This paper is published in Volume-11, Issue-1, 2025
Area
Artificial Intelligence
Author
Chaitanya Jain, Aniruddha Bhaumik, Harsh Bhanushali
Org/Univ
Vellore Institute of Technology, Vellore, India
Pub. Date
31 January, 2025
Paper ID
V11I1-1211
Publisher
Keywords
Diabetic Neuropathy, Explainable AI, Nerve Sensitivity

Citationsacebook

IEEE
Chaitanya Jain, Aniruddha Bhaumik, Harsh Bhanushali. Nerve Sensitivity Identification by Explainable AI for Diabetic Patients’ Nerve Stress Point: A New Approach, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Chaitanya Jain, Aniruddha Bhaumik, Harsh Bhanushali (2025). Nerve Sensitivity Identification by Explainable AI for Diabetic Patients’ Nerve Stress Point: A New Approach. International Journal of Advance Research, Ideas and Innovations in Technology, 11(1) www.IJARIIT.com.

MLA
Chaitanya Jain, Aniruddha Bhaumik, Harsh Bhanushali. "Nerve Sensitivity Identification by Explainable AI for Diabetic Patients’ Nerve Stress Point: A New Approach." International Journal of Advance Research, Ideas and Innovations in Technology 11.1 (2025). www.IJARIIT.com.

Abstract

Diabetic neuropathy, a common complication of diabetes, leads to impaired nerve sensitivity, particularly in the feet, resulting in an increased risk of foot ulcers, infections, and amputations. Current diagnostic techniques, often subjective and reliant on invasive procedures, fail to offer early detection of nerve damage, limiting timely interventions. This project leverages Explainable Artificial Intelligence (XAI) to create a diagnostic system aimed at identifying, categorizing, and analyzing foot dynamics and nerve sensitivity in diabetic patients. By utilizing XAI, the proposed system enhances interpretability, offering clinicians a transparent and reliable tool for early diagnosis and personalized treatment. Our solution focuses on capturing foot immersion and image data to assess nerve sensitivity, utilizing a four-point structural analysis to map foot dynamics and detect abnormalities. The system will also address the challenge of false diagnoses by distinguishing diabetic nerve damage from other nerve-related conditions using heat and frequency verification at the foot's nerve endings. The goal is to provide an objective, accurate, and interpretable diagnostic tool that empowers healthcare providers to improve patient outcomes by enabling timely interventions in diabetic neuropathy cases. The use of XAI ensures that the AI models are interpretable and transparent, allowing clinicians to understand the underlying factors influencing the diagnosis. This transparency is critical for clinical adoption, as it builds trust in AI-driven diagnostic systems. By integrating XAI into diabetic neuropathy diagnostics, this project seeks to revolutionize diabetic foot care, enabling more accurate and timely detection of nerve damage, reducing the risk of severe complications, and ultimately improving the quality of life for diabetic patients.