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

Journal: Journal of thermal biology
PMID:

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-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.

Authors

  • Connor Forbes
    School of Information and Communication Technology, Griffith University, Gold Coast, Australia.
  • Alberto Coccarelli
    Zienkiewicz Institute for Modelling, AI and Data, Mechanical Engineering Department, Faculty of Science and Engineering, Swansea University, Swansea, UK.
  • Zhiwei Xu
    Department of General Surgery, Pancreatic Disease Center, Ruijin Hospital Shanghai Jiaotong University School of Medicine, Shanghai, China. xuzhiwei10800@163.com.
  • Robert D Meade
    Human and Environmental Physiology Research Unit, School of Human Kinetics, University of Ottawa, Ottawa, Canada; Harvard T.H. Chan School of Public Health, Harvard University, Boston, United States.
  • Glen P Kenny
    Human and Environmental Physiology Research Unit, School of Human Kinetics, University of Ottawa, Ottawa, Canada.
  • Sebastian Binnewies
    School of Information and Communication Technology, Griffith University, Gold Coast, Australia.
  • Aaron J E Bach
    Cities Research Institute, Griffith University, Gold Coast, Australia; School of Health Sciences and Social Work, Griffith University, Gold Coast, Australia. Electronic address: a.bach@griffith.edu.au.