Smart pressure-sensing flooring for diabetic foot ulcer prevention: A narrative review of AI-driven optimization

Diabetic foot ulcers (DFUs) affect up to one-third of people with diabetes over their lifetime and are among the leading causes of diabetes-related lower-limb amputation. The lifetime risk of developing a DFU is approximately ۱۹–۳۴%, and recurrence remains common (around ۳۰–۴۰% within one year). Although standard care (foot examinations, patient education, offloading devices) reduces risk, a substantial recurrence risk remains (often around ۳۰%). Emerging approaches use embedded floor systems or in-shoe insoles together with artificial intelligence (AI) to continuously monitor plantar pressures and gait. In this narrative review, we examine DFU pathophysiology, preventive strategies, and novel pressure-sensing flooring technologies. We discuss pressure-sensing floors and insole hardware (piezoelectric, piezoresistive, and capacitive sensors) and AI/machine learning (ML) approaches used to analyze gait and pressure data for risk classification or early warning. Our review summarizes evidence of technical feasibility and predictive performance (e.g., ML models reporting ~۸۵–۹۵% accuracy in classification tasks) and highlights challenges such as sensor power, data privacy, and patient adherence. Future work should evaluate clinical effectiveness in prospective trials and explore integration into care pathways, including telehealth platforms.Diabetic foot ulcers (DFUs) affect up to one-third of people with diabetes over their lifetime and are among the leading causes of diabetes-related lower-limb amputation. The lifetime risk of developing a DFU is approximately ۱۹–۳۴%, and recurrence remains common (around ۳۰–۴۰% within one year). Although standard care (foot examinations, patient education, offloading devices) reduces risk, a substantial recurrence risk remains (often around ۳۰%). Emerging approaches use embedded floor systems or in-shoe insoles together with artificial intelligence (AI) to continuously monitor plantar pressures and gait. In this narrative review, we examine DFU pathophysiology, preventive strategies, and novel pressure-sensing flooring technologies. We discuss pressure-sensing floors and insole hardware (piezoelectric, piezoresistive, and capacitive sensors) and AI/machine learning (ML) approaches used to analyze gait and pressure data for risk classification or early warning. Our review summarizes evidence of technical feasibility and predictive performance (e.g., ML models reporting ~۸۵–۹۵% accuracy in classification tasks) and highlights challenges such as sensor power, data privacy, and patient adherence. Future work should evaluate clinical effectiveness in prospective trials and explore integration into care pathways, including telehealth platforms.

کلیدواژه ها:

Wearable Technology ، Gait Monitoring ، Deep Learning ، Telemedicine ، Biomechanics ، Chronic Wound Management