DEEP LEARNING-BASED PLANTAR PRESSURE ANALYSIS FOR EARLY DIABETIC FOOT RISK ASSESSMENT: A PROPOSED INTELLIGENT HEALTHCARE FRAMEWORK
Author
Ms. S.Brindha Devi
Abstract
Diabetes mellitus is a chronic health condition that can be associated with several long-term complications, including foot-related abnormalities and increased risk of diabetic foot complications. Early identification of abnormal plantar pressure patterns can provide useful information for preventive assessment and monitoring. Conventional assessment methods may depend on clinical examination and specialized equipment, motivating the development of intelligent computational approaches for automated plantar pressure analysis. This paper proposes a deep learning-based plantar pressure analysis framework for early diabetic foot risk assessment. The proposed framework consists of plantar pressure acquisition, preprocessing, foot-region segmentation, pressure-distribution analysis, deep feature extraction, risk classification, and explainable artificial intelligence. Convolutional neural networks and transfer-learning architectures such as ResNet and EfficientNet are proposed as candidate models for learning spatial characteristics from plantar pressure maps. An explainable AI module is incorporated to identify the plantar regions that contribute to the model's prediction. The proposed framework also includes an optional healthcare dashboard for visualizing pressure distributions and risk-assessment outputs. The methodology is designed as a conceptual and implementation-ready framework and does not claim experimental accuracy because a validated plantar-pressure dataset is not used in the present study. The work provides a foundation for future dataset-based validation and development of a non-invasive preliminary diabetic foot-risk screening system.
Keywords
Plantar Pressure, Diabetic Foot, Deep Learning, Diabetes, Footprint Analysis, Risk Assessment, CNN, Explainable AI, Healthcare Artificial Intelligence.
Full Text:
References
[1] K. Hullur, “Fake Product Authentication and Counterfeit Reporting Using Blockchain,” International Research Journal of Modernization in Engineering Technology and Science, Vol. 08, Issue 07, July 2026.
[2] A. Akhter and R. Rani, “Artificial Intelligence and Natural Language Processing Techniques for Smart Resume Analysis,” International Research Journal of Modernization in Engineering Technology and Science, Vol. 08, Issue 07, July 2026.
[3] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, Vol. 521, pp. 436–444, 2015.
[4] A. Vaswani et al., “Attention Is All You Need,” Advances in Neural Information Processing Systems, Vol. 30, 2017.
[5] S. Sarica and J. Luo, “Explainable Artificial Intelligence for Scientific Insights and Discoveries: A Survey,” Artificial Intelligence Review, Vol. 55, pp. 2059–2093, 2022.