AI (or should that be A-eye?) better than doctors at accurate optical diagnoses
TECH APPROACHING LEVEL OF SPECIALISTS, SAY RESEARCHERS
A CAMPAIGN has been launched to find carers for people with learning disabilities who have experienced domestic abuse.
The initiative – the first of its kind in the country – is a joint scheme between Cambridgeshire Shared Lives and the Cambridgeshire and Peterborough Domestic Abuse and Sexual Violence (DASV) Partnership.
It arose after the Cambridgeshire and Peterborough Domestic Abuse Safe Accommodation Needs Assessment identified gaps in safe accommodation for people with disabilities, including learning
ARTIFICIAL intelligence (AI) is better than doctors in accurately assessing eye problems, according to new research.
The clinical knowledge and reasoning skills of the ever-improving technology are already approaching the level of specialist eye doctors, say University of Cambridge scientists.
GPT-4 – a ‘large AI language model’ – was tested against medics at different stages in their careers, including unspecialised junior doctors, as well as trainee and expert eye doctors.
Each was presented with a series of 87 patient scenarios involving a specific eye problem, and asked to give a diagnosis or advise on treatment by selecting from four options.
GPT-4 scored “significantly better” in the test than unspecialised junior doctors, who are comparable to general practitioners (GPs) in their level of specialist eye knowledge. disabilities. Research shows a growing national need for more specialised domestic abuse services.
It was found that women with learning disabilities, autism or both are three times more likely to experience domestic abuse than their non-disabled peers (ONS, 2021).
Cambridgeshire County Council said it was pleased to launch the first project of its kind, addressing someone’s care and support needs at the same time as their needs as a victim of domestic abuse.
The aim of this campaign is to
The findings, published in the journal PLOS Digital Health, also showed that GPT-4 gained similar scores to trainee and expert eye doctors – although the top-performing doctors scored higher.
The Cambridge research team say that large language models aren’t likely to replace healthcare professionals, but have potential to improve healthcare as part of the clinical workflow.
The researchers believe that stateof-the-art large language models such as GPT-4 could be useful for providing eyerelated advice, diagnosis, and management suggestions in “well-controlled contexts” such as triaging patients, or where access to specialist healthcare professionals is limited.
Dr Arun Thirunavukarasu, study lead author, said: “We could realistically deploy AI in triaging patients with eye issues to decide which cases are emergencies that need to be seen by a specialist immediately, which can be seen by a GP, and which don’t need treatment.
“The models could follow clear recruit Shared Lives Domestic Abuse Carers – a paid role with carers being self-employed and the scheme paying their fees.
This will provide a personcentred, long-term support approach for survivors of domestic abuse, acknowledging the impact abuse can have for people specifically with learning disabilities.
People can offer support just for a few hours in the daytime, for an overnight stay, or for an extended break. Organisers are keen not only to provide vital care and support for those who have experienced algorithms already in use, and we’ve found that GPT-4 is as good as expert clinicians at processing eye symptoms and signs to answer more complicated questions.
“With further development, large language models could also advise GPs who are struggling to get prompt advice from eye doctors. People in the UK are waiting longer than ever for eye care. Large volumes of clinical text are needed to help fine-tune and develop these models, and work is ongoing around the world to facilitate this.”
The team say the research is “superior” to previous studies because they compared the abilities of AI to practicing doctors, rather than to sets of examination results.
Dr Thirunavukarasu, now an Academic Foundation Doctor at Oxford University Hospitals NHS Foundation Trust, said: “Doctors aren’t revising for exams for their whole career. We wanted to see how AI fared when pitted against to the onthe-spot knowledge and abilities of practising doctors, to provide a fair comparison. We also need to characterise the capabilities and limitations of commercially available models, as patients may already be using them – rather than the internet – for advice.”
The test included questions about domestic abuse in Cambridgeshire, but also to give residents new skills and career opportunities to encourage support within their communities.
The scheme is being funded by the Cambridgeshire and Peterborough DASV Partnership.
The Partnership chose to approach the Shared Lives team at Cambridgeshire County Council for the pilot due to their experience with supporting people with learning disabilities.
Councillor Neil Shailer, White Ribbon Ambassador for Cambridgeshire County Council, several eye health issues – including extreme light sensitivity, decreased vision, lesions, itchy and painful eyes – taken from a textbook used to test trainee eye doctors.
The textbook is not freely available on the internet, making it unlikely that its content was included in GPT4’s training datasets.
Dr Thirunavukarasu said: “Even taking the future use of AI into account, I think doctors will continue to be in charge of patient care.
“The most important thing is to empower patients to decide whether they want computer systems to be involved or not. That will be an individual decision for each patient to make,”
GPT-4 and GPT-3.5 – or ‘Generative Pre-trained Transformers’ – are trained on datasets containing hunsaid: “This is an exciting and muchneeded initiative which will provide invaluable support for people with learning disabilities who have experienced some sort of domestic abuse – often an underacknowledged characteristic which deserves greater recognition.
“As the first scheme of its kind in the country, I hope more will follow.
“Also that this will help raise the profile of people in similar situations who might currently be suffering in silence.”
■For further information email cambridgeshiresharedlives@ cambridgeshire.gov.uk dreds of billions of words from articles, books and other internet sources.
GPT-4 powers the online chatbot ChatGPT to provide “bespoke” responses to human queries.
ChatGPT has recently attracted significant attention in medicine for attaining passing level performance in medical school examinations, and providing more accurate and empathetic messages than human doctors in response to patient queries.
The researchers pointed out that the field of artificially intelligent large language models is moving “very rapidly” and, since the study was conducted, more advanced models have been released – which may be even closer to the level of expert eye doctors.
We’ve found GPT-4 is as good as expert clinicians at processing eye symptoms.
Dr Arun Thirunavukarasu