No Cover Image

Journal article 74 views 24 downloads

Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults

Connor Forbes, Alberto Coccarelli Orcid Logo, Zhiwei Xu, Robert D Meade, Glen P Kenny, Sebastian Binnewies, Aaron J E Bach

Journal of Thermal Biology, Volume: 128, Start page: 104078

Swansea University Author: Alberto Coccarelli Orcid Logo

  • 69082.VOR.pdf

    PDF | Version of Record

    © 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons CC-BY license.

    Download (10.47MB)

Check full text

DOI (Published version): 10.1016/j.jtherbio.2025.104078

Abstract

This study compares the efficacy of machine learning models to traditional biophysical models in predicting rectal (T ) and skin (T ) temperatures of older adults (≥60 years) during prolonged heat exposure. Five machine learning models were trained on data using 4-fold cross validation from 162 day-...

Full description

Published in: Journal of Thermal Biology
ISSN: 0306-4565 1879-0992
Published: Elsevier Ltd 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa69082
first_indexed 2025-03-12T12:29:16Z
last_indexed 2025-03-14T04:21:20Z
id cronfa69082
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-03-12T12:32:24.0839172</datestamp><bib-version>v2</bib-version><id>69082</id><entry>2025-03-12</entry><title>Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults</title><swanseaauthors><author><sid>06fd3332e5eb3cf4bb4e75a24f49149d</sid><ORCID>0000-0003-1511-9015</ORCID><firstname>Alberto</firstname><surname>Coccarelli</surname><name>Alberto Coccarelli</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-03-12</date><deptcode>ACEM</deptcode><abstract>This study compares the efficacy of machine learning models to traditional biophysical models in predicting rectal (T ) and skin (T ) temperatures of older adults (&#x2265;60 years) during prolonged heat exposure. Five machine learning models were trained on data using 4-fold cross validation from 162 day-long (8-9h) sessions involving 76 older adults across six environments, from thermoneutral to heatwave conditions. These models were compared to three biophysical models: the JOS-3 model, the Gagge two-node model, and an optimised two-node model. Our findings show that machine learning models, particularly ridge regression, outperformed biophysical models in prediction accuracy. The ridge regression model achieved a Root-Mean Squared Error (RMSE) of 0.27&#xA0;&#xB0;C for T , and 0.73&#xA0;&#xB0;C for T . Among the best biophysical models, the optimised two-node model achieved an RMSE of 0.40&#xA0;&#xB0;C for T , while JOS-3 achieved an RMSE of 0.74&#xA0;&#xB0;C for T . Of all models, ridge regression had the highest proportion of participants with T RMSEs within clinically meaningful thresholds at 70% (&lt;0.3&#xA0;&#xB0;C) and the highest proportion for T at 88% (&lt;1.0&#xA0;&#xB0;C), tied with the JOS-3 model. Our results suggest machine learning models better capture the complex thermoregulatory responses of older adults during prolonged heat exposure. The study highlights machine learning models' potential for personalised heat risk assessments and real-time predictions. Future research should expand upon training datasets, incorporate more dynamic conditions, and validate models in real-world settings. Integrating these models into home-based monitoring systems or wearable devices could enhance heat management strategies for older adults.</abstract><type>Journal Article</type><journal>Journal of Thermal Biology</journal><volume>128</volume><journalNumber/><paginationStart>104078</paginationStart><paginationEnd/><publisher>Elsevier Ltd</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0306-4565</issnPrint><issnElectronic>1879-0992</issnElectronic><keywords>Aged; Body temperature; Extreme heat; Heat stress disorders; Theoretical models</keywords><publishedDay>26</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-02-26</publishedDate><doi>10.1016/j.jtherbio.2025.104078</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>This research was funded by the Wellcome Trust (grant 224709/Z/21/Z: &#x2018;Individualised heat-health early warning systems: A novel digital solution&#x2019;, held by S. Rutherford, A. J. E. Bach, S. Binnewies). Funding for collection of physiological data was provided by the Canadian Institutes of Health Research (grant #399434 and PJT-180242, held by G. Kenny) and Health Canada (contract #4500387992, held by G. Kenny).</funders><projectreference/><lastEdited>2025-03-12T12:32:24.0839172</lastEdited><Created>2025-03-12T12:23:01.5741428</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Connor</firstname><surname>Forbes</surname><order>1</order></author><author><firstname>Alberto</firstname><surname>Coccarelli</surname><orcid>0000-0003-1511-9015</orcid><order>2</order></author><author><firstname>Zhiwei</firstname><surname>Xu</surname><order>3</order></author><author><firstname>Robert D</firstname><surname>Meade</surname><order>4</order></author><author><firstname>Glen P</firstname><surname>Kenny</surname><order>5</order></author><author><firstname>Sebastian</firstname><surname>Binnewies</surname><order>6</order></author><author><firstname>Aaron J E</firstname><surname>Bach</surname><order>7</order></author></authors><documents><document><filename>69082__33794__c03e6f127ee24732896345249c323dbe.pdf</filename><originalFilename>69082.VOR.pdf</originalFilename><uploaded>2025-03-12T12:27:45.5861620</uploaded><type>Output</type><contentLength>10974655</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons CC-BY license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-03-12T12:32:24.0839172 v2 69082 2025-03-12 Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults 06fd3332e5eb3cf4bb4e75a24f49149d 0000-0003-1511-9015 Alberto Coccarelli Alberto Coccarelli true false 2025-03-12 ACEM This study compares the efficacy of machine learning models to traditional biophysical models in predicting rectal (T ) and skin (T ) temperatures of older adults (≥60 years) during prolonged heat exposure. Five machine learning models were trained on data using 4-fold cross validation from 162 day-long (8-9h) sessions involving 76 older adults across six environments, from thermoneutral to heatwave conditions. These models were compared to three biophysical models: the JOS-3 model, the Gagge two-node model, and an optimised two-node model. Our findings show that machine learning models, particularly ridge regression, outperformed biophysical models in prediction accuracy. The ridge regression model achieved a Root-Mean Squared Error (RMSE) of 0.27 °C for T , and 0.73 °C for T . Among the best biophysical models, the optimised two-node model achieved an RMSE of 0.40 °C for T , while JOS-3 achieved an RMSE of 0.74 °C for T . Of all models, ridge regression had the highest proportion of participants with T RMSEs within clinically meaningful thresholds at 70% (<0.3 °C) and the highest proportion for T at 88% (<1.0 °C), tied with the JOS-3 model. Our results suggest machine learning models better capture the complex thermoregulatory responses of older adults during prolonged heat exposure. The study highlights machine learning models' potential for personalised heat risk assessments and real-time predictions. Future research should expand upon training datasets, incorporate more dynamic conditions, and validate models in real-world settings. Integrating these models into home-based monitoring systems or wearable devices could enhance heat management strategies for older adults. Journal Article Journal of Thermal Biology 128 104078 Elsevier Ltd 0306-4565 1879-0992 Aged; Body temperature; Extreme heat; Heat stress disorders; Theoretical models 26 2 2025 2025-02-26 10.1016/j.jtherbio.2025.104078 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University Another institution paid the OA fee This research was funded by the Wellcome Trust (grant 224709/Z/21/Z: ‘Individualised heat-health early warning systems: A novel digital solution’, held by S. Rutherford, A. J. E. Bach, S. Binnewies). Funding for collection of physiological data was provided by the Canadian Institutes of Health Research (grant #399434 and PJT-180242, held by G. Kenny) and Health Canada (contract #4500387992, held by G. Kenny). 2025-03-12T12:32:24.0839172 2025-03-12T12:23:01.5741428 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Connor Forbes 1 Alberto Coccarelli 0000-0003-1511-9015 2 Zhiwei Xu 3 Robert D Meade 4 Glen P Kenny 5 Sebastian Binnewies 6 Aaron J E Bach 7 69082__33794__c03e6f127ee24732896345249c323dbe.pdf 69082.VOR.pdf 2025-03-12T12:27:45.5861620 Output 10974655 application/pdf Version of Record true © 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons CC-BY license. true eng http://creativecommons.org/licenses/by/4.0/
title Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults
spellingShingle Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults
Alberto Coccarelli
title_short Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults
title_full Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults
title_fullStr Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults
title_full_unstemmed Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults
title_sort Biophysical versus machine learning models for predicting rectal and skin temperatures in older adults
author_id_str_mv 06fd3332e5eb3cf4bb4e75a24f49149d
author_id_fullname_str_mv 06fd3332e5eb3cf4bb4e75a24f49149d_***_Alberto Coccarelli
author Alberto Coccarelli
author2 Connor Forbes
Alberto Coccarelli
Zhiwei Xu
Robert D Meade
Glen P Kenny
Sebastian Binnewies
Aaron J E Bach
format Journal article
container_title Journal of Thermal Biology
container_volume 128
container_start_page 104078
publishDate 2025
institution Swansea University
issn 0306-4565
1879-0992
doi_str_mv 10.1016/j.jtherbio.2025.104078
publisher Elsevier Ltd
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 Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str 1
active_str 0
description This study compares the efficacy of machine learning models to traditional biophysical models in predicting rectal (T ) and skin (T ) temperatures of older adults (≥60 years) during prolonged heat exposure. Five machine learning models were trained on data using 4-fold cross validation from 162 day-long (8-9h) sessions involving 76 older adults across six environments, from thermoneutral to heatwave conditions. These models were compared to three biophysical models: the JOS-3 model, the Gagge two-node model, and an optimised two-node model. Our findings show that machine learning models, particularly ridge regression, outperformed biophysical models in prediction accuracy. The ridge regression model achieved a Root-Mean Squared Error (RMSE) of 0.27 °C for T , and 0.73 °C for T . Among the best biophysical models, the optimised two-node model achieved an RMSE of 0.40 °C for T , while JOS-3 achieved an RMSE of 0.74 °C for T . Of all models, ridge regression had the highest proportion of participants with T RMSEs within clinically meaningful thresholds at 70% (<0.3 °C) and the highest proportion for T at 88% (<1.0 °C), tied with the JOS-3 model. Our results suggest machine learning models better capture the complex thermoregulatory responses of older adults during prolonged heat exposure. The study highlights machine learning models' potential for personalised heat risk assessments and real-time predictions. Future research should expand upon training datasets, incorporate more dynamic conditions, and validate models in real-world settings. Integrating these models into home-based monitoring systems or wearable devices could enhance heat management strategies for older adults.
published_date 2025-02-26T08:18:33Z
_version_ 1829633328203956224
score 11.058267

Similar Items