Application of random forests methods to diabetic retinopathy classification analyses.

<h4>Background</h4>Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic inter...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ramon Casanova, Santiago Saldana, Emily Y Chew, Ronald P Danis, Craig M Greven, Walter T Ambrosius
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2014
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f08a9a45e69c4322b8494c042fce73a9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f08a9a45e69c4322b8494c042fce73a9
record_format	dspace
spelling	oai:doaj.org-article:f08a9a45e69c4322b8494c042fce73a92021-11-18T08:15:08ZApplication of random forests methods to diabetic retinopathy classification analyses.1932-620310.1371/journal.pone.0098587https://doaj.org/article/f08a9a45e69c4322b8494c042fce73a92014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24940623/pdf/?tool=EBIhttps://doaj.org/toc/1932-6203<h4>Background</h4>Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate its effects.<h4>Methodology</h4>Graded fundus photography and systemic data from 3443 ACCORD-Eye Study participants were used to estimate Random Forest (RF) and logistic regression classifiers. We studied the impact of sample size on classifier performance and the possibility of using RF generated class conditional probabilities as metrics describing DR risk. RF measures of variable importance are used to detect factors that affect classification performance.<h4>Principal findings</h4>Both types of data were informative when discriminating participants with or without DR. RF based models produced much higher classification accuracy than those based on logistic regression. Combining both types of data did not increase accuracy but did increase statistical discrimination of healthy participants who subsequently did or did not have DR events during four years of follow-up. RF variable importance criteria revealed that microaneurysms counts in both eyes seemed to play the most important role in discrimination among the graded fundus variables, while the number of medicines and diabetes duration were the most relevant among the systemic variables.<h4>Conclusions and significance</h4>We have introduced RF methods to DR classification analyses based on fundus photography data. In addition, we propose an approach to DR risk assessment based on metrics derived from graded fundus photography and systemic data. Our results suggest that RF methods could be a valuable tool to diagnose DR diagnosis and evaluate its progression.Ramon CasanovaSantiago SaldanaEmily Y ChewRonald P DanisCraig M GrevenWalter T AmbrosiusPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 6, p e98587 (2014)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ramon Casanova Santiago Saldana Emily Y Chew Ronald P Danis Craig M Greven Walter T Ambrosius Application of random forests methods to diabetic retinopathy classification analyses.
description	<h4>Background</h4>Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate its effects.<h4>Methodology</h4>Graded fundus photography and systemic data from 3443 ACCORD-Eye Study participants were used to estimate Random Forest (RF) and logistic regression classifiers. We studied the impact of sample size on classifier performance and the possibility of using RF generated class conditional probabilities as metrics describing DR risk. RF measures of variable importance are used to detect factors that affect classification performance.<h4>Principal findings</h4>Both types of data were informative when discriminating participants with or without DR. RF based models produced much higher classification accuracy than those based on logistic regression. Combining both types of data did not increase accuracy but did increase statistical discrimination of healthy participants who subsequently did or did not have DR events during four years of follow-up. RF variable importance criteria revealed that microaneurysms counts in both eyes seemed to play the most important role in discrimination among the graded fundus variables, while the number of medicines and diabetes duration were the most relevant among the systemic variables.<h4>Conclusions and significance</h4>We have introduced RF methods to DR classification analyses based on fundus photography data. In addition, we propose an approach to DR risk assessment based on metrics derived from graded fundus photography and systemic data. Our results suggest that RF methods could be a valuable tool to diagnose DR diagnosis and evaluate its progression.
format	article
author	Ramon Casanova Santiago Saldana Emily Y Chew Ronald P Danis Craig M Greven Walter T Ambrosius
author_facet	Ramon Casanova Santiago Saldana Emily Y Chew Ronald P Danis Craig M Greven Walter T Ambrosius
author_sort	Ramon Casanova
title	Application of random forests methods to diabetic retinopathy classification analyses.
title_short	Application of random forests methods to diabetic retinopathy classification analyses.
title_full	Application of random forests methods to diabetic retinopathy classification analyses.
title_fullStr	Application of random forests methods to diabetic retinopathy classification analyses.
title_full_unstemmed	Application of random forests methods to diabetic retinopathy classification analyses.
title_sort	application of random forests methods to diabetic retinopathy classification analyses.
publisher	Public Library of Science (PLoS)
publishDate	2014
url	https://doaj.org/article/f08a9a45e69c4322b8494c042fce73a9
work_keys_str_mv	AT ramoncasanova applicationofrandomforestsmethodstodiabeticretinopathyclassificationanalyses AT santiagosaldana applicationofrandomforestsmethodstodiabeticretinopathyclassificationanalyses AT emilyychew applicationofrandomforestsmethodstodiabeticretinopathyclassificationanalyses AT ronaldpdanis applicationofrandomforestsmethodstodiabeticretinopathyclassificationanalyses AT craigmgreven applicationofrandomforestsmethodstodiabeticretinopathyclassificationanalyses AT waltertambrosius applicationofrandomforestsmethodstodiabeticretinopathyclassificationanalyses
_version_	1718422020283170816

Application of random forests methods to diabetic retinopathy classification analyses.

Ejemplares similares