AI could spot eye disease more accurately than doctors, study suggests
AI could spot eye disease more accurately than doctors,
study suggests
By Victoria Ward 5 FEBRUARY 2018 • 7:22PM
Artificial intelligence developed by Google could be
better at spotting eye disease than human doctors, experts believe.
A two-year partnership between Google’s sister company,
DeepMind and the renowned Moorfields Eye Hospital, showed “promising signs” in
analysing retinal scans for signs of glaucoma, age-related macular degeneration
and diabetic retinopathy.
The research has been submitted to a peer-reviewed
medical journal amid hopes that the technology could enter clinical trials
within a few years.
Dominic King, DeepMind's clinical lead, told the
Financial Times: “In specific areas like medical imaging, you can see we're
going to make really tremendous progress in the next couple of years with
artificial intelligence.
“Machine learning could have a very important role
picking up things more sensitively and specifically than currently happens.”
Peng Tee Khaw, director of research at Moorfields, said:
"I am optimistic that what we learn from this research will benefit people
around the world and help put an end to avoidable sight loss."
DeepMind, which is based in London, analysed data from
thousands of anonymised retinal scans that had been labelled for signs of
disease by doctors.
The scans were used to train an AI algorithm to detect
signs of eye disease more quickly and efficiently than human specialists.
It is hoped that such programmes will ease some pressure
on the overstretched NHS by taking on some of the repetitive work.
Dr King said such artificial intelligence was
“generalised,” meaning it could be applied to other kinds of images and be used
to diagnose other illnesses.
There are plans for DeepMind to partner with University
College London Hospitals to analyse radiotherapy scans and with Imperial
College London to look at mammograms.
Technology companies are increasingly moving into health.
In 2016, Microsoft announced it planned to crack cancer within 10 years after
launching several projects to "hack" the body.
Google’s secretive arm Calico, is also investigating ways
to extend human life and even stop ageing altogether.
However, the relationship between such technology
companies and hospitals is sensitive.
Last year, the UK’s data protection watchdog ruled that
the NHS illegally handed Google the data of 1.6 million people.
The Information Commissioner's Office found that the
Royal Free NHS Foundation Trust in London "failed" to comply with
data protection rules when it gave patient records to DeepMind for a trial.
The ruling related to a trial that used technology to
track patients' symptoms and send alerts to doctors in the event of a drastic
change in their health through an app called Streams.
The company has since set up a research unit focused on
the ethical and social implications of the AI it is creating.
Dr King added. “[Artificial intelligence] needs to be
implemented and evaluated I would say as rigorously as a new pharmaceutical
medical device so you have evidence that then allows you to scale up across a
health system.”
Comments
Post a Comment