A thermal-imaging tool could enable nurses in the primary care setting to identify chronic wounds during a patient’s first in-home assessment.
While thermal imaging has previously been considered for detecting chronic wounds, the adoption of newer methods may enable significantly earlier detection than other approaches, according to researchers.
A RMIT University and Bolton Clarke Research Institute clinical study, published in Nature journal Scientific Reports, shows how an AI-powered system can predict how leg ulcers will heal based on thermal images from the first assessment.
“Our new work identifies chronic leg wounds during the first visit,” said lead researcher Professor Dinesh Kumar from RMIT University School of Engineering.
Thermal images of a venous leg ulcer showing healthy healing progress over three weeks. Credit: RMIT University
“This means that specialised treatment for slow-healing leg ulcers can begin up to four weeks earlier than the current gold standard.”
The latest published results allow the identification of these wounds a week earlier than their previous research indicated.
“Our innovation is not sensitive to changes in ambient temperature and light, so it is effective for nurses to use during their regular visits to people’s homes,” co-researcher, RMIT University Dr Quoc Cuong Ngo said.
“It is also effective in tropical environments, not just here in Melbourne.”
The new method provides information on spatial heat distribution in a wound. It predicts with 78% accuracy whether leg ulcers would heal in 12 weeks without specialised treatment.
Wounds change significantly over the healing trajectory: higher temperatures signal potential inflammation or infection, while lower temperatures can indicate a slower healing rate due to decreased oxygen in the region.
The research was based on thermal images collected from 56 clients with venous leg ulcers, the most common chronic wound in Australia.
The current gold-standard approach requires taking tracings of the wound size after four weeks, involving physical contact with the wound, which delays identification of slow-healing wounds.
The non-contact method reduced infection risk by minimising physical contact, Bolton Clarke Research Institute Senior Research Fellow Dr Rajna Ogrin said.
Nurse attending to a leg wound. Credit: Bolton Clark Research Institute
“This method provides a quick, objective, non-invasive way to determine the wound-healing potential of chronic leg wounds that can be used by healthcare providers, irrespective of the setting.
“This means specialised treatments, including advanced wound-cleaning techniques and therapies, can be implemented immediately for problematic leg wounds – up to four weeks earlier than the current gold standard.”
Nearly half a million Australians live with chronic wounds, which significantly affect quality of life and cost the nation’s health system around $3 billion each year.
The next step is to adapt the method for a nurse or doctor to have this thermal imaging and rapid assessment capability on their mobile phones, Professor Kumar said.
The team will also assess whether their method can predict healing of diabetes-related foot ulcers. Untreated chronic wounds in people living with diabetes are the leading cause of limb amputation in Western countries.
‘Computerised prediction of healing for venous leg ulcers’ is published in Scientific Reports.
