COMPUTER-BASED IDENTIFICATION OF PLANTAR PRESSURE IN TYPE 2 DIABETES SUBJECTS WITH AND WITHOUT NEUROPATHY

Abstract

Diabetes mellitus is a medical disorder characterized by varying or persistent hyperglycemia (elevated blood sugar levels), especially after eating. People with diabetes have problems converting food to energy. The most common form of diabetes is type 2 diabetes. Foot disease is a common complication of diabetes that can have tragic consequences. Abnormal plantar pressures are considered to play a major role in the pathologies of neuropathic ulcers in the diabetic foot. The purpose of this study was to classify the plantar pressure distribution in normal and type 2 diabetes subjects with and without neuropathy. Foot scans were obtained using the F-Scan (Tekscan, USA) in-shoe pressure measurement system. Various pedobarographic parameters such as the total plantar force, total contact area, peak pressures, and percentage medial impulse (PMI) were evaluated. These parameters were subjected to analysis of variance (ANOVA) test with a >95% confidence interval, giving excellent p-values in all of the categories. When these extracted parameters were presented to the artificial neural network (ANN) for classification, the neural network classifier was seen to be correct in more than 90% of the test cases.