moorfields   5

Artificial intelligence 'did not miss a single urgent case' • BBC News
Fergus Walsh:
<p>A team at DeepMind, based in London, created an algorithm, or mathematical set of rules, to enable a computer to analyse optical coherence tomography (OCT), a high resolution 3D scan of the back of the eye.

Thousands of scans were used to train the machine how to read the scans. Then, artificial intelligence was pitted against humans. The computer was asked to give a diagnosis in the cases of 1,000 patients whose clinical outcomes were already known.

The same scans were shown to eight clinicians - four leading ophthalmologists and four optometrists. Each was asked to make one of four referrals: urgent, semi-urgent, routine and observation only.

Artificial intelligence performed as well as two of the world's leading retina specialists, with an error rate of only 5.5%. Crucially, the algorithm did not miss a single urgent case.

The results, published in the journal Nature Medicine , were described as "jaw-dropping" by Dr Pearse Keane, consultant ophthalmologist, who is leading the research at Moorfields Eye Hospital.

He told the BBC: "I think this will make most eye specialists gasp because we have shown this algorithm is as good as the world's leading experts in interpreting these scans."

Artificial intelligence was able to identify serious conditions such as wet age-related macular degeneration (AMD), which can lead to blindness unless treated quickly. Dr Keane said the huge number of patients awaiting assessment was a "massive problem".</p>


Contrast this with IBM's Watson, trying to solve cancer and doing badly. This has a better data set, clearer pathways to disease, and is better understood generally. Part of doing well with AI is choosing the correct limits to work within.

And this won't replace the doctors; it will just be a pre-screen.
moorfields  eye  deepmind  ai 
august 2018 by charlesarthur
Moorfields announces research partnership • Moorfields Eye Hospital NHS Foundation Trust
<p>Two million people are living with sight loss in the UK, of whom around 360,000 are registered as blind or partially sighted. At the moment, eye health professionals rely on digital scans of the eye to diagnose and determine the correct treatment for common eye conditions such as age-related macular degeneration and diabetic retinopathy.

These scans are highly complex and to date, traditional analysis tools have been unable to explore them fully. It also takes eye health professionals a long time to analyse eye scans, which can have an impact on how quickly they can meet patients to discuss diagnosis and treatment…

…Faster and more efficient diagnosis of eye disease could help prevent many thousands of cases of sight loss due to wet age-related macular degeneration and diabetic retinopathy, which together affect more than 625,000 people in the UK.

Moorfields Eye Hospital will share approximately one million anonymised digital eye scans, used by eye health professionals to detect and diagnose eye conditions. Anonymous clinical diagnoses, information on the treatment of eye diseases, model of the machine used to acquire the images and demographic information on age (shown to be associated with eye disease) is also being shared. This has been collected over time through routine care, which means it’s not possible to identify any individual patients from the scans. And they’re also historic scans, meaning that while the results of our research may be used to improve future care, they won’t affect the care any of our patients receive today.</p>


What we want machines to do: take over tedious routine which conceals important data. I'm meantime wondering: is machine learning already being used for airport X-ray scanning?
moorfields  deepmind  machinelearning 
july 2016 by charlesarthur

related tags

ai  algorithms  artificialintelligence  data  deep  deepmind  eye  google  health  healthcare  hospital  machinelearning  medical  mind  predpol  research  retina  retinal  royalfreehospital  scan  vision  weibo 

Copy this bookmark:



description:


tags: