Search

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. [ABSTRACT FROM AUTHOR]

Diabetic foot represents the consequence of changes caused by diabetes in the foot, meaning an association of infection, ulceration and / or destruction of deep tissues with neuropathy and peripheral vascular disease in the foot, below the ankle. The aim of the study was to evaluate the factors that may influence the length of hospital stay in patients with diabetic foot ulcers. Material and methods. An observational study was performed on a sample of patients hospitalized in the Diabetes, Nutrition and Metabolic Diseases Clinic within "St. Spiridon” County Emergency Clinical Hospital, Iași, between 01.01.2007 and 31.12.2017. Sociodemographic characteristics of the patients, history of the disease, biological parameters, duration of hospitalization were registered in a database. Severity of foot ulcerations was quantified using the San Elian Wound Scoring System (SEWSS). The relationships between length of hospital stay, severity of ulceration, biological parameters and complications of diabetes were analyzed. Results. The average length of hospital stay in the studied group was 19.68 ± 13.38 days. When analyzing the correlation between length of hospital stay and inflammatory parameters, we found that it correlated positively with white blood cells, neutrophils (PMN), C-reactive protein (CRP) and negatively with hemoglobin, hematocrit, total proteins, alkaline reserve and sideremia. Assessment of the severity of ulcerations using SEWSS (mild, moderate and severe) revealed a percentage of 85.7% of cases with moderate grade ulcers, and 9% of cases having severe grade ulcers. Severity of ulcerations correlated inversely with hemoglobin, hematocrit, total proteins and sideremia. Direct correlations were found between the severity score and the following parameters: white blood cells, PMN, fibrinogen, CRP. The length of hospital stay was significantly correlated with the severity of ulceration assessed by the SEWSS (r = 0.272, p < 0.001). Conclusions. Admission in the hospital with more severe ulcerations has been associated with increased length of hospital stay, thus suggesting the need for patient education and active screening of the diabetic foot. [ABSTRACT FROM AUTHOR]