Can the Plantar Pressure and Temperature Data Trend Show the Presence of Diabetes? - A Comparative Study of a Variety of Machine Learning Techniques

Aug 2, 2026

Upload by Aria

This study explores diabetes prediction by analyzing trends in plantar thermal and plantar pressure data, used separately or together, across multiple machine learning techniques. Twenty-six participants—thirteen with diabetes and thirteen healthy—walked a 20 m path while in-shoe pressure and plantar temperature (pre/post) were recorded; each trial was repeated three times and averaged. Three experiments assessed correlations, standalone prediction, and multimodal prediction. Using 20 regression models and 16 classification algorithms with five-fold cross-validation, results showed weak cross-modality correlations but strong predictive gains when temperature and pressure were combined, with the Extra Trees Classifier reaching the highest accuracy (93.75%).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

Abstract

Introduction

Diabetes and its clinical challenges

Wearable sensors and multimodal data

Methods

Study design and data collection

Experiments and modeling strategy

Evaluation protocol

algorithms Article Can the Plantar Pressure and Temperature Data Trend Show the Presence of Diabetes? A Comparative Study of a Variety of Machine Learning Techniques Eduardo A. Gerlein 1, *, Francisco Calderón 1, Martha Zequera-Díaz 1 and Roozbeh Naemi 2,3, * Citation: Gerlein, E.A.; Calderón, F.; Zequera-Díaz, M.; Naemi, R. Can the Plantar Pressure and Temperature Data Trend Show the Presence of Diabetes? A Comparative Study of a Variety of Machine Learning Techniques. Algorithms 2024, 17, 519 . [https://doi.org/10.3390/a17110519](https://doi.org/10.3390/a17110519) Academic Editor: Maryam Ravan Received: 9 September 2024 Revised: 20 October 2024 Accepted: 25 October 2024 Published: 12 November 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Electronics, Pontificia Universidad Javeriana, Bogotá 110231, Colombia; [calderonf@javeriana.edu.co](calderonf@javeriana.edu.co) (F.C.); [mzequera@javeriana.edu.co](mzequera@javeriana.edu.co) (M.Z.-D.) 2 School of Health and Society, University of Salford, Manchester M6 6PU, UK 3 School of Health Science and Wellbeing, Staffordshire University, Stoke on Trent ST4 2DF, UK * Correspondence: [egerlein@javeriana.edu.co](egerlein@javeriana.edu.co) (E.A.G.); [r.naemi@salford.ac.uk](r.naemi@salford.ac.uk) (R.N.) Abstract: This study aimed to explore the potential of predicting diabetes by analyzing trends in plantar thermal and plantar pressure data, either individually or in combination, using various machine learning techniques. A total of twenty-six participants, comprising thirteen individuals diagnosed with diabetes and thirteen healthy individuals, walked along a 20 m path. In-shoe plantar pressure data were collected and the plantar temperature was measured both immediately before and after the walk. Each participant completed the trial three times, and the average data between the trials were calculated. The research was divided into three experiments: the first evaluated the correlations between the plantar pressure and temperature data; the second focused on predicting diabetes using each data type independently; and the third combined both data types and assessed the effect of such to enhance the predictive accuracy. For the experiments, 20 regression models and 16 classification algorithms were employed, and the performance was evaluated using a five-fold cross-validation strategy. The outcomes of the initial set of experiments indicated that the machine learning models were significant correlations between the thermal data and pressure estimates. This was consistent with the findings from the prior correlation analysis, which showed weak relationships between these two data modalities. However, a shift in focus towards predicting diabetes by aggregating the temperature and pressure data led to encouraging results, demonstrating the effectiveness of this approach in accurately predicting the presence of diabetes. The analysis revealed that, while several classifiers demonstrated reasonable metrics when using standalone variables, the integration of thermal and pressure data significantly improved the predictive accuracy. Specifically, when only plantar pressure data were used, the Logistic Regression model achieved the highest accuracy at 68.75% . Those predictions based solely on temperature data showed the Naive Bayes model as the lead with an accuracy of 87.5% . Notably, the highest accuracy of 93.75% was observed when both the temperature and pressure data were combined, with the Extra Trees Classifier performing the best. These results suggest that combining temperature and pressure data enhances the model’s predictive accura

FAQs

How were the plantar pressure and temperature data collected in the study?

Twenty-six participants walked a 20 m path while in-shoe plantar pressure was recorded and plantar temperature was measured immediately before and after the walk. Each participant completed the trial three times and averaged the data across trials.

What experiments were conducted to evaluate diabetes prediction?

The work was divided into three experiments: correlation analysis between pressure and temperature, prediction using each modality independently, and a combined-modality experiment to test whether integration improves predictive accuracy.

Which approach achieved the best diabetes prediction accuracy?

Combining plantar temperature and pressure produced the highest accuracy at 93.75%, with the Extra Trees Classifier performing best among the evaluated models.

Aug 2, 2026

Upload by Aria