Artificial intelligence developed by Google could soon be used to make diagnoses faster than doctors.
The sophisticated technology will be deployed to improve the detection and treatment of conditions ranging from cancer to common eye disease.
Researchers have already revealed ‘promising’ initial findings following a two-year project with Moorfields Eye Hospital in London. It is thought the technology, which has been programmed to detect signs of diseases including glaucoma and age-related macular degeneration, could enter clinical trials at other NHS hospitals within a couple of years. Google’s London-based AI firm, DeepMind, used retinal scans from thousands of patients to develop an algorithm – a set of mathematical instructions or rules that can work out answers to problems – to spot signs of disease.
Experts say the system can teach itself to read scans even quicker and more accurately than any human, meaning it could lead to both faster and more accurate diagnoses for patients. The next stage is to use the software for radiotherapy scans at University College Hospital and mammograms at Imperial College London.
For the Moorfields project, researchers used encrypted data so patients could not be identified. However, there was controversy last year when the Royal Free NHS Trust handed over 1.6million files to researchers at DeepMind without patients’ knowledge.
The Information Commissioner’s Office later said the trust had breached UK data protection laws. Professor Sir Peng Tee Khaw, director of research and development at Moorfields, said: ‘If we can diagnose and treat eye conditions early, it will give us the best chance of saving people’s sight.
‘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’. Dominic King, of DeepMind, said: ‘In areas like medical imaging, you can see we are going to make really tremendous progress in the next couple of years’.