Evaluating Classification Systems of Diabetic Foot Ulcer Severity: A 12-Year Retrospective Study on Factors Impacting Survival.

(1) Background: This study examines the survival of patients after their first presentation with diabetic foot ulcers (DFUs) to the regional Diabetes, Nutrition, and Metabolic Diseases Clinic within the Emergency Clinical Hospital "Sf. Spiridon", Iasi, and analyzes the factors associated with this outcome. (2) Methods: In this retrospective study, patients with DFUs consecutively referred between 1 January 2007 and 31 December 2017 were followed up until 31 December 2020 (for 13 years). The study group included 659 subjects. (3) Results: During the study period, there were 278 deaths (42.2%) and the average survival time was 9 years. The length of hospitalization, diabetic nephropathy, chronic kidney disease, glomerular filtration rate, cardiovascular disease, hypertension, anemia, and DFU severity were the most significant contributors to the increase in mortality. Patients with severe ulcers, meaning DFUs involving the tendon, joint, or bone, had a higher mortality risk than those with superficial or pre-ulcerative lesions on initial presentation (Texas classification HR = 1.963, 95% CI: 1.063-3.617; Wagner-Meggitt classification HR = 1.889, 95% CI: 1.024-3.417, SINBAD Classification System and Score HR = 2.333, 95% CI: 1.258-4.326) after adjusting for confounding factors. (4) Conclusions: The findings of this study suggested that patients presenting with severe ulcers involving the tendon, joint, or bone exhibited a significantly higher risk of mortality, even when potential confounders were taken into consideration.

Survival Prediction in Diabetic Foot Ulcers: A Machine Learning Approach.

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.