A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection

KC, RACHANA; Yang, Scott

doi:10.1049/htl2.70060

Journal article 86 views 5 downloads

A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection

RACHANA KC, Scott Yang

Healthcare Technology Letters, Volume: 13, Issue: 1

Swansea University Authors: RACHANA KC, Scott Yang

PDF | Version of Record

© 2026 The Author(s). This is an open access article under the terms of the Creative Commons Attribution License.
Download (793.46KB)

Check full text

DOI (Published version): 10.1049/htl2.70060

Abstract

Diabetes has become a critical global health concern, particularly in regions where access to diagnostic facilities is limited. In this work, we propose a hybrid framework that combines extreme gradient boosting (XGBoost) and deep neural networks (DNNs) for early-stage diabetes detection, using soft...

Full description

Published in:	Healthcare Technology Letters
ISSN:	2053-3713 2053-3713
Published:	Institution of Engineering and Technology (IET) 2026
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa71382

first_indexed	2026-02-03T13:37:59Z
last_indexed	2026-02-28T05:41:35Z
id	cronfa71382
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2026-02-27T15:19:22.2623271</datestamp><bib-version>v2</bib-version><id>71382</id><entry>2026-02-03</entry><title>A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection</title><swanseaauthors><author><sid>3bde8733e79df1907dfeaf84f558f67c</sid><firstname>RACHANA</firstname><surname>KC</surname><name>RACHANA KC</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>81dc663ca0e68c60908d35b1d2ec3a9b</sid><ORCID>0000-0002-6618-7483</ORCID><firstname>Scott</firstname><surname>Yang</surname><name>Scott Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-02-03</date><abstract>Diabetes has become a critical global health concern, particularly in regions where access to diagnostic facilities is limited. In this work, we propose a hybrid framework that combines extreme gradient boosting (XGBoost) and deep neural networks (DNNs) for early-stage diabetes detection, using soft voting to generate the final ensemble predictions. The proposed framework was evaluated on two datasets: the widely used Diabetes UCI dataset and a newly collected dataset from Nepal. The ensemble method achieved 99% accuracy (ACC) with an area under the curve (AUC) of 1.00 on the Diabetes UCI dataset, and 91% ACC with a 0.96 AUC on the Nepal diabetes dataset, demonstrating its strong generalisability across distinct populations. Compared to individual models, the hybrid approach offered increased stability and a lower rate of false negatives, which is particularly important in clinical contexts. These findings highlight the potential of hybrid machine learning–deep learning models as cost-effective, scalable and generalisable decision-support tools for diabetes risk assessment.</abstract><type>Journal Article</type><journal>Healthcare Technology Letters</journal><volume>13</volume><journalNumber>1</journalNumber><paginationStart/><paginationEnd/><publisher>Institution of Engineering and Technology (IET)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2053-3713</issnPrint><issnElectronic>2053-3713</issnElectronic><keywords/><publishedDay>14</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-02-14</publishedDate><doi>10.1049/htl2.70060</doi><url/><notes>Letter</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Swansea University</funders><projectreference/><lastEdited>2026-02-27T15:19:22.2623271</lastEdited><Created>2026-02-03T13:35:27.0029641</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>RACHANA</firstname><surname>KC</surname><order>1</order></author><author><firstname>Scott</firstname><surname>Yang</surname><orcid>0000-0002-6618-7483</orcid><order>2</order></author></authors><documents><document><filename>71382__36327__9e0430f644ed40319642b191384c08e7.pdf</filename><originalFilename>71382.VoR.pdf</originalFilename><uploaded>2026-02-27T15:17:22.3944867</uploaded><type>Output</type><contentLength>812498</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2026 The Author(s). This is an open access article under the terms of the Creative Commons Attribution License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2026-02-27T15:19:22.2623271 v2 71382 2026-02-03 A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection 3bde8733e79df1907dfeaf84f558f67c RACHANA KC RACHANA KC true false 81dc663ca0e68c60908d35b1d2ec3a9b 0000-0002-6618-7483 Scott Yang Scott Yang true false 2026-02-03 Diabetes has become a critical global health concern, particularly in regions where access to diagnostic facilities is limited. In this work, we propose a hybrid framework that combines extreme gradient boosting (XGBoost) and deep neural networks (DNNs) for early-stage diabetes detection, using soft voting to generate the final ensemble predictions. The proposed framework was evaluated on two datasets: the widely used Diabetes UCI dataset and a newly collected dataset from Nepal. The ensemble method achieved 99% accuracy (ACC) with an area under the curve (AUC) of 1.00 on the Diabetes UCI dataset, and 91% ACC with a 0.96 AUC on the Nepal diabetes dataset, demonstrating its strong generalisability across distinct populations. Compared to individual models, the hybrid approach offered increased stability and a lower rate of false negatives, which is particularly important in clinical contexts. These findings highlight the potential of hybrid machine learning–deep learning models as cost-effective, scalable and generalisable decision-support tools for diabetes risk assessment. Journal Article Healthcare Technology Letters 13 1 Institution of Engineering and Technology (IET) 2053-3713 2053-3713 14 2 2026 2026-02-14 10.1049/htl2.70060 Letter COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) Swansea University 2026-02-27T15:19:22.2623271 2026-02-03T13:35:27.0029641 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science RACHANA KC 1 Scott Yang 0000-0002-6618-7483 2 71382__36327__9e0430f644ed40319642b191384c08e7.pdf 71382.VoR.pdf 2026-02-27T15:17:22.3944867 Output 812498 application/pdf Version of Record true © 2026 The Author(s). This is an open access article under the terms of the Creative Commons Attribution License. true eng http://creativecommons.org/licenses/by/4.0/
title	A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection
spellingShingle	A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection RACHANA KC Scott Yang
title_short	A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection
title_full	A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection
title_fullStr	A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection
title_full_unstemmed	A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection
title_sort	A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection
author_id_str_mv	3bde8733e79df1907dfeaf84f558f67c 81dc663ca0e68c60908d35b1d2ec3a9b
author_id_fullname_str_mv	3bde8733e79df1907dfeaf84f558f67c_*_RACHANA KC 81dc663ca0e68c60908d35b1d2ec3a9b_*_Scott Yang
author	RACHANA KC Scott Yang
author2	RACHANA KC Scott Yang
format	Journal article
container_title	Healthcare Technology Letters
container_volume	13
container_issue	1
publishDate	2026
institution	Swansea University
issn	2053-3713 2053-3713
doi_str_mv	10.1049/htl2.70060
publisher	Institution of Engineering and Technology (IET)
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str	1
active_str	0
description	Diabetes has become a critical global health concern, particularly in regions where access to diagnostic facilities is limited. In this work, we propose a hybrid framework that combines extreme gradient boosting (XGBoost) and deep neural networks (DNNs) for early-stage diabetes detection, using soft voting to generate the final ensemble predictions. The proposed framework was evaluated on two datasets: the widely used Diabetes UCI dataset and a newly collected dataset from Nepal. The ensemble method achieved 99% accuracy (ACC) with an area under the curve (AUC) of 1.00 on the Diabetes UCI dataset, and 91% ACC with a 0.96 AUC on the Nepal diabetes dataset, demonstrating its strong generalisability across distinct populations. Compared to individual models, the hybrid approach offered increased stability and a lower rate of false negatives, which is particularly important in clinical contexts. These findings highlight the potential of hybrid machine learning–deep learning models as cost-effective, scalable and generalisable decision-support tools for diabetes risk assessment.
published_date	2026-02-14T05:32:33Z
_version_	1860067239615528960
score	11.099794

A Hybrid Ensemble Approach for Early‐Stage Diabetes Detection

Similar Items