Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort

Abstract The purpose of the current study was to predict intraocular pressure (IOP) using color fundus photography with a deep learning (DL) model, or, systemic variables with a multivariate linear regression model (MLM), along with least absolute shrinkage and selection operator regression (LASSO),...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kaori Ishii, Ryo Asaoka, Takashi Omoto, Shingo Mitaki, Yuri Fujino, Hiroshi Murata, Keiichi Onoda, Atsushi Nagai, Shuhei Yamaguchi, Akira Obana, Masaki Tanito
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b2680dd513714f27bb02f72b461817bc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b2680dd513714f27bb02f72b461817bc
record_format	dspace
spelling	oai:doaj.org-article:b2680dd513714f27bb02f72b461817bc2021-12-02T13:30:22ZPredicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort10.1038/s41598-020-80839-42045-2322https://doaj.org/article/b2680dd513714f27bb02f72b461817bc2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-80839-4https://doaj.org/toc/2045-2322Abstract The purpose of the current study was to predict intraocular pressure (IOP) using color fundus photography with a deep learning (DL) model, or, systemic variables with a multivariate linear regression model (MLM), along with least absolute shrinkage and selection operator regression (LASSO), support vector machine (SVM), and Random Forest: (RF). Training dataset included 3883 examinations from 3883 eyes of 1945 subjects and testing dataset 289 examinations from 289 eyes from 146 subjects. With the training dataset, MLM was constructed to predict IOP using 35 systemic variables and 25 blood measurements. A DL model was developed to predict IOP from color fundus photographs. The prediction accuracy of each model was evaluated through the absolute error and the marginal R-squared (mR2), using the testing dataset. The mean absolute error with MLM was 2.29 mmHg, which was significantly smaller than that with DL (2.70 dB). The mR2 with MLM was 0.15, whereas that with DL was 0.0066. The mean absolute error (between 2.24 and 2.30 mmHg) and mR2 (between 0.11 and 0.15) with LASSO, SVM and RF were similar to or poorer than MLM. A DL model to predict IOP using color fundus photography proved far less accurate than MLM using systemic variables.Kaori IshiiRyo AsaokaTakashi OmotoShingo MitakiYuri FujinoHiroshi MurataKeiichi OnodaAtsushi NagaiShuhei YamaguchiAkira ObanaMasaki TanitoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kaori Ishii Ryo Asaoka Takashi Omoto Shingo Mitaki Yuri Fujino Hiroshi Murata Keiichi Onoda Atsushi Nagai Shuhei Yamaguchi Akira Obana Masaki Tanito Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort
description	Abstract The purpose of the current study was to predict intraocular pressure (IOP) using color fundus photography with a deep learning (DL) model, or, systemic variables with a multivariate linear regression model (MLM), along with least absolute shrinkage and selection operator regression (LASSO), support vector machine (SVM), and Random Forest: (RF). Training dataset included 3883 examinations from 3883 eyes of 1945 subjects and testing dataset 289 examinations from 289 eyes from 146 subjects. With the training dataset, MLM was constructed to predict IOP using 35 systemic variables and 25 blood measurements. A DL model was developed to predict IOP from color fundus photographs. The prediction accuracy of each model was evaluated through the absolute error and the marginal R-squared (mR2), using the testing dataset. The mean absolute error with MLM was 2.29 mmHg, which was significantly smaller than that with DL (2.70 dB). The mR2 with MLM was 0.15, whereas that with DL was 0.0066. The mean absolute error (between 2.24 and 2.30 mmHg) and mR2 (between 0.11 and 0.15) with LASSO, SVM and RF were similar to or poorer than MLM. A DL model to predict IOP using color fundus photography proved far less accurate than MLM using systemic variables.
format	article
author	Kaori Ishii Ryo Asaoka Takashi Omoto Shingo Mitaki Yuri Fujino Hiroshi Murata Keiichi Onoda Atsushi Nagai Shuhei Yamaguchi Akira Obana Masaki Tanito
author_facet	Kaori Ishii Ryo Asaoka Takashi Omoto Shingo Mitaki Yuri Fujino Hiroshi Murata Keiichi Onoda Atsushi Nagai Shuhei Yamaguchi Akira Obana Masaki Tanito
author_sort	Kaori Ishii
title	Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort
title_short	Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort
title_full	Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort
title_fullStr	Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort
title_full_unstemmed	Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort
title_sort	predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/b2680dd513714f27bb02f72b461817bc
work_keys_str_mv	AT kaoriishii predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT ryoasaoka predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT takashiomoto predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT shingomitaki predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT yurifujino predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT hiroshimurata predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT keiichionoda predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT atsushinagai predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT shuheiyamaguchi predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT akiraobana predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort AT masakitanito predictingintraocularpressureusingsystemicvariablesorfundusphotographywithdeeplearninginahealthexaminationcohort
_version_	1718392936181268480

Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort

Ejemplares similares