deepmind   685

« earlier    

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 
2 days ago by charlesarthur
Twitter
DeepMind’s AI agents are better than humans at being your teammate
AI  DeepMind  from twitter_favs
5 weeks ago by neuralmarket

« earlier    

related tags

2016  3d  ai  ai_assisted_fake_porn  aihealth  algorithms  alphago  alphazero  app  artificialintelligence  arxiv  audio-generation  blackbox  brain  businessmodel  cell  chess  clinicalai  colonialism  competition  computervision  cortex  could  ctf  data-access  data-ethics  data-protection  data  death  deep-learning  deep  deepfakes  deeplearning  deepmind_health  deepmindy  digital  digitalhealth  distributed-computing  dopamine  endoflife  engagement  engine  ethics  eye  face2face  fairness  gain...  gain  game-theory  gans  gdpr  generative  go  google  gov-data  graphics  grid  health  healthcare  hospital  hsk  ico  ifttt  image-generation  images  in4care  intelligence  jm  kylemcdonald  learning  lifespan  machine-learning  machinelearning  mainframe  marketing  match  mediaart  memory  mentalhealth  meta  mind  mix  ml  monopoly  moorfields  nature  neural-networks  neuralnets  neuralnetwork  neuralnetworks  newsletter  nhs  nlp  nn  papers  patents  personal-data  perspective  porn  pornhub  power  power’  prefrontal  probability  program  q3a  quake3  query  reading  recommender  regularization  reinforcement-learning  reinforcement  report  research  retina  retinal  scan  security  sgd  softwarepatents  speech-generation  speech  streetview  study-group  synthesis  tech  techcrunch  tensorflow  text-to-speech  tutorial  twitter  uk  understanding  up-to-us  video  videos  vision  warns  watson  wavenet  web  wtf      ‘excessive 

Copy this bookmark:



description:


tags: