Summary
Artificial intelligence (AI) is increasingly being used in medicine to help with the diagnosis of diseases such as skin cancer. To be able to assist with this, AI needs to be ‘trained’ by looking at data and images from a large number of patients where the diagnosis has already been established, so an AI programme depends heavily upon the information it is trained on. This review, published in The Lancet Digital Health, looked at all freely accessible sets of data on skin lesions around the world.
Content
This review examined 21 sets of data on skin lesions, including more than 100,000 images.
The findings of the review highlighted that many of the datasets were missing important information, such as how images were chosen to be included and evidence of ethical approval or patient consent. 14 of 21 datasets gave information on which country they came from and, of those, nine contained images from European countries. The review notes that only a small percentage of images were accompanied by information about the patients’ skin colour or ethnicity.
Among pictures where skin colour was stated (2,436 pictures), only ten were of brown skin and only one was of dark brown or black skin. Among pictures where ethnicity was stated (1,585 pictures), none were from people with African, Afro-Caribbean or South Asian background.
Commenting on the review, one of its authors, Dr David Wen from the University of Oxford, said:
“We found that for the majority of datasets, lots of important information about the images and patients in these datasets wasn’t reported. There was limited information on who, how and why the images were taken. This has implications for the programs developed from these images, due to uncertainty around how they may perform in different groups of people, especially in those who aren’t well represented in datasets, such as those with darker skin. This can potentially lead to the exclusion or even harm of these groups from AI technologies. Although skin cancer is rarer in people with darker skins, there is evidence that those who do develop it may have worse disease or be more likely to die of the disease. One factor contributing to this could be the result of skin cancer being diagnosed too late.”[1]
Dr Neil Steven, member of the National Cancer Research Institute Skin Group, Honorary Consultant in Medical Oncology at University Hospitals Birmingham NHS Foundation Trust, also commented on these findings:
“Skin cancer affects more than 200,000 people each year in the UK alone. Some types of skin cancer are more aggressive than others so quick diagnosis and treatment can be vital. We already know that there are not enough pictures of people from black and Asian backgrounds in the textbooks we use to train doctors. The findings of this review – that pictures of people with darker skin are under-represented in datasets – raise concerns about the ability of AI to assist in skin cancer diagnosis, especially in a global context. I hope this work will continue and help ensure that the progress we make in using AI in medicine will benefit all patients, recognising that human skin colour is highly diverse.”[1]
References
Related reading
- Raynor M, Essat Z, Ménage D, et al. Decolonising Midwifery Education Part 1: How Colour Aware Are You When Assessing Women With Darker Skin Tones in Midwifery Practice? The Practising Midwife, Volume 24 Issue 6 June 2021.
- Mukwende M, Tamonv P, Turner M. Mind the Gap: A handbook of clinical signs in Black and Brown skin. 14 September 2021.
- Neil Singh. Decolonising dermatology: why black and brown skin need better treatment. The Guardian, 13 August 2021.
- Rebecca Tatum. ‘Mistreatment’ due to the colour of your skin. the hub, 12 August 2021
0 Comments
Recommended Comments
There are no comments to display.
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now