Australian researchers and clinicians have developed an AI-powered thermal imaging tool to predict if diabetes-related foot ulcers are likely to heal, potentially reducing hospitalisations and amputations.
Diabetes affects over 500 million people globally and about a third will develop a foot ulcer during their life, which can lead to infection, hospitalisation and amputation if not managed appropriately.
Clinical guidelines assess progress over the first four weeks of treatment to determine whether an ulcer is healing.
Now a study in the Journal of Diabetes Science and Technology introduces a new smartphone-based AI tool, called THERMUL, that provides clinicians with an indication of healing risk much earlier, using thermal images captured when a patient first presents for care.
The researchers from RMIT University, the University of Melbourne and Bolton Clarke conducted a clinical study at Austin Health and St Vincent’s Hospital Melbourne involving 110 patients with diabetes-related foot ulcers.
Using a light-weight thermal camera, researchers took images of the patients’ ulcers when they initially presented to the clinic, with additional images captured two and four weeks later.
At 12 weeks, clinicians assessed whether each ulcer had healed, allowing the research team to compare healing outcomes with the thermal image data collected earlier.
RMIT’s Professor Dinesh Kumar lead the development of THERMUL with Endocrinologist Professor Elif Ekinci, Head of the University of Melbourne’s Department of Medicine.
Kumar said the researchers used the data to train the AI model to identify heat patterns associated with ulcers that healed successfully and those that did not.
“These patterns may provide an early indication of a wound’s likely healing trajectory, potentially allowing clinicians to identify people who might benefit from earlier intervention or escalation of care,” said Kumar, from RMIT’s School of Engineering.
Ekinci, who is also Director of the Australian Centre for Accelerating Diabetes Innovations (ACADI), said the technology has the potential to improve health equity and deliver economic benefits for Australia’s healthcare system.
“Diabetes-related foot disease places a significant burden on individuals and the Australian health system, costing an estimated $875 million every year,” she said.
“By enabling earlier identification of ulcers at risk of delayed wound healing, THERMUL has the potential to improve access to timely care and reduce complications.”
Senior research fellow at Bolton Clarke, Dr Rajna Ogrin, said people in regional, rural and remote areas living with diabetes and receiving 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,” she said.
Seed funding from ACADI enabled the research team to develop the prototype.
The research team also recently received $490,539 through Australia’s Economic Accelerator program and $50,000 from the University of Melbourne’s Proof of Concept Fund.
They will use this funding to validate the technology across a range of healthcare settings, including metropolitan, regional and remote services, and to further improve the predictive model.
THERMUL is currently progressing through additional validation and development activities required to support future use in healthcare settings.
Partner organisations include the Australian Centre for Accelerating Diabetes Innovations, Austin Health, Bolton Clarke, St Vincent’s Hospital Melbourne, Royal Flying Doctor Service Victoria and Software Medical Devices Pty Ltd.
‘Automated prediction of Diabetes-related foot ulcer healing at initial assessment‘ is published in the Journal of Diabetes Science and Technology (DOI: 10.1177/19322968261501979).