A new machine-learning system is as good as the best human experts at detecting eye problems and referring patients for treatment, say scientists. The groundbreaking artificial intelligence system, developed by the AI-outfit DeepMind with Moorfields eye hospital NHS foundation trust and University College London, was capable of correctly referring patients with more than 50 different eye diseases for further treatment with 94% accuracy, matching or beating world-leading eye specialists.
Can AI replace doctors? It's a question that's partially answered by The Guardian's report today that new AI trialled at Moorfields has matched eye experts in correctly diagnosing eye conditions with the same degree of accuracy, with wide-reaching implications for speeding up diagnosis and medical treatment.
Unlike typical 'black-box' AI where data is fed in and it's impossible to see how a decision has been reached, the two-stage tech used at Moorfields takes a more human-like approach, combining the results from five separate systems to give a final referral decision.
In an ageing society where keeping pace with the need for treatment of age-related conditions is a tough ask, this is one use of AI that's likely to be welcomed widely as tech plays a growing role in medicine.