“…Initially, the study undertook the process of feature selection, which led to the identification of several non-invasive predictors related to the 5- and 10-year mortality outcome: age, hemoglobine, creatinine, urea, length of hospitalization, The University of Texas Staging System for Diabetic Foot Ulcers score, ischemia from the Saint Elian Wound Score System (SEWSS), neuropathy from the SEWSS, glomerular filtration rate, cardiovascular disease, SEWSS score, the Wagner–Meggitt classification of foot ulcers grade, topographic aspects of the lesion from the SEWSS, hypertension, diabetic nephropathy, peripheral artery disease, hyperuricemia, and depth of lesion from the SEWSS. This is in accordance with the scientific literature as, to date, many of these variables were studied as mortality predictors in diabetes mellitus patients [ 17 , 18 , 19 , 20 ]. However, our paper is the first to consider combining the predictive power of all these variables by developing an AI/ML classifier.…”