EUVIMEDEUVIMED entdecken
Open Access

Digital infrared thermography and machine learning for diabetic foot assessment: thermal patterns and classification

Rogelio Castillo-Morquecho, Edgar Guevara, Jose Luis Ramirez-GarciaLuna, Mario Aurelio Martínez-Jiménez, María Guadalupe Medina-Rangel, Eleazar Samuel Kolosovas-Machuca iD

Journal of Diabetes & Metabolic Disorders · 12.06.2024 · 23 (2) · 1967-1976

DOI: 10.1007/s40200-024-01452-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Diabetes & Metabolic Disorders, online erschienen am 12.06.2024. Verfasst von Rogelio Castillo-Morquecho und 5 weiteren Autor:innen. Beteiligte Einrichtung: Coordinación para la Innovación y Aplicación de la Ciencia y la Tecnología, Universidad Autónoma San Luis Potosí, San Luis Potosí, SLP Mexico. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Digital infrared thermography is a noninvasive tool used for assessing diseases, including the diabetic foot. This study aims to analyze thermal patterns of the foot sole in patients with type 2 diabetes mellitus using thermography and explore correlations with clinical variables. Additionally, a machine learning approach was developed for classification.

Methods

A total of 23 diabetic patients and 27 age- and sex-matched controls were included. Thermograms of the plantar foot surface were acquired and segmented into regions of interest. Mean foot temperature and temperature change index were calculated from predefined regions of interest. Pearson's correlation analysis was conducted for temperature measures, glycated hemoglobin, and body mass index. A two-layered cross-validation model using principal component analysis and support vector machines were employed for classification.

Results

Significant positive correlations were found between mean foot temperature and glycated hemoglobin (ρ = 0.44, p = 0.0015), as well as between mean foot temperature and body mass index (ρ = 0.35, p = 0.013). Temperature change index did not show significant correlations with clinical variables. The machine learning model achieved high overall accuracy (90%) and specificity (100%) with a moderate sensitivity (78.3%) for classifying diabetic and control groups based on thermal data.

Conclusions

Thermography combined with machine learning shows potential for assessing diabetic foot complications. Correlations between mean foot temperature and clinical variables suggest foot temperature changes as potential indicators. The machine learning model demonstrates promising accuracy for classification, suitable for screening purposes. Further research is needed to understand underlying mechanisms and establish clinical utility in diagnosing and managing diabetic foot complications.

Schlagwörter

Stichwörter der Autor:innen

Diabetes mellitusDiabetic footDigital infrared thermographyMachine learningPrincipal component analysisSupport vector machine

Autor:innen und Institutionen

  • Coordinación para la Innovación y Aplicación de la Ciencia y la Tecnología, Universidad Autónoma San Luis Potosí, San Luis Potosí, SLP Mexico.
  • CONAHCYT-Universidad Autónoma de San Luis Potosí, San Luis Potosí, SLP Mexico.
  • Department of Surgery, Faculty of Medicine, Universidad Autónoma de San Luis Potosí, San Luis Potosí, SLP Mexico.
  • Faculty of Science, Universidad Autónoma de San Luis Potosí, San Luis Potosí, SLP Mexico.
  • Burn Unit, Hospital Central Dr. Ignacio Morones Prieto, San Luis Potosí, SLP Mexico.
  • Department of Family Medicine, Instituto Mexicano del Seguro Social, San Luis Potosí, SLP Mexico.

ORCID-Profile: Eleazar Samuel Kolosovas-Machuca

Zitieren

APA

Castillo-Morquecho, R., Guevara, E., Ramirez-GarciaLuna, J. L., Martínez-Jiménez, M. A., Medina-Rangel, M. G., & Kolosovas-Machuca, E. S. (2024). Digital infrared thermography and machine learning for diabetic foot assessment: thermal patterns and classification. Journal of Diabetes & Metabolic Disorders, 23(2), 1967-1976. https://doi.org/10.1007/s40200-024-01452-0

Vancouver

Castillo-Morquecho R, Guevara E, Ramirez-GarciaLuna JL, Martínez-Jiménez MA, Medina-Rangel MG, Kolosovas-Machuca ES. Digital infrared thermography and machine learning for diabetic foot assessment: thermal patterns and classification. Journal of Diabetes & Metabolic Disorders. 2024;23(2):1967-1976. doi:10.1007/s40200-024-01452-0

BibTeX
@article{CastilloMorquecho2024,
  author = {Castillo-Morquecho, Rogelio and Guevara, Edgar and Ramirez-GarciaLuna, Jose Luis and Martínez-Jiménez, Mario Aurelio and Medina-Rangel, María Guadalupe and Kolosovas-Machuca, Eleazar Samuel},
  title = {Digital infrared thermography and machine learning for diabetic foot assessment: thermal patterns and classification},
  journal = {Journal of Diabetes & Metabolic Disorders},
  year = {2024},
  volume = {23},
  number = {2},
  pages = {1967--1976},
  doi = {10.1007/s40200-024-01452-0}
}
Kostenlos starten →