Google DeepMind is working with the NHS to fight blindness

It’s aimed at detecting two diseases – age-related macular degeneration and diabetic retinopathy.

Using tech created by DeepMind, a British startup acquired by Google back in 2014, Google is partnering with the UK’s state-run National Health Service.

Google DeepMind’s research protocol has been submitted for open peer review, and the company has also promised to subject any results from this research to scrutiny by peer-reviewed journals.

This is Google DeepMind’s second partnership with an NHS organisation.

Computers have long played a role in eye care. In October 2015, AlphaGo beat the European Go Champion, Fan Hui, five times in a row which is the first time an AI defeated a professional player.

That’s just the kind of task that artificial intelligence can be used to tackle, though. “Within a couple of days I got in touch with Mustafa, and he replied”.

The aim is to determine whether the algorithms can learn to spot early signs of age-related macular degeneration and sight loss that occurs as a result of diabetes. “Optical Coherence Tomography is my area, and we have the largest depository of OCT images in the world”. Then, using something the organization calls “machine learning”, the specialists will teach the AI how doctors diagnosed ocular diseases. The Seva Foundation, founded in the late 1970s to cure vision loss in India and the surrounding countries, got an Apple II from Steve Jobs to process the complex data they were dealing with. NVIDIA recently announced a partnership with Massachusetts General Hospital to apply artificial intelligence techniques to the detection and treatment of diseases, and one neural network model, the subject of a 2012 study, correctly identified coronary artery disease with 91.2 accuracy (others have isolated symptomatic patterns in diseases from cancer to diabetes).

“Every single day – in the United Kingdom alone – almost 200 people lose sight from the severe, blinding form of this condition and globally the number of people with AMD is set to rise to almost 200 million by 2020”, DeepMind stated. Moorfields and Google have stated that though the scans are from real patients it would be impossible to identify any individual patient’s identity and as the scans are historical their use won’t affect the care any current patients are receiving. It is important to understand the objective of the AI is not to replace human experts but to assist them. “Not because it’s ideal, but because it works as well as it does within some incredible constraints”.