AI-Assisted Smart Insole for Early Diabetic Foot Ulcer Risk Detection: Design, Prototype Implementation and Experimental Observations

Diabetic foot ulcers (DFUs) tend to develop quietly. Reduced sensation, repeated loading of the same plantar regions and local changes in skin temperature build up over weeks, and a person with neuropathy may not notice none of it. This paper describes the design and prototype implementation of an AI-assisted smart insole meant to watch two of those signals together. An ESP32 DevKit V1 reads six force-sensitive resistors (FSRs) placed at the heel, midfoot, first, third and fifth metatarsal heads and great toe, together with an MLX90640 infrared array that returns 768 temperature points per frame, and streams both over USB serial at 921600 baud. A Processing application draws the thermal frame as a colour image, reports the minimum, maximum and mean temperature, and marks pixels at or above 35 °C. A companion Python platform, FootGuard-AI, handles dataset management, training and evaluation of thermal and pressure models on public and synthetic data. The prototype has been shown to acquire, transmit and display both signals. FSR readings are still raw ADC counts, the 35 °C threshold has no clinical validation, and the machine-learning benchmarks come from public datasets rather than from the insole itself. The work is therefore offered as a prototype-level engineering contribution and a foundation for calibration and clinical validation, not as a diagnostic device.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-19
DOI
https://doi.org/10.5281/zenodo.24373532
Primary Topic
Diabetic Foot Ulcer Assessment and Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI-Assisted Smart Insole for Early Diabetic Foot Ulcer Risk Detection: Design, Prototype Implementation and Experimental Observations

R Namratha, Maaz Nabeel, Pavithra V K, Ankitha Mohan
Zenodo (CERN European Organization for Nuclear Research)
Diabetic Foot Ulcer Assessment and Management
article

AI-Assisted Smart Insole for Early Diabetic Foot Ulcer Risk Detection: Design, Prototype Implementation and Experimental Observations

R Namratha, Maaz Nabeel, Pavithra V K, Ankitha Mohan
article en

Abstract

Diabetic foot ulcers (DFUs) tend to develop quietly. Reduced sensation, repeated loading of the same plantar regions and local changes in skin temperature build up over weeks, and a person with neuropathy may not notice none of it. This paper describes the design and prototype implementation of an AI-assisted smart insole meant to watch two of those signals together. An ESP32 DevKit V1 reads six force-sensitive resistors (FSRs) placed at the heel, midfoot, first, third and fifth metatarsal heads and great toe, together with an MLX90640 infrared array that returns 768 temperature points per frame, and streams both over USB serial at 921600 baud. A Processing application draws the thermal frame as a colour image, reports the minimum, maximum and mean temperature, and marks pixels at or above 35 °C. A companion Python platform, FootGuard-AI, handles dataset management, training and evaluation of thermal and pressure models on public and synthetic data. The prototype has been shown to acquire, transmit and display both signals. FSR readings are still raw ADC counts, the 35 °C threshold has no clinical validation, and the machine-learning benchmarks come from public datasets rather than from the insole itself. The work is therefore offered as a prototype-level engineering contribution and a foundation for calibration and clinical validation, not as a diagnostic device.

Zenodo (CERN European Organization for Nuclear Research)
B.M.S. College of Engineering (IN)
Diabetic Foot Ulcer Assessment and Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon