/s11892-019-1189-3 10.1016/j.ophtha.2016.11.014 10.1038/s41746-018-0040–6 10.1159/000486284 10.1177/1932296816628546 10.1016/j.ophtha.2017.08.046 10.1001/jama.298.8.902 10.1111/dme.13053 10.1038/s41591-018-0107-6 10.3310/hta20920 10.1001/jama.2016.17216 10.1016/S0161-6420(13)38014-2 10.1038/s41591-018-0107-6 10.1001/jama.298.8.902 10.1111/dme.13053 10.1016/j.ophtha.2017.08.046 10.1001/jama.2016.17216 10.3310/hta20220 10.1007/s11892-019-1189-3 10.1177/1932296816628546 10.1016/S0161-6420(13)38014-2 10.1016/j.ophtha.2016.11.014 10.1038/s41746-018-0040-6 10.1159/000486284 10.1089/dia.2019.0164
ContentType	Journal Article
Copyright	Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. 2021 Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/ . Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. 2021
Copyright_xml	– notice: Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. – notice: 2021 Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/ . Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. 2021
DBID	9YT ACMMV AAYXX CITATION NPM 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA BENPR BTHHO CCPQU FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM
DOI	10.1136/bjophthalmol-2020-316594
DatabaseName	BMJ Open Access Journals BMJ Journals:Open Access CrossRef PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central BMJ Journals ProQuest One Community College Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) ProQuest Health & Medical Collection Medical Database ProQuest Proquest Central Premium ProQuest One Academic (New) ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef PubMed ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Central China ProQuest Hospital Collection (Alumni) ProQuest Central ProQuest Health & Medical Complete ProQuest Health & Medical Research Collection Health Research Premium Collection ProQuest Medical Library ProQuest One Academic UKI Edition Health and Medicine Complete (Alumni Edition) BMJ Journals Health & Medical Research Collection ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) ProQuest Medical Library (Alumni) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic ProQuest One Academic Middle East (New) PubMed
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Public Health
EISSN	1468-2079
EndPage	728
ExternalDocumentID	PMC8077216 32606081 10_1136_bjophthalmol_2020_316594 bjophthalmol
Genre	Journal Article
GeographicLocations	United Kingdom--UK
GeographicLocations_xml	– name: United Kingdom--UK
GrantInformation_xml	– fundername: ; – fundername: ; grantid: NIHR200152
GroupedDBID	--- -~X .55 .GJ .VT 0R~ 18M 23N 2WC 354 39C 3O- 4.4 40O 53G 5GY 5RE 5VS 6J9 7X7 7~S 88E 8FI 8FJ 8R4 8R5 9YT AAHLL AAKAS AAOJX AAWJN ABAAH ABJNI ABKDF ABMQD ABTFR ABUWG ABVAJ ACCCW ACGFO ACGFS ACGTL ACHTP ACMFJ ACMMV ACNCT ACOAB ACOFX ACQSR ACTZY ADBBV ADCEG ADZCM AENEX AFKRA AFWFF AGQPQ AHMBA AHNKE AHQMW AJYBZ ALIPV ALMA_UNASSIGNED_HOLDINGS ASPBG AVWKF AZFZN BAWUL BENPR BLJBA BOMFT BPHCQ BTFSW BTHHO BVXVI C1A C45 CAG CCPQU COF CS3 CXRWF DIK DU5 E3Z EBS EJD F5P FYUFA H13 HAJ HMCUK HYE HZ~ IAO IEA IHR IOF ITC J5H KQ8 L7B M1P N9A NTWIH NXWIF O9- OK1 OVD P2P PHGZT PQQKQ PROAC PSQYO Q2X R53 RHI RMJ RPM RV8 TEORI TR2 UAW UKHRP UYXKK V24 VM9 W8F WH7 WOQ X7M XOL YFH YQY ZGI AAFWJ AAYXX ACQHZ AERUA AFFHD CITATION PHGZM PJZUB PPXIY NPM 3V. 7XB 8FK K9. PKEHL PQEST PQUKI PRINS 7X8 5PM
ID	FETCH-LOGICAL-b492t-db7a53bc29cff8c85738cf2e9bd9f6542ea75f1bdaedf4aea3bee5c98401723
IEDL.DBID	7X7
ISICitedReferencesCount	113
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000642451300021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0007-1161 1468-2079
IngestDate	Tue Nov 04 01:55:31 EST 2025 Sun Nov 09 12:06:49 EST 2025 Tue Oct 07 07:26:40 EDT 2025 Thu Apr 03 07:01:52 EDT 2025 Sat Nov 29 03:06:06 EST 2025 Tue Nov 18 20:23:07 EST 2025 Thu Apr 24 23:09:34 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	5
Keywords	Treatment Medical Clinical Trial Telemedicine Imaging Diagnostic tests/Investigation Retina Degeneration Medical Education Epidemiology Public health
Language	English
License	This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/. Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-b492t-db7a53bc29cff8c85738cf2e9bd9f6542ea75f1bdaedf4aea3bee5c98401723
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0003-0369-8574 0000-0001-7029-4188 0000-0001-8513-710X 0000-0003-1135-5977
OpenAccessLink	https://pubmed.ncbi.nlm.nih.gov/PMC8077216
PMID	32606081
PQID	2516671108
PQPubID	2041039
PageCount	6
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_8077216 proquest_miscellaneous_2419416880 proquest_journals_2516671108 pubmed_primary_32606081 crossref_citationtrail_10_1136_bjophthalmol_2020_316594 crossref_primary_10_1136_bjophthalmol_2020_316594 bmj_primary_10_1136_bjophthalmol_2020_316594
PublicationCentury	2000
PublicationDate	2021-05-01
PublicationDateYYYYMMDD	2021-05-01
PublicationDate_xml	– month: 05 year: 2021 text: 2021-05-01 day: 01
PublicationDecade	2020
PublicationPlace	England
PublicationPlace_xml	– name: England – name: London – name: BMA House, Tavistock Square, London, WC1H 9JR
PublicationTitle	British journal of ophthalmology
PublicationTitleAlternate	Br J Ophthalmol
PublicationYear	2021
Publisher	BMJ Publishing Group LTD BMJ Publishing Group
Publisher_xml	– name: BMJ Publishing Group LTD – name: BMJ Publishing Group
References	Lee, Taylor, Kalpathy-Cramer 2017; 124 De Fauw, Ledsam, Romera-Paredes 2018; 24 Norgaard, Grauslund 2018; 60 Tufail, Rudisill, Egan 2017; 124 1991; 98 Gulshan, Peng, Coram 2016; 316 Zachariah, Wykes, Yorston 2015; 28 Lam, Yi, Guo 2018; 2017 Tufail, Kapetanakis, Salas-Vega 2016; 20 Bhaskaranand, Ramachandra, Bhat 2019; 21 Bhaskaranand, Ramachandra, Bhat 2016; 10 Abramoff, Lavin, Birch 2018; 1 Mohamed, Gillies, Wong 2007; 298 Oke, Stratton, Aldington 2016; 33 Bellemo, Lim, Rim 2019; 19 Oke (2021042208101370000_105.5.723.11) 2016; 33 2021042208101370000_105.5.723.9 Zachariah (2021042208101370000_105.5.723.15) 2015; 28 Lam (2021042208101370000_105.5.723.21) 2018; 2017 De Fauw (2021042208101370000_105.5.723.22) 2018; 24 2021042208101370000_105.5.723.19 2021042208101370000_105.5.723.18 Lee (2021042208101370000_105.5.723.3) 2017; 124 2021042208101370000_105.5.723.14 2021042208101370000_105.5.723.16 Bhaskaranand (2021042208101370000_105.5.723.17) 2019; 21 2021042208101370000_105.5.723.10 Bellemo (2021042208101370000_105.5.723.12) 2019; 19 2021042208101370000_105.5.723.13 2021042208101370000_105.5.723.23 2021042208101370000_105.5.723.7 2021042208101370000_105.5.723.8 2021042208101370000_105.5.723.5 2021042208101370000_105.5.723.20 2021042208101370000_105.5.723.6 2021042208101370000_105.5.723.4 2021042208101370000_105.5.723.1 2021042208101370000_105.5.723.2
References_xml	– volume: 21 start-page: 635 year: 2019 article-title: The value of automated diabetic retinopathy screening with the EyeArt system: a study of more than 100,000 consecutive encounters from people with diabetes publication-title: Diabetes Technol Ther doi: 10.1089/dia.2019.0164 – volume: 28 start-page: s22 year: 2015 article-title: The Scottish Diabetic Retinopathy Screening programme publication-title: Community Eye Health – volume: 19 start-page: 72 year: 2019 article-title: Artificial intelligence screening for diabetic retinopathy: the real-world emerging application publication-title: Curr Diab Rep doi: 10.1007/s11892-019-1189-3 – volume: 124 start-page: 343 year: 2017 article-title: Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost-effectiveness compared with human graders publication-title: Ophthalmology doi: 10.1016/j.ophtha.2016.11.014 – volume: 1 year: 2018 article-title: Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices publication-title: npj Digit Med doi: 10.1038/s41746-018-0040–6 – volume: 60 start-page: 9 year: 2018 article-title: Automated screening for diabetic retinopathy - a systematic review publication-title: Ophthalmic Res doi: 10.1159/000486284 – volume: 10 start-page: 254 year: 2016 article-title: Automated diabetic retinopathy screening and monitoring using retinal fundus image analysis publication-title: J Diabetes Sci Technol doi: 10.1177/1932296816628546 – volume: 124 start-page: 1726 year: 2017 article-title: Machine learning has arrived! publication-title: Ophthalmology doi: 10.1016/j.ophtha.2017.08.046 – volume: 298 start-page: 902 year: 2007 article-title: Management of diabetic retinopathy: a systematic review publication-title: JAMA doi: 10.1001/jama.298.8.902 – volume: 33 start-page: 896 year: 2016 article-title: The use of statistical methodology to determine the accuracy of grading within a diabetic retinopathy screening programme publication-title: Diabet Med doi: 10.1111/dme.13053 – volume: 24 start-page: 1342 year: 2018 article-title: Clinically applicable deep learning for diagnosis and referral in retinal disease publication-title: Nat Med doi: 10.1038/s41591-018-0107-6 – volume: 20 start-page: 1 year: 2016 article-title: An observational study to assess if automated diabetic retinopathy image assessment software can replace one or more steps of manual imaging grading and to determine their cost-effectiveness publication-title: Health Technol Assess doi: 10.3310/hta20920 – volume: 316 start-page: 2402 year: 2016 article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs publication-title: JAMA doi: 10.1001/jama.2016.17216 – volume: 2017 start-page: 147 year: 2018 article-title: Automated detection of diabetic retinopathy using deep learning publication-title: AMIA Jt Summits Transl Sci Proc – volume: 98 start-page: 823 year: 1991 article-title: Fundus photographic risk factors for progression of diabetic retinopathy. ETDRS report number 12. publication-title: Ophthalmology doi: 10.1016/S0161-6420(13)38014-2 – ident: 2021042208101370000_105.5.723.9 – ident: 2021042208101370000_105.5.723.7 – ident: 2021042208101370000_105.5.723.8 – volume: 24 start-page: 1342 year: 2018 ident: 2021042208101370000_105.5.723.22 article-title: Clinically applicable deep learning for diagnosis and referral in retinal disease publication-title: Nat Med doi: 10.1038/s41591-018-0107-6 – ident: 2021042208101370000_105.5.723.1 doi: 10.1001/jama.298.8.902 – volume: 33 start-page: 896 year: 2016 ident: 2021042208101370000_105.5.723.11 article-title: The use of statistical methodology to determine the accuracy of grading within a diabetic retinopathy screening programme publication-title: Diabet Med doi: 10.1111/dme.13053 – volume: 124 start-page: 1726 year: 2017 ident: 2021042208101370000_105.5.723.3 article-title: Machine learning has arrived! publication-title: Ophthalmology doi: 10.1016/j.ophtha.2017.08.046 – ident: 2021042208101370000_105.5.723.14 – ident: 2021042208101370000_105.5.723.2 – ident: 2021042208101370000_105.5.723.16 doi: 10.1001/jama.2016.17216 – ident: 2021042208101370000_105.5.723.5 doi: 10.3310/hta20220 – volume: 19 start-page: 72 year: 2019 ident: 2021042208101370000_105.5.723.12 article-title: Artificial intelligence screening for diabetic retinopathy: the real-world emerging application publication-title: Curr Diab Rep doi: 10.1007/s11892-019-1189-3 – ident: 2021042208101370000_105.5.723.18 – ident: 2021042208101370000_105.5.723.19 – volume: 2017 start-page: 147 year: 2018 ident: 2021042208101370000_105.5.723.21 article-title: Automated detection of diabetic retinopathy using deep learning publication-title: AMIA Jt Summits Transl Sci Proc – ident: 2021042208101370000_105.5.723.4 doi: 10.1177/1932296816628546 – volume: 28 start-page: s22 year: 2015 ident: 2021042208101370000_105.5.723.15 article-title: The Scottish Diabetic Retinopathy Screening programme publication-title: Community Eye Health – ident: 2021042208101370000_105.5.723.10 doi: 10.1016/S0161-6420(13)38014-2 – ident: 2021042208101370000_105.5.723.23 – ident: 2021042208101370000_105.5.723.6 doi: 10.1016/j.ophtha.2016.11.014 – ident: 2021042208101370000_105.5.723.20 doi: 10.1038/s41746-018-0040-6 – ident: 2021042208101370000_105.5.723.13 doi: 10.1159/000486284 – volume: 21 start-page: 635 year: 2019 ident: 2021042208101370000_105.5.723.17 article-title: The value of automated diabetic retinopathy screening with the EyeArt system: a study of more than 100,000 consecutive encounters from people with diabetes publication-title: Diabetes Technol Ther doi: 10.1089/dia.2019.0164
SSID	ssj0002617
Score	2.6447072
SecondaryResourceType	review_article
Snippet	Background/aimsHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing... Human grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of...
SourceID	pubmedcentral proquest pubmed crossref bmj
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	723
SubjectTerms	Algorithms Artificial intelligence Automation Clinical Science Cost analysis Diabetes Diabetic retinopathy Epidemiology Machine learning Medical diagnosis Patient care planning Public health Software upgrading Telemedicine
Title	Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients
URI	https://bjo.bmj.com/content/105/5/723.full https://www.ncbi.nlm.nih.gov/pubmed/32606081 https://www.proquest.com/docview/2516671108 https://www.proquest.com/docview/2419416880 https://pubmed.ncbi.nlm.nih.gov/PMC8077216
Volume	105
WOSCitedRecordID	wos000642451300021&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: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1468-2079 dateEnd: 20250609 omitProxy: false ssIdentifier: ssj0002617 issn: 0007-1161 databaseCode: 7X7 dateStart: 19220101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1468-2079 dateEnd: 20250609 omitProxy: false ssIdentifier: ssj0002617 issn: 0007-1161 databaseCode: BENPR dateStart: 19220101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwEB6xuwghIR7Lq7CsjMQRa9M6ieMTArQrDlBVwKG3yHZs2lWblDZF4g_wu5lxHtuChFbikkPsxElmMv7GnvkG4JUnjjevBI9TY3hsYsVVYTMulM2KxGJLFBKFP8rxOJtO1aRdcNu0YZWdTQyGuqgsrZGf4TycppKC1t-svnOqGkW7q20JjQM4orLZpOdy2jtcgW28gb-SDxHadJE8Ij0zl9VqVs_0YlktUFNCGnGaUOniA7O83J-k_kKefwZQ7sxIF_f-913uw90Wi7K3jfI8gBuuPIZbn9rd9mO406zpsSZV6SH8mqyrLjOTXdGEs8ozXTLSwYaOgs13eD65C9lZBdOLb_gM9WzJECczva0rBMt4vln9xWEon7KsqETyT4bGDB1snFbp5iJi-HFZSwG7eQRfLs6_vv_A2zoOHEU_qnlhpE6EsSNlvc9slkiRWT9yyhTKU8Esp2Xih6bQrvCxdloY5xKr0PdEeCUew2FZle4psDiJrEF8aqh2eVxgVxnryAkhvUI3NRnAaxRevmp4OvLg34g035V1TrLOG1kPQHZSzm3LiE6FORbXuHLYX3n90U46ZchbO7HJrzRhAC_7ZvzDadtGl67aYp94qBA2o6EdwJNG7_pBEXxHKaI6fJU9jew7EHv4fks5nwUW8SySRNz07N-P9RxujyiKJ4R4nsBhvd66F3DT_qjnm_Vp-N3CMTuFo3fn48nn31OpOZA
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB61BQES4lFegQKLBLeu6nhtr_eAEAKqVk2jSvSQE9buek1SJXZIHFD_AL-GH8mMH2kCEuqlB67etdePb2fnW898A_A6I423TAkeRMbwwASKq9TGXCgbp6HFFq9KFO7Jfj8eDNTJBvxqc2EorLK1iZWhTgtLe-R7uA5HkaSg9XfTb5yqRtHf1baERg2LI3f-Aynb_O3hR_y-b3x__9PphwPeVBXgeCN-yVMjdSiM9ZXNstjGoRSxzXynTKoyKt_ktAyzrkm1S7NAOy2Mc6FVyIRwsRd41U24hlZcEtWTgyW9q7TNa2db8i46Um3ckIj2zFkxHZZDPZ4UY8RllbQchVQoedNMztaXxL_83D_DNVfWv_27_9ebuwd3Gj-bva8nxn3YcPk23DhuIgm24Xa9X8nqNKwH8PNkVrRZp-xCAp0VGdM5o_lVS22w0YqGKXdV5lnK9PgrPnE5nDDkAEwvygKJAB6vd7ZxGMoVzQsq_3zO0FA7R9tRdHHhMfyUrJG3nT-Ez1fwTh7BVl7k7gmwIPSsQd_bUF32IMWuMtCeE0JmCil42IFdhEoyrTVIkoq7iShZRVZCyEpqZHVAtphKbKP2TkVHxpc4s7s88_Kj7bTQSxobOE8ucNeBV8tmtF70S0rnrlhgn6CrkBLgItKBxzXKl4MisfAi9FjxUdbwv-xAyujrLfloWCmkx54kUaqn_76tl3Dz4PS4l_QO-0fP4JZP0UpVKOsObJWzhXsO1-33cjSfvagmOoMvVzs7fgOmnJab
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFD7aOjQhTVzGYIUBRoI3rKZxEscPCAFbxbRRVcDDnohsx6ad2qS0KWh_gN_Ez-M4l64FCe1lD7zGTpzLd27OOd8BeG4dx5sVjAaRUjRQgaAi1TFlQsdpqHHEKwuFT3m_H5-dicEG_GpqYVxaZaMTS0Wd5trtkXfQDkcRd0nrHVunRQwOe6-n36jrIOX-tDbtNCqInJiLHxi-zV8dH-K3fuH7vaPP797TusMAxZvyC5oqLkOmtC-0tbGOQ85ibX0jVCqsa-VkJA9tV6XSpDaQRjJlTKgFRkVo-BledRO2OLoYQQu23h71Bx-XVsAxnVeuN6dddKuaLCIWddR5Ph0WQzme5GNEaVnCHIWubfKmmpyvG8i_vN4_kzdXrGHv9v_7Hu_ArdoDJ28qkbkLGybbhe0PdY7BLuxUO5mkKtC6Bz8Hs7ypRyWX5Ogkt0RmxEleRcJBRivsptSUNWkpkeOv-MTFcEIwOiByUeQYIuDxas8bl3FVpFnuGkNfEFThxriNKndx5hH8rKQmvp3vwadreCf3oZXlmdkHEoSeVuiVK9exPUhxKg-kZxjjVmBwHrbhJcImmVbsJEkZ1bEoWUVZ4lCWVChrA2_wleiaB961Ixlf4czu8syrr3bQwDCpteM8ucRgG54th1GvuZ9VMjP5AucEXYHBApqXNjyoEL9cFEMOL0JfFh9lTRaWExxn-vpINhqW3Omxxx1d1cN_39ZT2EahSE6P-yeP4Kbv0pjKHNcDaBWzhXkMN_T3YjSfPamlnsCX6xWP35jsoLs
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=Prospective+evaluation+of+an+artificial+intelligence-enabled+algorithm+for+automated+diabetic+retinopathy+screening+of+30+000+patients&rft.jtitle=British+journal+of+ophthalmology&rft.au=Heydon%2C+Peter&rft.au=Egan%2C+Catherine&rft.au=Bolter%2C+Louis&rft.au=Chambers%2C+Ryan&rft.date=2021-05-01&rft.pub=BMJ+Publishing+Group+LTD&rft.issn=0007-1161&rft.eissn=1468-2079&rft.volume=105&rft.issue=5&rft.spage=723&rft.epage=728&rft_id=info:doi/10.1136%2Fbjophthalmol-2020-316594&rft.externalDBID=HAS_PDF_LINK
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0007-1161&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0007-1161&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0007-1161&client=summon