We founded DeepMind to make the world a better place by developing technologies that help address some of society's toughest challenges.
So we’re excited to announce our first medical research project with an NHS Trust.
We’ll be working with Moorfields Eye Hospital NHS Foundation Trust, one of the world’s leading eye hospitals with a 200 year track record in clinical care, research and education.
This collaboration came about when Pearse Keane, a consultant ophthalmologist at Moorfields, contacted DeepMind to explore how we could work together on two specific conditions that cause sight loss: diabetic retinopathy and age-related macular degeneration (AMD). Together, these affect more than 625,000 people in the UK and over 100 million people worldwide.
Diabetes is on the rise. It’s estimated that 1 in 11 of the world’s adult population are affected. It’s also the leading cause of blindness in the working age population - if you’re diabetic you are 25 times more likely to suffer some kind of sight loss. Early detection and treatment can prevent 98% of severe visual loss resulting from diabetes - but that doesn’t always happen.
Age-related Macular Degeneration (AMD) is the commonest cause of blindness in the UK. Every single day - in the UK alone - nearly 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 nearly 200m by 2020. By allowing earlier detection and treatment of AMD, machine learning has the potential to help save the sight of many of these people.
At the moment, eye care professionals use digital scans of the fundus (the back of the eye) and scans called optical coherence tomography (OCT) to diagnose and determine the correct treatment for these serious eye conditions. These scans are highly complex and take a long time for eye health professionals to analyse, which can have an impact on how quickly they can meet patients to discuss diagnosis and treatment. And to date, traditional computer analysis tools have been unable to explore them fully.
Our research project aims to investigate how machine learning could help analyse these scans efficiently and effectively, leading to earlier detection and intervention for patients and reducing the number of cases of patient deterioration.
The set of one million anonymised eye scans and some related anonymous information about eye condition and disease management, which Moorfields will share with us for the research, has been collected over time through routine care. This means it’s not possible to identify any individual patients from the scans. And they’re also historic scans, meaning that while the results of our research may be used to improve future care, they won’t affect the care any patient receives today.
We’re proud to be contributing to the many thousands of medical research efforts underway at any given time. As is standard practice in such projects, we never own the data - the NHS does. And we’re bound by clear rules covering what we can do with it, which are distinct to (though equally strict as) the rules that govern our direct patient care work with the Royal Free Hospital.
More information about the project can be found on our Health Research page. We have submitted our research protocol for open peer review and we’ll also submit any results from this research to peer-reviewed journals, as is normal, so others in the medical community can analyse them.
It’s early days for this work, but we’re optimistic about the long-term potential for machine learning technology to help eye health professionals diagnose and treat other diseases that, like macular degeneration, affect the lives of millions of people across the world. It’s a hugely exciting opportunity to make a difference to the NHS and its patients, and we’ll keep you updated as we continue on this journey.
We founded DeepMind to solve intelligence and use it to make the world a better place by developing technologies that help address some of society's toughest challenges. It was clear to us that we should focus on healthcare because it’s an area where we believe we can make a real difference to people’s lives across the world.
We're starting in the UK, where the National Health Service is hugely important to our team. The NHS helped bring many of us into the world, and has looked after our loved ones when they've most needed help. We want to see the NHS thrive, and to ensure that its talented clinicians get the tools and support they need to continue providing world-class care.
Frontline nurses, doctors and other healthcare professionals who spend their days treating patients know better than anyone what's needed to provide outstanding care. We at DeepMind Health aim to support clinicians by providing the technical expertise needed to build and scale technologies that help them provide the best possible care to their patients.
While projects like Hark and AKI detection are in their early stages, the problems they solve are fundamental to the NHS. The hope is that these tools can help shift more resources away from reaction and towards better prevention. Ultimately the aim is to give nurses and doctors more time to focus on what’s most important.
These past few months have given us a glimpse of what’s possible. As we continue to explore what nurses and doctors need, and work with them to design and scale new and better tools, we will remain guided by the following principles:
Valuing clinician and patient expertise
Nurses, doctors and patients are the experts — we can help by building tools that support them. Everything we do will be driven by the needs and insights of those involved in frontline care. From identifying challenges, to co-designing solutions, to oversight and governance, clinicians and patients will lead us every step of the way.
Stand behind the National Health Service
We are proud supporters of the NHS and believe in the core principle that healthcare should be universally available and free at the point of use. DeepMind Health’s work will support and strengthen the delivery of exemplary care in the NHS.
Build technologies that work together
Effective healthcare technologies must work well with existing systems while supporting further innovation by clinicians and technologists. We will develop open and interoperable technology while absolutely protecting the confidentiality of patient data. This ensures that the benefits of innovation are widely shared.
The world’s toughest problems become more tractable when diverse teams of leading practitioners work together in partnership. Building world-class technologies that support clinicians is one of the most important things we can do, and DeepMind Health is our promise to do just that.