AI systems being developed to diagnose skin cancer run the risk of being less accurate for people with dark skin, research suggests.
The potential of AI has led to developments in healthcare, with some studies suggesting image recognition technology based on machine learning algorithms can classify skin cancers as successfully as human experts.
NHS trusts have begun exploring AI to help dermatologists triage patients with skin lesions.
But researchers say more needs to be done to ensure the technology benefits all patients, after finding that few freely available image databases that could be used to develop or “train” AI systems for skin cancer diagnosis contain information on ethnicity or skin type. Those that do have very few images of people with dark skin.
Dr David Wen, first author of the study from the University of Oxford, said: “You could have a situation where the regulatory authorities say that because this algorithm has only been trained on images in fair-skinned people, you’re only allowed to use it for fair-skinned individuals, and therefore that could lead to certain populations being excluded from algorithms that are approved for clinical use.
“Alternatively, if the regulators are a bit more relaxed and say: ‘OK, you can use it [on all patients]’, the algorithms may not perform as accurately on populations who don’t have that many images involved in training.”
Writing in the journal Lancet Digital Health, Wen and colleagues report how they identified 21 open-access datasets for skin cancer images of which 14 recorded their country of origin. Of these, 11 included images only from Europe, North America and Oceania.
Few of the 21 datasets recorded the ethnicity or skin type of the individuals photographed, with the team noting that means it is unclear how generalisable algorithms based on them would be.
The team found just 2,436 of a total of 106,950 images within the 21 databases had skin type recorded. Of these, only 10 images were from people recorded as having brown skin and one was from an individual recorded as having dark brown or black skin.
Only 1,585 images contained data on ethnicity instead of, or as well as, information on skin type. “No images were from individuals with an African, African-Caribbean or South Asian background,” the team report.
“Coupled with the geographical origins of datasets, there was massive under-representation of skin lesion images from darker-skinned populations,” they add.
Wen said the omissions are unlikely to be deliberate but that there is a need for standards to ensure important information, including ethnicity or skin type, is reported with images. The authors add datasets used to develop AI systems should represent the populations the technology will be used in.
Charlotte Proby, professor of dermatology at the University of Dundee and British Skin Foundation spokesperson – who was not involved in the work – said the findings are of concern.
“Failure to train AI tools using images from darker skin types may impact on their reliability for assessment of skin lesions in skin of colour,” she said, adding there could be wider implications.
… as you’re joining us today from Italy, we have a small favour to ask. Tens of millions have placed their trust in the Guardian’s high-impact journalism since we started publishing 200 years ago, turning to us in moments of crisis, uncertainty, solidarity and hope. More than 1.5 million readers, from 180 countries, have recently taken the step to support us financially – keeping us open to all, and fiercely independent.
With no shareholders or billionaire owner, we can set our own agenda and provide trustworthy journalism that’s free from commercial and political influence, offering a counterweight to the spread of misinformation. When it’s never mattered more, we can investigate and challenge without fear or favour.
Unlike many others, Guardian journalism is available for everyone to read, regardless of what they can afford to pay. We do this because we believe in information equality. Greater numbers of people can keep track of global events, understand their impact on people and communities, and become inspired to take meaningful action.
We aim to offer readers a comprehensive, international perspective on critical events shaping our world – from the Black Lives Matter movement, to the new American administration, Brexit, and the world’s slow emergence from a global pandemic. We are committed to upholding our reputation for urgent, powerful reporting on the climate emergency, and made the decision to reject advertising from fossil fuel companies, divest from the oil and gas industries, and set a course to achieve net zero emissions by 2030.
[ Tratto da: www.theguardian.com ]