A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy

Diabetic Retinopathy (DR) is the most common and insidious microvascular complication of diabetes, and can progress asymptomatically until a sudden loss of vision occurs. Although DR is prevalent nowadays, its prevention remains challenging. The multiple aim of this study was to predict the risk of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Michele Bernardini, Luca Romeo, Adriano Mancini, Emanuele Frontoni
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Predictive medicine diabetic retinopathy machine learning electronic health records Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/197e3abbfe0344f791335621c1322bb2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:197e3abbfe0344f791335621c1322bb2
record_format	dspace
spelling	oai:doaj.org-article:197e3abbfe0344f791335621c1322bb22021-11-18T00:00:59ZA Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy2169-353610.1109/ACCESS.2021.3127274https://doaj.org/article/197e3abbfe0344f791335621c1322bb22021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9611287/https://doaj.org/toc/2169-3536Diabetic Retinopathy (DR) is the most common and insidious microvascular complication of diabetes, and can progress asymptomatically until a sudden loss of vision occurs. Although DR is prevalent nowadays, its prevention remains challenging. The multiple aim of this study was to predict the risk of developing DR as diabetic complication (task 1) and, subsequently, temporally stratify the DR risk (task 2) using electronic health records data. To perform these objectives, a novel preprocessing procedure was designed to select both control and pathological patients, and moreover, a novel fully annotated/standardized 120K dataset from multiple diabetologic centers was provided. Globally, although the Extreme Gradient Boosting model offers satisfying predictive performance, the Random Forest model obtained the best predictive performance to solve task 1 and task 2, reaching the best Area Under the Precision-Recall Curve of 72.43 % and 84.38 %, respectively. Also the features importance extracted from the best Machine Learning (ML) models is provided. The proposed Artificial Intelligence-based solution was proven to be capable of generalizing across different diabetologic centers while ensuring high-interpretability. Moreover, the proposed ML solution is currently being adopted as a Clinical Decision Support System in several diabetologic centers for DR screening and follow-up purposes.Michele BernardiniLuca RomeoAdriano ManciniEmanuele FrontoniIEEEarticlePredictive medicinediabetic retinopathymachine learningelectronic health recordsElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 151864-151872 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Predictive medicine diabetic retinopathy machine learning electronic health records Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Predictive medicine diabetic retinopathy machine learning electronic health records Electrical engineering. Electronics. Nuclear engineering TK1-9971 Michele Bernardini Luca Romeo Adriano Mancini Emanuele Frontoni A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy
description	Diabetic Retinopathy (DR) is the most common and insidious microvascular complication of diabetes, and can progress asymptomatically until a sudden loss of vision occurs. Although DR is prevalent nowadays, its prevention remains challenging. The multiple aim of this study was to predict the risk of developing DR as diabetic complication (task 1) and, subsequently, temporally stratify the DR risk (task 2) using electronic health records data. To perform these objectives, a novel preprocessing procedure was designed to select both control and pathological patients, and moreover, a novel fully annotated/standardized 120K dataset from multiple diabetologic centers was provided. Globally, although the Extreme Gradient Boosting model offers satisfying predictive performance, the Random Forest model obtained the best predictive performance to solve task 1 and task 2, reaching the best Area Under the Precision-Recall Curve of 72.43 % and 84.38 %, respectively. Also the features importance extracted from the best Machine Learning (ML) models is provided. The proposed Artificial Intelligence-based solution was proven to be capable of generalizing across different diabetologic centers while ensuring high-interpretability. Moreover, the proposed ML solution is currently being adopted as a Clinical Decision Support System in several diabetologic centers for DR screening and follow-up purposes.
format	article
author	Michele Bernardini Luca Romeo Adriano Mancini Emanuele Frontoni
author_facet	Michele Bernardini Luca Romeo Adriano Mancini Emanuele Frontoni
author_sort	Michele Bernardini
title	A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy
title_short	A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy
title_full	A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy
title_fullStr	A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy
title_full_unstemmed	A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy
title_sort	clinical decision support system to stratify the temporal risk of diabetic retinopathy
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/197e3abbfe0344f791335621c1322bb2
work_keys_str_mv	AT michelebernardini aclinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy AT lucaromeo aclinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy AT adrianomancini aclinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy AT emanuelefrontoni aclinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy AT michelebernardini clinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy AT lucaromeo clinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy AT adrianomancini clinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy AT emanuelefrontoni clinicaldecisionsupportsystemtostratifythetemporalriskofdiabeticretinopathy
_version_	1718425209552240640

A Clinical Decision Support System to Stratify the Temporal Risk of Diabetic Retinopathy

Ejemplares similares