Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Sep 7;12(18):5816.
doi: 10.3390/jcm12185816.

Survival Prediction in Diabetic Foot Ulcers: A Machine Learning Approach

Alina Delia Popa  1 , Radu Sebastian Gavril  1 , Iolanda Valentina Popa  1 , Laura Mihalache  1 , Andreea Gherasim  1 , George Niță  1 , Mariana Graur  2 , Lidia Iuliana Arhire  1 , Otilia Niță  1
Affiliations

Survival Prediction in Diabetic Foot Ulcers: A Machine Learning Approach

Alina Delia Popa et al. J Clin Med. .

Abstract

Our paper proposes the first machine learning model to predict long-term mortality in patients with diabetic foot ulcers (DFUs). The study includes 635 patients with DFUs admitted from January 2007 to December 2017, with a follow-up period extending until December 2020. Two multilayer perceptron (MLP) classifiers were developed. The first MLP model was developed to predict whether the patient will die in the next 5 years after the current hospitalization. The second MLP classifier was built to estimate whether the patient will die in the following 10 years. The 5-year and 10-year mortality models were based on the following predictors: age; the University of Texas Staging System for Diabetic Foot Ulcers score; the Wagner-Meggitt classification; the Saint Elian Wound Score System; glomerular filtration rate; topographic aspects and the depth of the lesion; and the presence of foot ischemia, cardiovascular disease, diabetic nephropathy, and hypertension. The accuracy for the 5-year and 10-year models was 0.7717 and 0.7598, respectively (for the training set) and 0.7244 and 0.7087, respectively (for the test set). Our findings indicate that it is possible to predict with good accuracy the risk of death in patients with DFUs using non-invasive and low-cost predictors.

Keywords: Saint Elian Wound Score System; University of Texas Staging System; Wagner–Meggitt classification; diabetic foot ulcers; machine learning; mortality.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Pearson correlation heatmap between the selected continuous variables.
Figure 2
Figure 2
ROC curve of the 5-year prediction model.
Figure 3
Figure 3
Variable importance for the 5-year prediction model.
Figure 4
Figure 4
ROC curve of the 10-year prediction model.
Figure 5
Figure 5
Variable importance for the 10-year prediction model.
See this image and copyright information in PMC

References

    1. Ibrahim A. IDF Clinical Practice Recommendation on the Diabetic Foot: A Guide for Healthcare Professionals. Diabetes Res. Clin. Pract. 2017;127:285–287. doi: 10.1016/j.diabres.2017.04.013. - DOI - PubMed
    1. IDF Diabetes Atlas IDF Diabetes Atlas 2022 Reports. [(accessed on 3 June 2023)]. Available online: https://diabetesatlas.org/2022-reports/
    1. Jaiïn A.K.C. A Simple New Classification for Diabetic Foot Ulcers. Med. Sci. 2015;4:2109–2120. doi: 10.5455/medscience.2014.03.8215. - DOI
    1. Jalilian M., Ahmadi Sarbarzeh P., Oubari S. Factors Related to Severity of Diabetic Foot Ulcer: A Systematic Review. Diabetes Metab. Syndr. Obes. Targets Ther. 2020;13:1835–1842. doi: 10.2147/DMSO.S256243. - DOI - PMC - PubMed
    1. Lauwers P., Hendriks J.M.H., Van Bouwel S., Verrijken A., Van Dessel K., Van Gils C., Peiffer F., Yogeswaran K., De Block C., Dirinck E. Malnutrition According to the 2018 GLIM Criteria Is Highly Prevalent in People with a Diabetic Foot Ulcer but Does Not Affect Outcome. Clin. Nutr. ESPEN. 2021;43:335–341. doi: 10.1016/j.clnesp.2021.03.029. - DOI - PubMed

LinkOut - more resources