Healthcare (Commonwealth Union) – Diabetic foot ulcers remain a devastating condition for individuals with diabetes. The need to be cautious about getting injured and wearing specific types of foot wear are measures taken.
A collaboration in Australia between the University of Melbourne and RMIT University has resulted in the creation of THERMUL, a thermal imaging artificial intelligence (AI) tool designed to reduce diabetes-related foot ulcer complications, including hospital admissions and amputations, by enabling earlier intervention.
More than 500 million people worldwide live with diabetes, and as many as 34 per cent are expected to develop a foot ulcer at some stage in their lives. Without effective management, these ulcers can become infected, require hospital treatment, lead to lower limb amputation and increase the risk of premature death.
The collaboration has produced a smartphone-based solution that combines thermal imaging with AI to forecast whether a diabetes-related foot ulcer is likely to heal within a 12-week period. By examining temperature patterns captured in thermal images of wounds, the technology can help identify ulcers that are progressing normally as well as those showing signs of delayed healing.
Researchers from the University of Melbourne, RMIT University and Bolton Clarke evaluated the technology through a clinical study conducted at Austin Health and St Vincent’s Hospital Melbourne. The trial involved 110 patients living with diabetes-related foot ulcers.
Researchers used a portable thermal camera to capture images of patients’ ulcers when they first arrived at the clinic, followed by further thermal scans taken after two and four weeks.
After 12 weeks, medical teams evaluated whether the ulcers had healed, enabling the researchers to compare the final healing results with the thermal imaging information gathered at the earlier stages.
Professor Elif Ekinci, an endocrinologist and Head of the University of Melbourne’s Department of Medicine and Director of the Australian Centre for Accelerating Diabetes Innovations (ACADI), indicated that the team used this data to train an AI system to identify temperature patterns in the initial thermal images that could distinguish ulcers likely to heal from those that were unlikely to recover.
She indicated that these patterns may give an early sign of a wound’s healing trajectory, possibly permitting clinicians to identify individuals who may get an advantage from earlier intervention or escalation of care.
RMIT University Professor Dinesh Kumar said the innovative technology could help address healthcare inequalities while also creating financial benefits for Australia’s medical system.
He indicated that diabetes-related foot disease creates a major burden for patients and the Australian healthcare sector, with annual costs estimated at around $875 million.
Professor Kumar indicated that by permitting clinicians to detect ulcers that may be slow to heal at an earlier stage, THERMUL could support faster access to appropriate treatment and help minimise complications linked to diabetes-related foot disease.
The present clinical recommendations typically evaluate the progress of a diabetes-related foot ulcer during the first month of care to establish whether the wound is responding to treatment and healing appropriately.
However, for many people in regional, rural and remote areas, obtaining regular access to specialist healthcare services remains a significant challenge.
A senior research fellow at Bolton Clarke, Dr Rajna Ogrin, says “People in regional areas who are living with diabetes and receive care at home, or through outreach services, may not have timely access to specialist diabetes foot services.”
“A portable, non-contact tool like THERMUL has the potential to bring specialist-level decision support closer to where people live and receive care.”
The project was first supported through seed funding from ACADI, allowing the research team to advance the concept and develop it into a working prototype.
