No Cover Image

Journal article 58 views 23 downloads

Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability

Mohammad Abedin

Expert Systems with Applications

Swansea University Author: Mohammad Abedin

  • 67278.VoR.pdf

    PDF | Version of Record

    © 2024 The Author(s). This is an open access article under the CC BY license.

    Download (3.65MB)

DOI (Published version): 10.1016/j.eswa.2024.124886

Abstract

In medical risk prediction, such as predicting heart disease, machine learning (ML) classifiers must achieve high accuracy, precision, and recall to minimize the chances of incorrect diagnoses or treatment recommendations. However, real-world datasets often have imbalanced data, which can affect cla...

Full description

Published in: Expert Systems with Applications
Published: Elsevier 2024
URI: https://cronfa.swan.ac.uk/Record/cronfa67278
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-08-01T09:06:44Z
last_indexed 2024-08-01T09:06:44Z
id cronfa67278
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>67278</id><entry>2024-08-01</entry><title>Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability</title><swanseaauthors><author><sid>4ed8c020eae0c9bec4f5d9495d86d415</sid><ORCID></ORCID><firstname>Mohammad</firstname><surname>Abedin</surname><name>Mohammad Abedin</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-08-01</date><deptcode>CBAE</deptcode><abstract>In medical risk prediction, such as predicting heart disease, machine learning (ML) classifiers must achieve high accuracy, precision, and recall to minimize the chances of incorrect diagnoses or treatment recommendations. However, real-world datasets often have imbalanced data, which can affect classifier performance. Traditional data balancing methods can lead to overfitting and underfitting, making it difficult to identify potential health risks accurately. Early prediction of heart attacks is of paramount importance, and researchers have developed ML-based systems to address this problem. However, much of the existing ML research is based on a single dataset, often ignoring performance evaluation across multiple datasets. As the demand for interpretable ML models grows, model interpretability becomes central to revealing insights and feature effects within predictive models. To address these challenges, we present a novel data balancing technique that uses a divide-and-conquer strategy with the -Means clustering algorithm to segment the dataset. The performance of our approach is highlighted through comparisons with established techniques, which demonstrate the superiority of our proposed method. To address the challenge of inter-dataset discrepancies, we use two different datasets. Our holistic pipeline, strengthened by the innovative balancing technique, effectively addresses performance discrepancies, culminating in a significant improvement from 81% to 90%. Furthermore, through advanced statistical analysis, it has been determined that the 95% confidence interval for the AUC metric of our method ranges from 0.8187 to 0.8411. This observation serves to underscore the consistency and reliability of our approach, demonstrating its ability to achieve high performance across a range of scenarios. Incorporating Explainable AI (XAI), we examine the feature rankings and their contributions within the best performing Random Forest model. While the domain expert feedback is consistent with the explanatory power of XAI, some differences remain. Nevertheless, a remarkable convergence in feature ranking and weighting is observed, bridging the insights from XAI tools and domain expert perspectives.</abstract><type>Journal Article</type><journal>Expert Systems with Applications</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>Elsevier</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>1</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-12-01</publishedDate><doi>10.1016/j.eswa.2024.124886</doi><url/><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Swansea University</funders><projectreference/><lastEdited>2024-08-01T10:09:41.4359705</lastEdited><Created>2024-08-01T10:01:52.7078722</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Accounting and Finance</level></path><authors><author><firstname>Mohammad</firstname><surname>Abedin</surname><orcid></orcid><order>1</order></author></authors><documents><document><filename>67278__31017__c0ba97c997cd45b8992c03f061f8b45a.pdf</filename><originalFilename>67278.VoR.pdf</originalFilename><uploaded>2024-08-01T10:06:56.0115302</uploaded><type>Output</type><contentLength>3826972</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2024 The Author(s). This is an open access article under the CC BY license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 67278 2024-08-01 Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability 4ed8c020eae0c9bec4f5d9495d86d415 Mohammad Abedin Mohammad Abedin true false 2024-08-01 CBAE In medical risk prediction, such as predicting heart disease, machine learning (ML) classifiers must achieve high accuracy, precision, and recall to minimize the chances of incorrect diagnoses or treatment recommendations. However, real-world datasets often have imbalanced data, which can affect classifier performance. Traditional data balancing methods can lead to overfitting and underfitting, making it difficult to identify potential health risks accurately. Early prediction of heart attacks is of paramount importance, and researchers have developed ML-based systems to address this problem. However, much of the existing ML research is based on a single dataset, often ignoring performance evaluation across multiple datasets. As the demand for interpretable ML models grows, model interpretability becomes central to revealing insights and feature effects within predictive models. To address these challenges, we present a novel data balancing technique that uses a divide-and-conquer strategy with the -Means clustering algorithm to segment the dataset. The performance of our approach is highlighted through comparisons with established techniques, which demonstrate the superiority of our proposed method. To address the challenge of inter-dataset discrepancies, we use two different datasets. Our holistic pipeline, strengthened by the innovative balancing technique, effectively addresses performance discrepancies, culminating in a significant improvement from 81% to 90%. Furthermore, through advanced statistical analysis, it has been determined that the 95% confidence interval for the AUC metric of our method ranges from 0.8187 to 0.8411. This observation serves to underscore the consistency and reliability of our approach, demonstrating its ability to achieve high performance across a range of scenarios. Incorporating Explainable AI (XAI), we examine the feature rankings and their contributions within the best performing Random Forest model. While the domain expert feedback is consistent with the explanatory power of XAI, some differences remain. Nevertheless, a remarkable convergence in feature ranking and weighting is observed, bridging the insights from XAI tools and domain expert perspectives. Journal Article Expert Systems with Applications Elsevier 1 12 2024 2024-12-01 10.1016/j.eswa.2024.124886 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University SU Library paid the OA fee (TA Institutional Deal) Swansea University 2024-08-01T10:09:41.4359705 2024-08-01T10:01:52.7078722 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Mohammad Abedin 1 67278__31017__c0ba97c997cd45b8992c03f061f8b45a.pdf 67278.VoR.pdf 2024-08-01T10:06:56.0115302 Output 3826972 application/pdf Version of Record true © 2024 The Author(s). This is an open access article under the CC BY license. true eng http://creativecommons.org/licenses/by/4.0/
title Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability
spellingShingle Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability
Mohammad Abedin
title_short Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability
title_full Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability
title_fullStr Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability
title_full_unstemmed Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability
title_sort Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability
author_id_str_mv 4ed8c020eae0c9bec4f5d9495d86d415
author_id_fullname_str_mv 4ed8c020eae0c9bec4f5d9495d86d415_***_Mohammad Abedin
author Mohammad Abedin
author2 Mohammad Abedin
format Journal article
container_title Expert Systems with Applications
publishDate 2024
institution Swansea University
doi_str_mv 10.1016/j.eswa.2024.124886
publisher Elsevier
college_str Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id facultyofhumanitiesandsocialsciences
hierarchy_top_title Faculty of Humanities and Social Sciences
hierarchy_parent_id facultyofhumanitiesandsocialsciences
hierarchy_parent_title Faculty of Humanities and Social Sciences
department_str School of Management - Accounting and Finance{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Accounting and Finance
document_store_str 1
active_str 0
description In medical risk prediction, such as predicting heart disease, machine learning (ML) classifiers must achieve high accuracy, precision, and recall to minimize the chances of incorrect diagnoses or treatment recommendations. However, real-world datasets often have imbalanced data, which can affect classifier performance. Traditional data balancing methods can lead to overfitting and underfitting, making it difficult to identify potential health risks accurately. Early prediction of heart attacks is of paramount importance, and researchers have developed ML-based systems to address this problem. However, much of the existing ML research is based on a single dataset, often ignoring performance evaluation across multiple datasets. As the demand for interpretable ML models grows, model interpretability becomes central to revealing insights and feature effects within predictive models. To address these challenges, we present a novel data balancing technique that uses a divide-and-conquer strategy with the -Means clustering algorithm to segment the dataset. The performance of our approach is highlighted through comparisons with established techniques, which demonstrate the superiority of our proposed method. To address the challenge of inter-dataset discrepancies, we use two different datasets. Our holistic pipeline, strengthened by the innovative balancing technique, effectively addresses performance discrepancies, culminating in a significant improvement from 81% to 90%. Furthermore, through advanced statistical analysis, it has been determined that the 95% confidence interval for the AUC metric of our method ranges from 0.8187 to 0.8411. This observation serves to underscore the consistency and reliability of our approach, demonstrating its ability to achieve high performance across a range of scenarios. Incorporating Explainable AI (XAI), we examine the feature rankings and their contributions within the best performing Random Forest model. While the domain expert feedback is consistent with the explanatory power of XAI, some differences remain. Nevertheless, a remarkable convergence in feature ranking and weighting is observed, bridging the insights from XAI tools and domain expert perspectives.
published_date 2024-12-01T10:09:42Z
_version_ 1806175706523107328
score 11.021648

Similar Items