Loading…
Diabetes detection using deep learning techniques with oversampling and feature augmentation
•A deep learning model has been built to address the prediction of diabetes.•Variational auto encoder was trained for sample data augmentation.•Sparse auto encoder was trained for feature augmentation.•Results obtained demonstrate the powerful of the model using convolutional layers•A 92.31% of accu...
Saved in:
Published in: | Computer methods and programs in biomedicine 2021-04, Vol.202, p.105968-105968, Article 105968 |
---|---|
Main Authors: | , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c356t-a38f3a957e121101e2d9ae164c1109b45ee8effd72fc4238a179e028e10a14be3 |
---|---|
cites | cdi_FETCH-LOGICAL-c356t-a38f3a957e121101e2d9ae164c1109b45ee8effd72fc4238a179e028e10a14be3 |
container_end_page | 105968 |
container_issue | |
container_start_page | 105968 |
container_title | Computer methods and programs in biomedicine |
container_volume | 202 |
creator | García-Ordás, María Teresa Benavides, Carmen Benítez-Andrades, José Alberto Alaiz-Moretón, Héctor García-Rodríguez, Isaías |
description | •A deep learning model has been built to address the prediction of diabetes.•Variational auto encoder was trained for sample data augmentation.•Sparse auto encoder was trained for feature augmentation.•Results obtained demonstrate the powerful of the model using convolutional layers•A 92.31% of accuracy was obtained outperforming the state of the art techniques.
Background and objective: Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential.
Methods: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic people. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glucose or insulin level, blood pressure or age, has been evaluated.
Results: A 92.31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art.
Conclusions: Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals. |
doi_str_mv | 10.1016/j.cmpb.2021.105968 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2494279285</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0169260721000432</els_id><sourcerecordid>2494279285</sourcerecordid><originalsourceid>FETCH-LOGICAL-c356t-a38f3a957e121101e2d9ae164c1109b45ee8effd72fc4238a179e028e10a14be3</originalsourceid><addsrcrecordid>eNp9kMtOwzAQRS0EoqXwAyxQlmxS_IidWGKDylOqxAZ2SJbjTFpXeWEnRfw9jlJYsrE1njNXnoPQJcFLgom42S1N3eVLiikJD1yK7AjNSZbSOOWCH6N5gGRMBU5n6Mz7HcaYci5O0YwxwYhg2Rx93FudQw8-KsJpets20eBtswk1dFEF2jVjFXrbxn4OAfyy_TZq9-C8rrtqbOqmiErQ_eAg0sOmhqbXY9I5Oil15eHicC_Q--PD2-o5Xr8-vazu1rFhXPSxZlnJtOQpEErCZkALqYGIxIRK5gkHyKAsi5SWJqEs0ySVgGkGBGuS5MAW6HrK7Vw7frFXtfUGqko30A5e0UQmNJU04wGlE2pc672DUnXO1tp9K4LVaFXt1GhVjVbVZDUMXR3yh7yG4m_kV2MAbicAwpZ7C055Y6ExUFgXpKqitf_l_wAvIonh</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2494279285</pqid></control><display><type>article</type><title>Diabetes detection using deep learning techniques with oversampling and feature augmentation</title><source>ScienceDirect Journals</source><creator>García-Ordás, María Teresa ; Benavides, Carmen ; Benítez-Andrades, José Alberto ; Alaiz-Moretón, Héctor ; García-Rodríguez, Isaías</creator><creatorcontrib>García-Ordás, María Teresa ; Benavides, Carmen ; Benítez-Andrades, José Alberto ; Alaiz-Moretón, Héctor ; García-Rodríguez, Isaías</creatorcontrib><description>•A deep learning model has been built to address the prediction of diabetes.•Variational auto encoder was trained for sample data augmentation.•Sparse auto encoder was trained for feature augmentation.•Results obtained demonstrate the powerful of the model using convolutional layers•A 92.31% of accuracy was obtained outperforming the state of the art techniques.
Background and objective: Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential.
Methods: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic people. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glucose or insulin level, blood pressure or age, has been evaluated.
Results: A 92.31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art.
Conclusions: Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals.</description><identifier>ISSN: 0169-2607</identifier><identifier>EISSN: 1872-7565</identifier><identifier>DOI: 10.1016/j.cmpb.2021.105968</identifier><identifier>PMID: 33631638</identifier><language>eng</language><publisher>Ireland: Elsevier B.V</publisher><subject>Databases, Factual ; Deep Learning ; Detection ; Diabetes ; Diabetes Mellitus - diagnosis ; Humans ; Neural Networks, Computer ; Oversampling ; Sparse autoencoder ; Variational autoencoder</subject><ispartof>Computer methods and programs in biomedicine, 2021-04, Vol.202, p.105968-105968, Article 105968</ispartof><rights>2021 Elsevier B.V.</rights><rights>Copyright © 2021 Elsevier B.V. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c356t-a38f3a957e121101e2d9ae164c1109b45ee8effd72fc4238a179e028e10a14be3</citedby><cites>FETCH-LOGICAL-c356t-a38f3a957e121101e2d9ae164c1109b45ee8effd72fc4238a179e028e10a14be3</cites><orcidid>0000-0002-4450-349X ; 0000-0001-6572-1261</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33631638$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>García-Ordás, María Teresa</creatorcontrib><creatorcontrib>Benavides, Carmen</creatorcontrib><creatorcontrib>Benítez-Andrades, José Alberto</creatorcontrib><creatorcontrib>Alaiz-Moretón, Héctor</creatorcontrib><creatorcontrib>García-Rodríguez, Isaías</creatorcontrib><title>Diabetes detection using deep learning techniques with oversampling and feature augmentation</title><title>Computer methods and programs in biomedicine</title><addtitle>Comput Methods Programs Biomed</addtitle><description>•A deep learning model has been built to address the prediction of diabetes.•Variational auto encoder was trained for sample data augmentation.•Sparse auto encoder was trained for feature augmentation.•Results obtained demonstrate the powerful of the model using convolutional layers•A 92.31% of accuracy was obtained outperforming the state of the art techniques.
Background and objective: Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential.
Methods: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic people. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glucose or insulin level, blood pressure or age, has been evaluated.
Results: A 92.31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art.
Conclusions: Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals.</description><subject>Databases, Factual</subject><subject>Deep Learning</subject><subject>Detection</subject><subject>Diabetes</subject><subject>Diabetes Mellitus - diagnosis</subject><subject>Humans</subject><subject>Neural Networks, Computer</subject><subject>Oversampling</subject><subject>Sparse autoencoder</subject><subject>Variational autoencoder</subject><issn>0169-2607</issn><issn>1872-7565</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kMtOwzAQRS0EoqXwAyxQlmxS_IidWGKDylOqxAZ2SJbjTFpXeWEnRfw9jlJYsrE1njNXnoPQJcFLgom42S1N3eVLiikJD1yK7AjNSZbSOOWCH6N5gGRMBU5n6Mz7HcaYci5O0YwxwYhg2Rx93FudQw8-KsJpets20eBtswk1dFEF2jVjFXrbxn4OAfyy_TZq9-C8rrtqbOqmiErQ_eAg0sOmhqbXY9I5Oil15eHicC_Q--PD2-o5Xr8-vazu1rFhXPSxZlnJtOQpEErCZkALqYGIxIRK5gkHyKAsi5SWJqEs0ySVgGkGBGuS5MAW6HrK7Vw7frFXtfUGqko30A5e0UQmNJU04wGlE2pc672DUnXO1tp9K4LVaFXt1GhVjVbVZDUMXR3yh7yG4m_kV2MAbicAwpZ7C055Y6ExUFgXpKqitf_l_wAvIonh</recordid><startdate>202104</startdate><enddate>202104</enddate><creator>García-Ordás, María Teresa</creator><creator>Benavides, Carmen</creator><creator>Benítez-Andrades, José Alberto</creator><creator>Alaiz-Moretón, Héctor</creator><creator>García-Rodríguez, Isaías</creator><general>Elsevier B.V</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-4450-349X</orcidid><orcidid>https://orcid.org/0000-0001-6572-1261</orcidid></search><sort><creationdate>202104</creationdate><title>Diabetes detection using deep learning techniques with oversampling and feature augmentation</title><author>García-Ordás, María Teresa ; Benavides, Carmen ; Benítez-Andrades, José Alberto ; Alaiz-Moretón, Héctor ; García-Rodríguez, Isaías</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c356t-a38f3a957e121101e2d9ae164c1109b45ee8effd72fc4238a179e028e10a14be3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Databases, Factual</topic><topic>Deep Learning</topic><topic>Detection</topic><topic>Diabetes</topic><topic>Diabetes Mellitus - diagnosis</topic><topic>Humans</topic><topic>Neural Networks, Computer</topic><topic>Oversampling</topic><topic>Sparse autoencoder</topic><topic>Variational autoencoder</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>García-Ordás, María Teresa</creatorcontrib><creatorcontrib>Benavides, Carmen</creatorcontrib><creatorcontrib>Benítez-Andrades, José Alberto</creatorcontrib><creatorcontrib>Alaiz-Moretón, Héctor</creatorcontrib><creatorcontrib>García-Rodríguez, Isaías</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Computer methods and programs in biomedicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>García-Ordás, María Teresa</au><au>Benavides, Carmen</au><au>Benítez-Andrades, José Alberto</au><au>Alaiz-Moretón, Héctor</au><au>García-Rodríguez, Isaías</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Diabetes detection using deep learning techniques with oversampling and feature augmentation</atitle><jtitle>Computer methods and programs in biomedicine</jtitle><addtitle>Comput Methods Programs Biomed</addtitle><date>2021-04</date><risdate>2021</risdate><volume>202</volume><spage>105968</spage><epage>105968</epage><pages>105968-105968</pages><artnum>105968</artnum><issn>0169-2607</issn><eissn>1872-7565</eissn><abstract>•A deep learning model has been built to address the prediction of diabetes.•Variational auto encoder was trained for sample data augmentation.•Sparse auto encoder was trained for feature augmentation.•Results obtained demonstrate the powerful of the model using convolutional layers•A 92.31% of accuracy was obtained outperforming the state of the art techniques.
Background and objective: Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential.
Methods: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic people. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glucose or insulin level, blood pressure or age, has been evaluated.
Results: A 92.31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art.
Conclusions: Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals.</abstract><cop>Ireland</cop><pub>Elsevier B.V</pub><pmid>33631638</pmid><doi>10.1016/j.cmpb.2021.105968</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-4450-349X</orcidid><orcidid>https://orcid.org/0000-0001-6572-1261</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0169-2607 |
ispartof | Computer methods and programs in biomedicine, 2021-04, Vol.202, p.105968-105968, Article 105968 |
issn | 0169-2607 1872-7565 |
language | eng |
recordid | cdi_proquest_miscellaneous_2494279285 |
source | ScienceDirect Journals |
subjects | Databases, Factual Deep Learning Detection Diabetes Diabetes Mellitus - diagnosis Humans Neural Networks, Computer Oversampling Sparse autoencoder Variational autoencoder |
title | Diabetes detection using deep learning techniques with oversampling and feature augmentation |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T13%3A08%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Diabetes%20detection%20using%20deep%20learning%20techniques%20with%20oversampling%20and%20feature%20augmentation&rft.jtitle=Computer%20methods%20and%20programs%20in%20biomedicine&rft.au=Garc%C3%ADa-Ord%C3%A1s,%20Mar%C3%ADa%20Teresa&rft.date=2021-04&rft.volume=202&rft.spage=105968&rft.epage=105968&rft.pages=105968-105968&rft.artnum=105968&rft.issn=0169-2607&rft.eissn=1872-7565&rft_id=info:doi/10.1016/j.cmpb.2021.105968&rft_dat=%3Cproquest_cross%3E2494279285%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c356t-a38f3a957e121101e2d9ae164c1109b45ee8effd72fc4238a179e028e10a14be3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2494279285&rft_id=info:pmid/33631638&rfr_iscdi=true |