AI-powered system can predict healing of venous leg ulcers

AI-powered system can predict healing of venous leg ulcers

A thermal imaging tool to screen for chronic wounds could allow nurses to identify these hard-to-heal wounds during a person’s first home assessment.

Nearly half a million Australians live with chronic wounds, which significantly affect their quality of life and cost the country’s healthcare system an estimated $3 billion each year.

The latest innovation from researchers at RMIT University and Bolton Clarke Research Institute builds on their team’s work published last year, which identified chronic leg wounds as early as the second week after assessment basic.

Their latest published results identify these sores a week earlier and represent a significant leap forward, according to the team.

Lead researcher Professor Dinesh Kumar said their latest clinical study, published in the journal Nature Scientific reportspresents an AI-powered system to predict how leg ulcers will heal based on first-assessment thermal images.

Our new work that identifies chronic leg wounds on first visit is a world first. This means specialist treatment for slow-healing leg ulcers can start up to four weeks earlier than the current gold standard. »

Professor Dinesh Kumar, RMIT School of Engineering

Co-investigator Dr Quoc Cuong Ngo from RMIT said that while thermal imaging had previously been considered for detecting chronic wounds, the team’s methods provided much earlier detection than other approaches that have is the subject of research.

“Our innovation is not sensitive to changes in ambient temperature and light, so it is effective for nurses during their regular visits to people’s homes.

“It’s also effective in tropical environments, not just here in Melbourne.”

How innovation works

The new method provides information on the spatial distribution of heat in a wound and predicts, with 78% accuracy, whether leg ulcers would heal in 12 weeks without specialist treatment.

Wounds change dramatically during the healing trajectory – higher temperatures signal potential inflammation or infection, while lower temperatures may indicate a slower rate of healing due to decreased oxygen in the wound. region.

The research was based on thermal images collected from 56 clients with venous leg ulcers – a type of ulcer associated with poor venous function. This type of ulcer is the most common chronic wound in Australia.

The current gold standard approach requires taking wound size tracings after four weeks, involving physical contact with the wound, which delays the identification of slow-healing wounds.

Dr Rajna Ogrin, principal investigator at the Bolton Clarke Research Institute, said the no-touch method reduces the risk of infection by minimizing physical contact.

“Clinical care is provided in many different places, including specialty clinics, general practices and home care,” she said.

“This method provides a rapid, objective, and non-invasive way to determine the healing potential of chronic leg wounds that can be used by healthcare providers in any setting.

“This means specialist treatments, including advanced wound cleansing techniques and therapies, can be implemented immediately for problematic leg wounds – up to four weeks earlier than the current gold standard.”

Next steps

Kumar said that now that the method has been successfully demonstrated in controlled trials with partner clinicians, the next step is to adapt it so that a busy nurse or doctor has this thermal imaging and assessment capability. fast on his cell phone.

“With the funding we received from the Medical Research Future Fund, we are now working towards this,” he said.

“We are eager to work with potential partners with different expertise to help us achieve this goal in the coming years.”

The team will also assess whether their method can predict the healing of diabetes-related foot ulcers. Chronic untreated wounds in people with diabetes are the leading cause of limb amputation in Western countries.


Journal reference:

Ngo, QC, et al. (2022) Computerized prediction of healing of venous leg ulcers. Scientific reports.

#AIpowered #system #predict #healing #venous #leg #ulcers

Leave a Comment

Your email address will not be published. Required fields are marked *