Geoff Twist, managing director for Roche Diagnostics UK and Ireland, writes about the value of AI for clinical diagnostics.
Artificial Intelligence (AI) can help healthcare professionals transform the NHS. Not only will it improve care for patients and lead to increased cost savings, it can also enhance the speed and accuracy of diagnosis for long-term conditions like cancer.
So prime minister Boris Johnson’s announcement last week that £250 million will be used to set up a national AI laboratory should be welcomed as a positive step forward for the health service. We hope it is a sign of things to come and will be working closely with partners across the system to support this important focus on innovation.
Mr Johnson has said the funding would be aimed at "freeing up staff to care for patients" and improving the detection of diseases such as cancer and dementia. He also said new AI technologies could estimate future needs of beds, medicines, or devices, and improve cancer screening by speeding up the results of tests and automate routine administrative tasks so clinicians can spend more time with patients.
It is no secret that the NHS is facing unprecedented challenges including an ageing population, long-term conditions and significant funding issues. Leaders in the healthcare space have to find innovative ways to do more with less, without compromising patient care. The dawn of new technology such as AI presents an opportunity to help alleviate some of the pressure, while also offering potential for groundbreaking revolution in what healthcare can do.
This is something we have significant experience in at Roche Diagnostics. Developing AI solutions that can free up staff to care for patients, and improving detection of diseases is something we are truly passionate about. For example, we are proud to be part of a pioneering collaborative effort, the Northern Pathology Imaging Co-operative (NPIC) in Leeds, which has been given funding by the UK Government’s innovation funding agency, Innovate UK, to bring together the NHS and academia to pioneer the use of AI in digital pathology. This funding will be combined with £7 million that the industry partners, including Roche, have committed to invest.
This collaborative project, which covers 12 hospitals and 15 million patients, will revolutionise how cancer is diagnosed. We will be able to train AI to recognise the patterns of disease – for example searching for small areas of cancer in a large sample. This means that pathologists will be able to use AI to diagnose cancer faster, better and at lower cost, which is obviously an attractive prospect for the NHS.
To work, AI needs to “learn” the patterns by looking at large numbers of images and learn from them, like a human would. But there are no large collections of digital images that can be used for this. The NPIC brings together the NHS, industry and scientists to solve this problem.
The project will see Roche and other partners putting scanners into all these northern NHS hospitals to gather digital pathology images training AI systems. This will generate a lot of data – about 760,000 images per year by the end of the project.
We will also be working to make new AI systems to analyse our images and make better diagnoses. This is a big opportunity for the UK to lead in this new area. Crucially, everyone involved in this project will ensure that AI systems are safe, and that doctors and the NHS are in control of how they are used. Just as important, we need to ensure the public understand what we are doing and trust that we are using NHS data properly and securely.
Our ambition is to create something that is world leading. We want to develop the best process for gathering and using data to make AI systems, bringing value for the NHS and patients. It’s the perfect balance between a collaborative partnership that makes the most of people power to make new technology work for us. This is a great example of how working together can transform healthcare.
The future of healthcare is incredibly exciting, with potential for true world-leading digital pathways to support exceptional clinical decision making. The fact is that early and accurate diagnoses saves lives – and AI has the potential to take this to the next level, which can only be good news for the NHS, for pathologists, and most importantly, for patients.
