Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.

<h4>Background</h4>Diabetic retinopathy (DR) affects 10-24% of patients with diabetes mellitus type 1 or 2 in the primary care (PC) sector. As early detection is crucial for treatment, deep learning screening methods in PC setting could potentially aid in an accurate and timely diagnosis...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Larisa Wewetzer, Linda A Held, Jost Steinhäuser
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/bc6fd489bd594fc7aeafbd9d7a999f11
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bc6fd489bd594fc7aeafbd9d7a999f11
record_format	dspace
spelling	oai:doaj.org-article:bc6fd489bd594fc7aeafbd9d7a999f112021-12-02T20:15:06ZDiagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.1932-620310.1371/journal.pone.0255034https://doaj.org/article/bc6fd489bd594fc7aeafbd9d7a999f112021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0255034https://doaj.org/toc/1932-6203<h4>Background</h4>Diabetic retinopathy (DR) affects 10-24% of patients with diabetes mellitus type 1 or 2 in the primary care (PC) sector. As early detection is crucial for treatment, deep learning screening methods in PC setting could potentially aid in an accurate and timely diagnosis.<h4>Purpose</h4>The purpose of this meta-analysis was to determine the current state of knowledge regarding deep learning (DL) screening methods for DR in PC.<h4>Data sources</h4>A systematic literature search was conducted using Medline, Web of Science, and Scopus to identify suitable studies.<h4>Study selection</h4>Suitable studies were selected by two researchers independently. Studies assessing DL methods and the suitability of these screening systems (diagnostic parameters such as sensitivity and specificity, information on datasets and setting) in PC were selected. Excluded were studies focusing on lesions, applying conventional diagnostic imaging tools, conducted in secondary or tertiary care, and all publication types other than original research studies on human subjects.<h4>Data extraction</h4>The following data was extracted from included studies: authors, title, year of publication, objectives, participants, setting, type of intervention/method, reference standard, grading scale, outcome measures, dataset, risk of bias, and performance measures.<h4>Data synthesis and conclusion</h4>The summed sensitivity of all included studies was 87% and specificity was 90%. Given a prevalence of DR of 10% in patients with DM Type 2 in PC, the negative predictive value is 98% while the positive predictive value is 49%.<h4>Limitations</h4>Selected studies showed a high variation in sample size and quality and quantity of available data.Larisa WewetzerLinda A HeldJost SteinhäuserPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 8, p e0255034 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Larisa Wewetzer Linda A Held Jost Steinhäuser Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.
description	<h4>Background</h4>Diabetic retinopathy (DR) affects 10-24% of patients with diabetes mellitus type 1 or 2 in the primary care (PC) sector. As early detection is crucial for treatment, deep learning screening methods in PC setting could potentially aid in an accurate and timely diagnosis.<h4>Purpose</h4>The purpose of this meta-analysis was to determine the current state of knowledge regarding deep learning (DL) screening methods for DR in PC.<h4>Data sources</h4>A systematic literature search was conducted using Medline, Web of Science, and Scopus to identify suitable studies.<h4>Study selection</h4>Suitable studies were selected by two researchers independently. Studies assessing DL methods and the suitability of these screening systems (diagnostic parameters such as sensitivity and specificity, information on datasets and setting) in PC were selected. Excluded were studies focusing on lesions, applying conventional diagnostic imaging tools, conducted in secondary or tertiary care, and all publication types other than original research studies on human subjects.<h4>Data extraction</h4>The following data was extracted from included studies: authors, title, year of publication, objectives, participants, setting, type of intervention/method, reference standard, grading scale, outcome measures, dataset, risk of bias, and performance measures.<h4>Data synthesis and conclusion</h4>The summed sensitivity of all included studies was 87% and specificity was 90%. Given a prevalence of DR of 10% in patients with DM Type 2 in PC, the negative predictive value is 98% while the positive predictive value is 49%.<h4>Limitations</h4>Selected studies showed a high variation in sample size and quality and quantity of available data.
format	article
author	Larisa Wewetzer Linda A Held Jost Steinhäuser
author_facet	Larisa Wewetzer Linda A Held Jost Steinhäuser
author_sort	Larisa Wewetzer
title	Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.
title_short	Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.
title_full	Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.
title_fullStr	Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.
title_full_unstemmed	Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.
title_sort	diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-a meta-analysis.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/bc6fd489bd594fc7aeafbd9d7a999f11
work_keys_str_mv	AT larisawewetzer diagnosticperformanceofdeeplearningbasedscreeningmethodsfordiabeticretinopathyinprimarycareametaanalysis AT lindaaheld diagnosticperformanceofdeeplearningbasedscreeningmethodsfordiabeticretinopathyinprimarycareametaanalysis AT joststeinhauser diagnosticperformanceofdeeplearningbasedscreeningmethodsfordiabeticretinopathyinprimarycareametaanalysis
_version_	1718374606428962816

Diagnostic performance of deep-learning-based screening methods for diabetic retinopathy in primary care-A meta-analysis.

Ejemplares similares