Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning Approaches

Diabetes is a significant global health issue impacting millions. Approximately 26 million diabetics experience foot ulcers, with 20% ending up with amputations, resulting in high morbidity, mortality, and costs. Plantar pressure screening shows potential for early detection of Diabetic Foot Ulcers...

Full description

Saved in:
Bibliographic Details
Main Authors: Dipak Kumar Agrawal, Watcharin Jongpinit, Soodkhet Pojprapai, Wipawee Usaha, Pattra Wattanapan, Pornthep Tangkanjanavelukul, Timporn Vitoonpong
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Technologies
Subjects:
Online Access:https://www.mdpi.com/2227-7080/12/11/231
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850227888409804800
author Dipak Kumar Agrawal
Watcharin Jongpinit
Soodkhet Pojprapai
Wipawee Usaha
Pattra Wattanapan
Pornthep Tangkanjanavelukul
Timporn Vitoonpong
author_facet Dipak Kumar Agrawal
Watcharin Jongpinit
Soodkhet Pojprapai
Wipawee Usaha
Pattra Wattanapan
Pornthep Tangkanjanavelukul
Timporn Vitoonpong
author_sort Dipak Kumar Agrawal
collection DOAJ
description Diabetes is a significant global health issue impacting millions. Approximately 26 million diabetics experience foot ulcers, with 20% ending up with amputations, resulting in high morbidity, mortality, and costs. Plantar pressure screening shows potential for early detection of Diabetic Foot Ulcers (DFUs). Although foot ulcers often occur due to excessive pressure on the soles during dynamic activities, most studies focus on static pressure measurements. This study’s primary objective is to apply wireless plantar pressure sensor-embedded insoles to classify and detect diabetic feet from healthy ones based on dynamic plantar pressure. The secondary objective is to compare statistical-based and Machine Learning (ML) classification methods. Data from 150 subjects were collected from the insoles during walking, revealing that diabetic feet have higher plantar pressure than healthy feet, which is consistent with prior research. The Adaptive Boosting (AdaBoost) ML model achieved the highest accuracy of 0.85, outperforming the statistical method, which had an accuracy of 0.67. These findings suggest that ML models, combined with pressure sensor-embedded insoles, can effectively classify healthy and diabetic feet using plantar pressure features. Future research will focus on using these insoles with ML to classify various stages of diabetic neuropathy, aiming for early prediction of foot ulcers in home settings.
format Article
id doaj-art-6529323a6c4e4bf8bbd92240b28b842b
institution OA Journals
issn 2227-7080
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Technologies
spelling doaj-art-6529323a6c4e4bf8bbd92240b28b842b2025-08-20T02:04:41ZengMDPI AGTechnologies2227-70802024-11-01121123110.3390/technologies12110231Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning ApproachesDipak Kumar Agrawal0Watcharin Jongpinit1Soodkhet Pojprapai2Wipawee Usaha3Pattra Wattanapan4Pornthep Tangkanjanavelukul5Timporn Vitoonpong6School of Telecommunication Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandSchool of Ceramic Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandSchool of Ceramic Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandSchool of Telecommunication Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandDepartment of Rehabilitation Medicine, Khon Kaen University, Khon Kaen 40002, ThailandInstitute of Medicine, Suranaree University of Technology, Nakhon Ratchasima 30000, ThailandRehabilitation Department, Faculty of Medicine, Chulalongkorn University, Bangkok 10330, ThailandDiabetes is a significant global health issue impacting millions. Approximately 26 million diabetics experience foot ulcers, with 20% ending up with amputations, resulting in high morbidity, mortality, and costs. Plantar pressure screening shows potential for early detection of Diabetic Foot Ulcers (DFUs). Although foot ulcers often occur due to excessive pressure on the soles during dynamic activities, most studies focus on static pressure measurements. This study’s primary objective is to apply wireless plantar pressure sensor-embedded insoles to classify and detect diabetic feet from healthy ones based on dynamic plantar pressure. The secondary objective is to compare statistical-based and Machine Learning (ML) classification methods. Data from 150 subjects were collected from the insoles during walking, revealing that diabetic feet have higher plantar pressure than healthy feet, which is consistent with prior research. The Adaptive Boosting (AdaBoost) ML model achieved the highest accuracy of 0.85, outperforming the statistical method, which had an accuracy of 0.67. These findings suggest that ML models, combined with pressure sensor-embedded insoles, can effectively classify healthy and diabetic feet using plantar pressure features. Future research will focus on using these insoles with ML to classify various stages of diabetic neuropathy, aiming for early prediction of foot ulcers in home settings.https://www.mdpi.com/2227-7080/12/11/231diabetic footmachine learning algorithmsplantar pressurepressure sensorsmart insolestatistical analysis
spellingShingle Dipak Kumar Agrawal
Watcharin Jongpinit
Soodkhet Pojprapai
Wipawee Usaha
Pattra Wattanapan
Pornthep Tangkanjanavelukul
Timporn Vitoonpong
Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning Approaches
Technologies
diabetic foot
machine learning algorithms
plantar pressure
pressure sensor
smart insole
statistical analysis
title Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning Approaches
title_full Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning Approaches
title_fullStr Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning Approaches
title_full_unstemmed Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning Approaches
title_short Smart Insole-Based Plantar Pressure Analysis for Healthy and Diabetic Feet Classification: Statistical vs. Machine Learning Approaches
title_sort smart insole based plantar pressure analysis for healthy and diabetic feet classification statistical vs machine learning approaches
topic diabetic foot
machine learning algorithms
plantar pressure
pressure sensor
smart insole
statistical analysis
url https://www.mdpi.com/2227-7080/12/11/231
work_keys_str_mv AT dipakkumaragrawal smartinsolebasedplantarpressureanalysisforhealthyanddiabeticfeetclassificationstatisticalvsmachinelearningapproaches
AT watcharinjongpinit smartinsolebasedplantarpressureanalysisforhealthyanddiabeticfeetclassificationstatisticalvsmachinelearningapproaches
AT soodkhetpojprapai smartinsolebasedplantarpressureanalysisforhealthyanddiabeticfeetclassificationstatisticalvsmachinelearningapproaches
AT wipaweeusaha smartinsolebasedplantarpressureanalysisforhealthyanddiabeticfeetclassificationstatisticalvsmachinelearningapproaches
AT pattrawattanapan smartinsolebasedplantarpressureanalysisforhealthyanddiabeticfeetclassificationstatisticalvsmachinelearningapproaches
AT porntheptangkanjanavelukul smartinsolebasedplantarpressureanalysisforhealthyanddiabeticfeetclassificationstatisticalvsmachinelearningapproaches
AT timpornvitoonpong smartinsolebasedplantarpressureanalysisforhealthyanddiabeticfeetclassificationstatisticalvsmachinelearningapproaches