DeepMind and Moorfields Eye Hospital NHS Foundation Trust
Our work with Moorfields Eye Hospital NHS Foundation Trust (Moorfields) began in mid-2016 after Pearse Keane, a consultant ophthalmologist at the hospital, approached us to ask whether our technology could help provide a better understanding of eye disease.
Over 600,000 patients enter Moorfields' doors every year, and they carry out more than 3,000 optical coherence tomography (OCT) scans every week. These scans require highly trained, expert analysis in order to interpret the result, which can cause huge delays in getting to diagnosis and treatment.
We believe that the AI and machine learning technology within DeepMind Health can succeed in reducing the time required for experts to go through all aspects of the scan by spotting patterns and categorising results for faster diagnosis. So we are working together to analyse one million de-personalised eye scans using machine learning, to explore the impact it can have on our understanding and treatment of eye diseases.
Further details of this work can be found in our published research protocol.
Why are we looking at eye disease research?
Eye health professionals rely on digital scans of the eye so they can diagnose and monitor patients’ conditions, and determine the correct treatment for common eye diseases such as age-related macular degeneration and diabetic retinopathy.
These scans are highly complex, and to date, traditional analysis tools have been unable to explore them fully. It also takes eye health professionals a long time to analyse eye scans, which can have an impact on how quickly they can meet patients to discuss diagnosis and treatment.
This can have a major impact on patients with the following conditions:
- Age-related macular degeneration
Age-related macular degeneration (AMD), a painless eye condition that causes you to lose central vision, will affect an estimated 2.5 million adults by 2020 in the UK alone. Around 15% of early cases of AMD progress to the more serious form of wet AMD, which can be difficult for clinicians to predict. Machine learning has an opportunity to filter through the huge quantity of information available from scans of the eye, and potentially recognise subtle features which predict the onset of wet AMD.
- Diabetic eye disease
Diabetic retinopathy is a complication of diabetes, caused by high blood sugar levels damaging the back of the eye (retina). 50% of people with severe diabetic retinopathy who do not receive timely treatment will be registered as blind within five years. Up to 98% of severe vision loss from diabetic retinopathy can be prevented by early detection and treatment. By efficiently analysing the large number of scans and images taken of the eye every year, a machine learning algorithm could ensure the right patients in need of treatment are seen at the right time by the right clinician.
This would effectively give clinicians an early warning system allowing them to prioritise patients with the most serious cases and treat them before lasting damage occurs. We are confident that machine learning can help even further with the detection and prevention of eye deterioration diseases and other severe conditions in the future.
Data & Security with Moorfields
Data security and integrity is hugely important to all of our partnerships. That is why every step is taken by our teams to protect data shared with us, audit it, and destroy it when it is no longer being used.
Moorfields are sharing one million de-personalised digital eye scans, used by eye health professionals to detect and diagnose eye conditions.
All research projects go through rigorous regulatory and Trust approvals and are conducted only on de-personalised patient data. There is a lot more information on our agreements with Moorfields in our FAQs, and more on the way we handle data below.