Creating an Artificial Intelligence (AI) magnetic resonance imaging (MRI) service and integration software
Originally, the aim of the project was to improve the productivity of the MRI service at Guy’s and St Thomas’ NHS Foundation Trust using fast, automated deep learning-based image-quality rating to decrease rescan and recall rates. Secondly, the algorithm would audit images to check they were correctly coded, ensuring hospitals charge for any extra imaging required to reach an accurate diagnosis.
However, deploying AI often involves installing separate hardware and bespoke connectivity for each AI algorithm. To solve this, Haris was able to secure £100,000 of funding to develop of a platform that could host the AI software.
The software platform turned out to have significant value in deploying AI generally into NHS systems. Much like an app store accessed on a Smartphone, the platform can host multiple AI software applications safely, effectively, and efficiently, enabling the integration of AI models into existing hardware operations and clinical workflows.
This work attracted the attention of the London Medical Imaging and AI Centre for Value Based Healthcare which co-opted the software as one of their flagship platforms for the AI Deployment Engine (AIDE), funded in part from their £16m programme to scale up AI in the NHS. This allows for the deployment of multiple AI models, integrating them into clinical systems, lowering the cost and effort to deliver cutting-edge med tech to the frontline.
Currently, AIDE enables access to 20 applications including brain tumour and liver MRI, Covid-19 chest x-rays and mammography screening, allowing clinicians to access near real-time AI analysis within seconds.
Another application measures lactose acid in the brains of new-born babies who have had a difficult birth and suffered a hypoxic ischemic event (a loss of oxygen to the brain), a potentially serious or life-shortening condition. Previously that process was done manually by a team available only on weekdays, 9 am to 5pm, so parents could be waiting a considerable time to know their baby’s condition. With the app that analysis is now fully automated and takes 30 seconds to get the result, having a real impact on the quality of care those parents receive.
AIDE is being rolled out in 10 NHS Trusts in London and the South East. First to go live was King’s College Hospital NHS Foundation Trust in October 2021 and it will be rolled out to the nine further Trusts by 2023.
Evaluation of patient benefit is very application specific. Certain applications can easily demonstrate that automation saves patient and MRI departments time, as the almost live score on the image quality removes the need to recall and rescan a patient at a later date. Some more operational departments, such as diagnostics, are still impacted by Covid-19 backlogs so it’s difficult to get good data to compare the impacts of automation.
The optimisation of oncology and surgical pathways are now being explored, as well as more operational functions such as triaging surgical lists and endoscopy scheduling. This uses natural language machine learning applications to work out the acuity of a patient and when their next appointment should be which gets sent to an administrator, freeing up the gastroenterologists to do other tasks.
The project has also led to Haris working with an international community working on the same problem, particularly in the States, leading to mutual collaboration on technical design with Stanford University, the Mayo Clinic and Massachusetts General Hospital.
Haris is a medical and MRI physicist by background, which is why his project initially focussed on MRI imaging. Since completing the Topol Fellowship, he is now a consultant clinical physicist and Head of the Clinical Scientific Computing section at Guy’s & St Thomas’ where his team are developing people, platforms, and policy for digital health.
He is also the AI Transformation Lead at the London Medical Imaging and AI Centre for Value Based Healthcare where he oversees the development of AI prototypes across over 20 patient pathways in partnership with academia, industry and NHS Trusts. Haris is also director of his own fellowship programme offering clinical AI fellowships, funded by NHS England.
Haris said: “I feel extremely grateful to have been on the Fellowship. There were a couple of things that were pivotal – not just to my work but to my career. One day was spent with the Government Digital Service talking about how they transformed public access to government services – such as changing your passport or driving license – though the GOV.UK platform. It exposed me to a whole new world of thinking – that it’s not just the technical, but also the cultural and organisational challenges in technology adoption that I needed to learn in order to be effective.
“I realised was that you can’t just build technology and expect someone else to do all the hard work of persuading managers that they need it. You need to build a coalition of others who can see the benefits in their world so they can take it forward to their clinical directors, not just me.”
“Do it! My career has been completely transformed in the space of two years. It’s been a bit of a rocket ship!
“A really good aspect of the Topol Digital Fellowship is that you are in a multi-disciplinary environment with Fellows from different backgrounds, so you get a really good peer review of what you’re doing and where you’re heading.
“You meet people from all over the country so you can collaborate, build a network and share what you’re doing so it can be tried in other hospitals so you can scale the scale the impact of your project. I’m still collaborating with people I met on the Fellowship today.”
“I am delighted to be the first user of the AIDE solution. At King’s, we will be sharing the capabilities of artificial intelligence (AI) with colleagues across London to improve the lives of our patients. AI will hugely support our work and help us personalise care and treatment for patients through providing richer information about the individuals and their illness.”
Haris Shuaib
Guy’s and St Thomas’ NHS Foundation Trust
