THEIA™ development, and testing of artificial intelligence-based primary triage of diabetic retinopathy screening images in New Zealand.

Show simple item record Vaghefi, E Yang, S Xie, L Hill, S Schmiedel, O Murphy, R Squirrell, D
dc.coverage.spatial England 2022-06-23T04:20:35Z 2022-06-23T04:20:35Z 2021-04
dc.identifier.citation (2021). Diabetic Medicine, 38(4), e14386-.
dc.identifier.issn 0742-3071
dc.description.abstract <h4>Aim</h4>To develop and evaluate an artificial intelligence triage system with high sensitivity for detecting referable diabetic retinopathy and maculopathy, while maintaining high specificity for non-referable disease, for clinical implementation within the New Zealand national diabetic retinopathy screening programme.<h4>Methods</h4>The THEIA™ artificial intelligence system for retinopathy and maculopathy screening, was developed at Toku Eyes using routinely collected retinal screening datasets from two of the largest district health boards in Auckland, New Zealand: the Auckland District Health Board and the Counties Manukau District Health Board. All retinal images from consecutive individuals receiving retinal screening between January 2009 and December 2018 were used. Images were labelled as non-sight-threatening, potentially referable or sight-threatening for New Zealand implementation, or as referable (potentially referable + sight-threatening)/non-referable (non-sight-threatening) for global comparison.<h4>Results</h4>Data from 32 354 unique people with diabetes (63 843 when including multiple visits) were available, of which 95-97%, 0.9-2.4% and 1.1-3.1% were categorized as non-sight-threatening, potentially referable and sight-threatening, respectively. Using the referable/non-referable categories, THEIA achieved overall sensitivity of 94% (95% CI 92-95) in the Auckland District Health Board and 95% (95% CI 92-97) in the Counties Manukau District Health Board datasets, while preserving specificity of 63% (95% CI 62-64) for the Auckland District Health Board and 61% (95% CI 60-62) for the Counties Manukau District Health Board. Implementing THEIA into a New Zealand national diabetic screening programme could significantly reduce the manual grading load.<h4>Conclusion</h4>THEIA, an artificial intelligence tool to assist in clinical decision-making, tailored to the needs of the New Zealand national diabetic screening programme, delivered high sensitivity for detecting referable retinopathy within the multi-ethnic New Zealand population with diabetes.
dc.format.medium Print-Electronic
dc.language eng
dc.publisher Wiley
dc.relation.ispartofseries Diabetic medicine : a journal of the British Diabetic Association
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher.
dc.subject Retina
dc.subject Humans
dc.subject Diabetic Retinopathy
dc.subject Diabetes Mellitus
dc.subject Mass Screening
dc.subject Sensitivity and Specificity
dc.subject Retrospective Studies
dc.subject Algorithms
dc.subject Artificial Intelligence
dc.subject Image Processing, Computer-Assisted
dc.subject Adolescent
dc.subject Adult
dc.subject Aged
dc.subject Aged, 80 and over
dc.subject Middle Aged
dc.subject Child
dc.subject Triage
dc.subject New Zealand
dc.subject Female
dc.subject Male
dc.subject Young Adult
dc.subject Implementation Science
dc.subject Eye Disease and Disorders of Vision
dc.subject Diabetes
dc.subject Eye
dc.subject Metabolic and endocrine
dc.subject Science & Technology
dc.subject Life Sciences & Biomedicine
dc.subject Endocrinology & Metabolism
dc.subject VALIDATION
dc.subject PREVALENCE
dc.subject 1117 Public Health and Health Services
dc.subject 1103 Clinical Sciences
dc.subject 1701 Psychology
dc.title THEIA™ development, and testing of artificial intelligence-based primary triage of diabetic retinopathy screening images in New Zealand.
dc.type Journal Article
dc.identifier.doi 10.1111/dme.14386
pubs.issue 4
pubs.begin-page e14386
pubs.volume 38 2022-05-04T03:19:29Z
dc.rights.holder Copyright: The author en
dc.identifier.pmid 32794618 (pubmed)
pubs.publication-status Published
dc.rights.accessrights en
pubs.subtype Research Support, Non-U.S. Gov't
pubs.subtype research-article
pubs.subtype Evaluation Study
pubs.subtype Journal Article
pubs.elements-id 810457 Bioengineering Institute Medical and Health Sciences Science School of Computer Science Science Research School of Medicine Medicine Department ABI Associates Maurice Wilkins Centre (2010-2014) Optometry and Vision Science
dc.identifier.eissn 1464-5491
pubs.number ARTN e14386
pubs.record-created-at-source-date 2022-05-04 2020-09-27

Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record


Search ResearchSpace