Deepmind algorithm able to spot eye disease with more accuracy than doctors

The company has been working with the UK’s National Health Service and Moorfields Eye Hospital in London to analyse data from thousands of anonymised 3D retinal scans, and in the process ‘taught’ the technology to detect signs of age-related macular degeneration (AMD), diabetic retinopathy (DR) and glaucoma.The results have been so promising that Moorfields’ director of research and development Professor Peng Tee Khaw said in an interview with The Financial Times that they hoped to publish the results in a peer reviewed journal within 12 months.“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,” he said.{{quote-A:R-W:450-I:2-Q: Machine learning could have a very important role picking up things more sensitively and specifically than currently happens. -WHO:Dominic King, Deepmind}}Aside from potentially improving diagnosis rates, the technology is also seen as a way to rove the repetitive nature of reviewing scans for signs of disease and reduce the pressure on the NHS.“In specific areas like medical imaging, you can see we’re going to make really trendous progress in the next couple of years with artificial intelligence,” Deepmind clinical lead Dr Dominic King told FT.“Machine learning could have a very important role picking up things more sensitively and specifically than currently happens.”DeepMind has begun discussing clinical trials for the technology in UK hospitals, including Moorfields, but the next stage will be training the algorithm to analyse radiotherapy scans through a partnership with the University College London Hospitals, and mammograms in partnership with Imperial College London.However, despite the success of the program, Deepmind was also broiled in controversy last year after the Information Commissioner’s Office claimed the NHS trust illegally provided the company with access to the medical records of 1.6 million patients.The data was used in trials for a health app called Streams. Deepmind’s AI technology was trained with patients’ data to diagnose symptoms and send alerts to doctors when it detected a sudden change in health conditions.As a result, Deepmind established a research unit to focus on social and ethical implications of its AI technology.“[Artificial intelligence] needs to be implented 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 syst,” King said.