Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network

Bo Su Department of Endocrinology, Aviation General Hospital, Beijing, 100012, People’s Republic of ChinaCorrespondence: Bo SuDepartment of Endocrinology, Aviation General Hospital, China Medical University, Beijing, 100012, People’s Republic of ChinaTel +8613439927892Email sss_19@163.comPurpose: Ti...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Su B
Formato:	article
Lenguaje:	EN
Publicado:	Dove Medical Press 2021
Materias:	diabetic retinopathy type 2 diabetes probability threshold bp-ann Specialties of internal medicine RC581-951
Acceso en línea:	https://doaj.org/article/b6ffc5519a814059a03fe15282f4d514
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b6ffc5519a814059a03fe15282f4d514
record_format	dspace
spelling	oai:doaj.org-article:b6ffc5519a814059a03fe15282f4d5142021-12-02T17:42:13ZUsing Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network1178-7007https://doaj.org/article/b6ffc5519a814059a03fe15282f4d5142021-09-01T00:00:00Zhttps://www.dovepress.com/using-metabolic-and-biochemical-indicators-to-predict-diabetic-retinop-peer-reviewed-fulltext-article-DMSOhttps://doaj.org/toc/1178-7007Bo Su Department of Endocrinology, Aviation General Hospital, Beijing, 100012, People’s Republic of ChinaCorrespondence: Bo SuDepartment of Endocrinology, Aviation General Hospital, China Medical University, Beijing, 100012, People’s Republic of ChinaTel +8613439927892Email sss_19@163.comPurpose: Timely diagnosis of diabetic retinopathy (DR) can significantly improve the prognosis of patients. In this study, we established a prediction model by analyzing the relationship between diabetic retinopathy and related metabolic and biochemical indicators.Methods: A total of 427 type 2 diabetes mellitus (T2DM) patients were selected from the datadryad website data. Logistic regression (MLR) was used to input layer variables of the model were screened. Then, Tan-Sigmoid was selected as the transfer function of the hidden layer node, and the linear function was used as the output layer function to establish the back propagation artificial neural network (BP-ANN) model. The model was applied to 183 patients with type 2 diabetes mellitus (T2DM) in our hospital to predict DR.Results: A total of 167 patients (39.2%) with DR were obtained from the Datadryad database. Input variables were screened by MLR model, and it was concluded that the age, sex, albumin and creatinine, diabetes course were independently associated with the occurrence of DR. The above variables were used to establish BP-ANN model. The area under receiver operating characteristic curve (AUC) was significantly higher than that of MLR model (0.88 vs 0.74, P< 0.05), the probability threshold of the model was 0.3. Type 2 diabetes mellitus (T2DM) were selected in our hospital, including 92 patients with DR (50.2%). The above BP-ANN model was used to predict the incidence of DR, and the AUC area was significantly higher than that of the MLR model (0.77 vs 0.70, P< 0.05), the probability threshold was 0.7.Conclusion: We established the BP-ANN model and applied it to diagnose DR. Taking diabetic course, age, sex, albumin and creatinine as the inputs of BP-ANN, the existence of DR could be well predicted. Meanwhile, the generalization ability of the model could be improved by selecting different probability thresholds in different ROC curves.Keywords: diabetic retinopathy, type 2 diabetes, probability threshold, BP-ANNSu BDove Medical Pressarticlediabetic retinopathytype 2 diabetesprobability thresholdbp-annSpecialties of internal medicineRC581-951ENDiabetes, Metabolic Syndrome and Obesity: Targets and Therapy, Vol Volume 14, Pp 4031-4041 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	diabetic retinopathy type 2 diabetes probability threshold bp-ann Specialties of internal medicine RC581-951
spellingShingle	diabetic retinopathy type 2 diabetes probability threshold bp-ann Specialties of internal medicine RC581-951 Su B Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network
description	Bo Su Department of Endocrinology, Aviation General Hospital, Beijing, 100012, People’s Republic of ChinaCorrespondence: Bo SuDepartment of Endocrinology, Aviation General Hospital, China Medical University, Beijing, 100012, People’s Republic of ChinaTel +8613439927892Email sss_19@163.comPurpose: Timely diagnosis of diabetic retinopathy (DR) can significantly improve the prognosis of patients. In this study, we established a prediction model by analyzing the relationship between diabetic retinopathy and related metabolic and biochemical indicators.Methods: A total of 427 type 2 diabetes mellitus (T2DM) patients were selected from the datadryad website data. Logistic regression (MLR) was used to input layer variables of the model were screened. Then, Tan-Sigmoid was selected as the transfer function of the hidden layer node, and the linear function was used as the output layer function to establish the back propagation artificial neural network (BP-ANN) model. The model was applied to 183 patients with type 2 diabetes mellitus (T2DM) in our hospital to predict DR.Results: A total of 167 patients (39.2%) with DR were obtained from the Datadryad database. Input variables were screened by MLR model, and it was concluded that the age, sex, albumin and creatinine, diabetes course were independently associated with the occurrence of DR. The above variables were used to establish BP-ANN model. The area under receiver operating characteristic curve (AUC) was significantly higher than that of MLR model (0.88 vs 0.74, P< 0.05), the probability threshold of the model was 0.3. Type 2 diabetes mellitus (T2DM) were selected in our hospital, including 92 patients with DR (50.2%). The above BP-ANN model was used to predict the incidence of DR, and the AUC area was significantly higher than that of the MLR model (0.77 vs 0.70, P< 0.05), the probability threshold was 0.7.Conclusion: We established the BP-ANN model and applied it to diagnose DR. Taking diabetic course, age, sex, albumin and creatinine as the inputs of BP-ANN, the existence of DR could be well predicted. Meanwhile, the generalization ability of the model could be improved by selecting different probability thresholds in different ROC curves.Keywords: diabetic retinopathy, type 2 diabetes, probability threshold, BP-ANN
format	article
author	Su B
author_facet	Su B
author_sort	Su B
title	Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network
title_short	Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network
title_full	Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network
title_fullStr	Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network
title_full_unstemmed	Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network
title_sort	using metabolic and biochemical indicators to predict diabetic retinopathy by back-propagation artificial neural network
publisher	Dove Medical Press
publishDate	2021
url	https://doaj.org/article/b6ffc5519a814059a03fe15282f4d514
work_keys_str_mv	AT sub usingmetabolicandbiochemicalindicatorstopredictdiabeticretinopathybybackpropagationartificialneuralnetwork
_version_	1718379663801188352

Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network

Ejemplares similares