Diabetes Prediction Using Foot Pressure Analysis
Vinod Desai
Assoc. Prof, Department of CSE
Sai Vidya Institute of Technology Bengaluru, India vinod.desai@saividya.ac.in
Neha C G
Department of CSE
Sai Vidya Institute of Technology Bengaluru, India nehacg.21cs@saividya.ac.in
Varun E
Assoc. Prof, Department of CSE
Sai Vidya Institute of Technology Bengaluru, India varun.e@saividya.ac.in
Nishitha G
Department of CSE
Sai Vidya Institute of Technology Bengaluru, India
nishithag.21cs@saividya.ac.in
Chinmay R D
Department of CSE
Sai Vidya Institute of Technology Bengaluru,India
chinmayardhadave.21cs@saividya.ac.in
V Gnana Murali
Department of CSE
Sai Vidya Institute of Technology Bengaluru, India
vgnanamurali.21cs@saividya.ac.in
Abstract— Diabetes mellitus (DM) is a chronic disorder that has become a major global health concern, exacerbated by factors like sedentary lifestyles, obesity, and aging populations. Among its severe complications, diabetic foot conditions, such as foot ulcers and amputations, significantly impact quality of life and healthcare systems. These complications, often resulting from diabetic peripheral neuropathy and vascular insufficiency, stress the need for early detection and intervention.
This research introduces an intelligent foot pressure analysis system that integrates advanced sensors and machine learning algorithms to detect foot pressure abnormalities, which are early indicators of diabetic neuropathy. The system uses high-resolution pressure sensors embedded in footwear or insoles to capture real-time data on foot pressure distribution. Machine learning models, including Support Vector Machines (SVM), process the data to classify normal and abnormal pressure patterns. By enabling continuous monitoring and real-time alerts, the system aids in early intervention, preventing complications like diabetic foot ulcers. This innovative approach offers significant improvements in diabetic foot care, enhancing patient outcomes and quality of life.
Keywords— Diabetes Detection, Classification Algorithms, Support Vector Machines (SVM), Real-Time Detection, Evaluation Metrics (Accuracy, Precision)
