Could AI help doctors better detect melanoma?

A clinical tool powered by artificial intelligence (AI) has been shown to improve the diagnosis of skin cancers, with experts suggesting its potential could extend to primary care.
 
Published in Nature Medicine, the study explored the use of PanDerm – an AI model built and trained to assist doctors by analysing multiple imaging types simultaneously.
 
It was developed by an international team of researchers led by Monash University in collaboration with the University of Queensland (UQ).
 
A series of evaluations showed PanDerm improved skin cancer diagnosis accuracy by 11% when used by doctors, as well as helping non-dermatologist healthcare professionals, including GPs, nurses and clinical trial assistants, improve diagnostic accuracy on various other skin conditions by 16.5%.
 
It also showed an ability to detect skin cancer early, identifying concerning lesions before clinician detection, the researchers report.

Melanoma is the third most common cancer nationally and an estimated 16,800 Australians will be diagnosed this year, according to the Melanoma Institute of Australia.

Co-lead author, Alfred Health Victorian Melanoma Service Director, Professor Victoria Mar, said PanDerm shows promise in helping detect subtle changes in lesions over time and provide clues to lesion biology and future risk of spread.
 
‘This kind of assistance could support earlier diagnosis and more consistent monitoring for patients at risk of melanoma,’ she said.
 
Fellow co-lead author and UQ Dermatology Research Centre Director, Peter Soyer, told newsGP the tool has potential to support GPs with early diagnosis and referral.
 
‘It could be particularly valuable in busy or resource-limited settings, or in primary care where access to dermatologists may be limited,’ he said.
 
‘AI-supported, or AI-augmented teledermatology will be very relevant for regional and rural regions in Australia and beyond.
 
‘This tool will also be of help for inflammatory rashes – of course, the implementation in real world is another step which will be driven by entrepreneurial colleagues.’
 
While results are promising, PanDerm is still in an evaluation phase before broader healthcare implementation. However, the study highlights the changing landscape for GPs with the rapid introduction of AI.
 
Dr Tracey Purnell, RACGP Specific Interests Dermatology Chair, said GPs play a vital role in the early detection and treatment of skin cancers in Australia and ‘anything that supports us in fulfilling our full scope of practice as GPs would be good’.
 
‘There are definitely benefits in areas where there are access barriers to dermatologists and skin cancer GPs,’ she told newsGP.
 
‘A tool like this would be useful for supporting GPs, however I think there’s a lack of evidence to show that it can be actually relied upon.
 
‘But overall, it’s exciting to see new developments and new research emerge. It’s early days, and we’re not sure if AI is up to the job … but it’s certainly a helpful and promising thing for the future.’
 
Looking ahead, the researchers aim to develop more comprehensive evaluation frameworks that address a wider range of dermatological conditions and clinical variants.
 
Log in below to join the conversation.

artificial intelligence melanoma preventive health skin cancer Skin checks