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...
Gespeichert in:
| Veröffentlicht in: | British journal of ophthalmology 2021-05, Vol.105 (5), p.723-728 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 728 |
|---|---|
| container_issue | 5 |
| container_start_page | 723 |
| container_title | British journal of ophthalmology |
| container_volume | 105 |
| creator | 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 |
| description | 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. |
| doi_str_mv | 10.1136/bjophthalmol-2020-316594 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8077216</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2419416880</sourcerecordid><originalsourceid>FETCH-LOGICAL-b492t-db7a53bc29cff8c85738cf2e9bd9f6542ea75f1bdaedf4aea3bee5c98401723</originalsourceid><addsrcrecordid>eNqNks-KFDEQxhtR3HX1FSTgRZDWJN2dTl8EGfwHCwp6D5V0ZSZDdzIm6Vn2CXwNn8UnM-Os4-ppLwmp-upLVX6pKsLoS8Ya8Upvw26TNzDNYao55bRumOiG9l51zlohS6gf7lfnlNK-Zkyws-pRStty5IL1D6uzhgsqqGTn1ffPMaQdmuz2SHAP0wLZBU-CJeAJxOysMw4m4nzGaXJr9AZr9KAnHAlM6xBd3szEhkhgyWGGXOKjA43ZGRLL6sMO8uaaJBMRvfPrg3lDf_4o_ZCScuhzelw9sDAlfHKzX1Rf3r39uvpQX356_3H15rLW7cBzPeoeukYbPhhrpZFd30hjOQ56HKzoWo7Qd5bpEXC0LSA0GrEzg2wp63lzUb0-uu4WPeNoys0RJrWLboZ4rQI49W_Gu41ah72StO85E8Xg-Y1BDN8WTFnNLpnyMOAxLEnxlg0tE1LSIn32n3QblujLcIp3TIieMSqLSh5VpnBIEe2pGUbVgbW6zVodWKsj61L69PYwp8I_cP96X6EONhl3YHeSldcXLW871hz-BVu5_Jv8Kiw-l9IXdy8t6uao1vP27v3_AqZo4DE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2516671108</pqid></control><display><type>article</type><title>Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients</title><source>PubMed Central</source><creator>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</creator><creatorcontrib>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</creatorcontrib><description>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.</description><identifier>ISSN: 0007-1161</identifier><identifier>EISSN: 1468-2079</identifier><identifier>DOI: 10.1136/bjophthalmol-2020-316594</identifier><identifier>PMID: 32606081</identifier><language>eng</language><publisher>LONDON: Bmj Publishing Group</publisher><subject>Algorithms ; Artificial intelligence ; Automation ; Clinical Science ; Cost analysis ; Diabetes ; Diabetic retinopathy ; Epidemiology ; Life Sciences & Biomedicine ; Machine learning ; Medical diagnosis ; Ophthalmology ; Patient care planning ; Public health ; Science & Technology ; Software upgrading ; Telemedicine</subject><ispartof>British journal of ophthalmology, 2021-05, Vol.105 (5), p.723-728</ispartof><rights>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.</rights><rights>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.</rights><rights>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</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>82</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000642451300021</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-b492t-db7a53bc29cff8c85738cf2e9bd9f6542ea75f1bdaedf4aea3bee5c98401723</citedby><cites>FETCH-LOGICAL-b492t-db7a53bc29cff8c85738cf2e9bd9f6542ea75f1bdaedf4aea3bee5c98401723</cites><orcidid>0000-0003-0369-8574 ; 0000-0001-7029-4188 ; 0000-0001-8513-710X ; 0000-0003-1135-5977 ; 0000-0003-1808-3580 ; 0000-0001-6131-7640</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8077216/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8077216/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,315,728,781,785,886,27928,27929,53795,53797</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/32606081$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Heydon, Peter</creatorcontrib><creatorcontrib>Egan, Catherine</creatorcontrib><creatorcontrib>Bolter, Louis</creatorcontrib><creatorcontrib>Chambers, Ryan</creatorcontrib><creatorcontrib>Anderson, John</creatorcontrib><creatorcontrib>Aldington, Steve</creatorcontrib><creatorcontrib>Stratton, Irene M</creatorcontrib><creatorcontrib>Scanlon, Peter Henry</creatorcontrib><creatorcontrib>Webster, Laura</creatorcontrib><creatorcontrib>Mann, Samantha</creatorcontrib><creatorcontrib>du Chemin, Alain</creatorcontrib><creatorcontrib>Owen, Christopher G</creatorcontrib><creatorcontrib>Tufail, Adnan</creatorcontrib><creatorcontrib>Rudnicka, Alicja Regina</creatorcontrib><title>Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients</title><title>British journal of ophthalmology</title><addtitle>BRIT J OPHTHALMOL</addtitle><addtitle>Br J Ophthalmol</addtitle><description>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.</description><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Automation</subject><subject>Clinical Science</subject><subject>Cost analysis</subject><subject>Diabetes</subject><subject>Diabetic retinopathy</subject><subject>Epidemiology</subject><subject>Life Sciences & Biomedicine</subject><subject>Machine learning</subject><subject>Medical diagnosis</subject><subject>Ophthalmology</subject><subject>Patient care planning</subject><subject>Public health</subject><subject>Science & Technology</subject><subject>Software upgrading</subject><subject>Telemedicine</subject><issn>0007-1161</issn><issn>1468-2079</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>9YT</sourceid><sourceid>ACMMV</sourceid><sourceid>HGBXW</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><recordid>eNqNks-KFDEQxhtR3HX1FSTgRZDWJN2dTl8EGfwHCwp6D5V0ZSZDdzIm6Vn2CXwNn8UnM-Os4-ppLwmp-upLVX6pKsLoS8Ya8Upvw26TNzDNYao55bRumOiG9l51zlohS6gf7lfnlNK-Zkyws-pRStty5IL1D6uzhgsqqGTn1ffPMaQdmuz2SHAP0wLZBU-CJeAJxOysMw4m4nzGaXJr9AZr9KAnHAlM6xBd3szEhkhgyWGGXOKjA43ZGRLL6sMO8uaaJBMRvfPrg3lDf_4o_ZCScuhzelw9sDAlfHKzX1Rf3r39uvpQX356_3H15rLW7cBzPeoeukYbPhhrpZFd30hjOQ56HKzoWo7Qd5bpEXC0LSA0GrEzg2wp63lzUb0-uu4WPeNoys0RJrWLboZ4rQI49W_Gu41ah72StO85E8Xg-Y1BDN8WTFnNLpnyMOAxLEnxlg0tE1LSIn32n3QblujLcIp3TIieMSqLSh5VpnBIEe2pGUbVgbW6zVodWKsj61L69PYwp8I_cP96X6EONhl3YHeSldcXLW871hz-BVu5_Jv8Kiw-l9IXdy8t6uao1vP27v3_AqZo4DE</recordid><startdate>20210501</startdate><enddate>20210501</enddate><creator>Heydon, Peter</creator><creator>Egan, Catherine</creator><creator>Bolter, Louis</creator><creator>Chambers, Ryan</creator><creator>Anderson, John</creator><creator>Aldington, Steve</creator><creator>Stratton, Irene M</creator><creator>Scanlon, Peter Henry</creator><creator>Webster, Laura</creator><creator>Mann, Samantha</creator><creator>du Chemin, Alain</creator><creator>Owen, Christopher G</creator><creator>Tufail, Adnan</creator><creator>Rudnicka, Alicja Regina</creator><general>Bmj Publishing Group</general><general>BMJ Publishing Group LTD</general><general>BMJ Publishing Group</general><scope>9YT</scope><scope>ACMMV</scope><scope>BLEPL</scope><scope>DTL</scope><scope>HGBXW</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>BTHHO</scope><scope>CCPQU</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-0369-8574</orcidid><orcidid>https://orcid.org/0000-0001-7029-4188</orcidid><orcidid>https://orcid.org/0000-0001-8513-710X</orcidid><orcidid>https://orcid.org/0000-0003-1135-5977</orcidid><orcidid>https://orcid.org/0000-0003-1808-3580</orcidid><orcidid>https://orcid.org/0000-0001-6131-7640</orcidid></search><sort><creationdate>20210501</creationdate><title>Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients</title><author>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</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-b492t-db7a53bc29cff8c85738cf2e9bd9f6542ea75f1bdaedf4aea3bee5c98401723</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Automation</topic><topic>Clinical Science</topic><topic>Cost analysis</topic><topic>Diabetes</topic><topic>Diabetic retinopathy</topic><topic>Epidemiology</topic><topic>Life Sciences & Biomedicine</topic><topic>Machine learning</topic><topic>Medical diagnosis</topic><topic>Ophthalmology</topic><topic>Patient care planning</topic><topic>Public health</topic><topic>Science & Technology</topic><topic>Software upgrading</topic><topic>Telemedicine</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Heydon, Peter</creatorcontrib><creatorcontrib>Egan, Catherine</creatorcontrib><creatorcontrib>Bolter, Louis</creatorcontrib><creatorcontrib>Chambers, Ryan</creatorcontrib><creatorcontrib>Anderson, John</creatorcontrib><creatorcontrib>Aldington, Steve</creatorcontrib><creatorcontrib>Stratton, Irene M</creatorcontrib><creatorcontrib>Scanlon, Peter Henry</creatorcontrib><creatorcontrib>Webster, Laura</creatorcontrib><creatorcontrib>Mann, Samantha</creatorcontrib><creatorcontrib>du Chemin, Alain</creatorcontrib><creatorcontrib>Owen, Christopher G</creatorcontrib><creatorcontrib>Tufail, Adnan</creatorcontrib><creatorcontrib>Rudnicka, Alicja Regina</creatorcontrib><collection>BMJ Open Access Journals</collection><collection>BMJ Journals:Open Access</collection><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>Web of Science - Science Citation Index Expanded - 2021</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>BMJ Journals</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>British journal of ophthalmology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Heydon, Peter</au><au>Egan, Catherine</au><au>Bolter, Louis</au><au>Chambers, Ryan</au><au>Anderson, John</au><au>Aldington, Steve</au><au>Stratton, Irene M</au><au>Scanlon, Peter Henry</au><au>Webster, Laura</au><au>Mann, Samantha</au><au>du Chemin, Alain</au><au>Owen, Christopher G</au><au>Tufail, Adnan</au><au>Rudnicka, Alicja Regina</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients</atitle><jtitle>British journal of ophthalmology</jtitle><stitle>BRIT J OPHTHALMOL</stitle><addtitle>Br J Ophthalmol</addtitle><date>2021-05-01</date><risdate>2021</risdate><volume>105</volume><issue>5</issue><spage>723</spage><epage>728</epage><pages>723-728</pages><issn>0007-1161</issn><eissn>1468-2079</eissn><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.</abstract><cop>LONDON</cop><pub>Bmj Publishing Group</pub><pmid>32606081</pmid><doi>10.1136/bjophthalmol-2020-316594</doi><tpages>6</tpages><orcidid>https://orcid.org/0000-0003-0369-8574</orcidid><orcidid>https://orcid.org/0000-0001-7029-4188</orcidid><orcidid>https://orcid.org/0000-0001-8513-710X</orcidid><orcidid>https://orcid.org/0000-0003-1135-5977</orcidid><orcidid>https://orcid.org/0000-0003-1808-3580</orcidid><orcidid>https://orcid.org/0000-0001-6131-7640</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0007-1161 |
| ispartof | British journal of ophthalmology, 2021-05, Vol.105 (5), p.723-728 |
| issn | 0007-1161 1468-2079 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8077216 |
| source | PubMed Central |
| subjects | Algorithms Artificial intelligence Automation Clinical Science Cost analysis Diabetes Diabetic retinopathy Epidemiology Life Sciences & Biomedicine Machine learning Medical diagnosis Ophthalmology Patient care planning Public health Science & Technology Software upgrading Telemedicine |
| title | Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T11%3A38%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prospective%20evaluation%20of%20an%20artificial%20intelligence-enabled%20algorithm%20for%20automated%20diabetic%20retinopathy%20screening%20of%2030%C2%A0000%20patients&rft.jtitle=British%20journal%20of%20ophthalmology&rft.au=Heydon,%20Peter&rft.date=2021-05-01&rft.volume=105&rft.issue=5&rft.spage=723&rft.epage=728&rft.pages=723-728&rft.issn=0007-1161&rft.eissn=1468-2079&rft_id=info:doi/10.1136/bjophthalmol-2020-316594&rft_dat=%3Cproquest_pubme%3E2419416880%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2516671108&rft_id=info:pmid/32606081&rfr_iscdi=true |