Researchers announced on Aug. 3 that artificial intelligence tools could play a significant role in developing simpler and lower-cost technologies for monitoring foot health, especially in areas with limited access to specialized equipment. The collaboration involved The University of Queensland, iOrthotics, and Healthia Limited, which produced an AI model capable of reconstructing detailed foot pressure maps using only information about foot shape and a small number of anatomical pressure points.
Emeritus Professor Martin Veidt, an applied mechanics engineer at the University of Queensland, said plantar pressure analysis is widely used to assess a person's foot function and balance, gait mechanics, and overall foot health. It also informs the design of orthotics aimed at minimizing the risk and progression of foot-related pathologies. "But existing measurement methods have limitations and are often costly and inaccessible for people living in rural and remote regions," Veidt said.
Dr. Stuart McDonald from UQ added that while in-shoe systems offer greater mobility and extended pressure monitoring, they typically rely on many sensors, which can increase cost, complexity, and power requirements. "This study looked at the potential for AI to overcome some of the challenges associated with traditional plantar pressure monitoring systems," McDonald said.
The research team explored how a multimodal deep learning system could help unlock practical methods to reconstruct dense plantar pressure information from sparse sensing data. Using anatomical information from 35 participants' feet combined with plantar pressure measurements, PhD student Chongguang Wang built an artificial neural network framework capable of generating accurate high-resolution pressure maps using significantly fewer physical sensors. The deep learning model achieved its best performance using just 16 anatomical landmarks from the bottom of the foot but showed promising results even when using only two landmarks.
"This research demonstrates that by combining information about foot shape with only a small number of anatomical inputs, it is possible to reconstruct detailed plantar pressure distributions with a high degree of accuracy," Veidt said. "The beauty is that data collection could feasibly take place anywhere, including in isolated communities where health outcomes are poor and services may be limited."
Healthia's group chief education and research officer Kerrie Evans said this work forms part of a broader program exploring how emerging technologies can improve access to assessment tools: "Foot complications, including diabetic foot ulcers and amputations, continue to have a significant impact on individuals and health systems," Evans said. "Our goal is to support the development of practical, affordable technologies that can help clinicians better understand foot function and identify potential problems earlier." She added: "While more research is needed... these findings demonstrate the potential for AI to play an important role in future foot-health monitoring technologies." The study was published in Sensors.
