One of London’s top NHS hospitals, University College London Hospital (UCLH), has partnered with the UK’s national organisation for data science, the Alan Turing Institute, to use artificial intelligence to carry out tasks that are usually performed by nurses and doctors.
The three-year research partnership will see AI applied to prioritise the treatment of patients coming through the Accident and Emergency (A&E) department. With A&E waits regularly exceeding four hours across the country, UCLH is not alone in finding that this department is a pressure point for hospital staff, and a trigger for wider resourcing problems.
“Despite some successes, hospitals have struggled to maintain long-term successes in reducing A&E waiting times,” said Professor Marcel Levi, UCLH chief executive. “A&E is a barometer of how the rest of the hospital and, indeed, the wider system is working.
“With ever increasing numbers of patients and ongoing financial pressures, we need to try something different, something innovative, something longer term. The partnership with the Alan Turing Institute provides an opportunity to work with the world’s leading data scientists to do just this.”
Levi explained how the research programme might work in practice: “Imagine a scenario where patients present to A&E with abdomen pain. Our standard response is to check bloods, order X-rays or scans, and in probably about 80 percent of cases, discharge for home management.
“But what if, through analysis of thousands of similar scenarios, we were able to identify patterns in the initial presentation of the 20 percent with serious conditions, such as intestinal perforation or severe infections? This could enable us to fast-track them through to a scan and a swift diagnosis. and could support clinical decision making to manage the 80 percent who need no further clinical input more effectively.”
Machines will never replace doctors, he added, but the combination of data, expertise, and new technology could “radically change” how the hospital manages its services.
AI-enabled treatments
In the longer term, the partnership could also see the use of AI extended to help doctors diagnose and treat serious conditions, such as cancer.
Professor Bryan Williams, director of the NIHR University College London Hospitals Biomedical Research Centre and director of research at University College London Hospitals NHS Foundation Trust, said: “The NHS routinely collects data that is analysed to develop research, track performance, and measure outcomes, but we could do so much more with the information we collect.
“Imagine a world where we could use this data to develop algorithms to rule out diseases, suggest treatment plans, or predict behaviour. That is more than possible with the wealth of data we have available and the expertise at The Alan Turing Institute. The partnership has the potential to tackle some of the big issues that the NHS has never been able to solve”.
Williams added that UCLH wants to “push the boundaries of routine clinical care by continuously analysing data, learning from it, changing the way we work, and testing.
“The potential to offer personalised care based on a range of parameters we might never have thought of before is what the partnership with Alan Turing Institute can offer. It is very exciting to be at the forefront of such an innovative project,” he said.
The partnership has been brokered by the NIHR University College London Hospitals Biomedical Research Centre, a £114 million translational research centre that transforms scientific breakthroughs into life-saving treatments for patients. The centre will provide pivotal infrastructure, such as data warehouses and storage, and expertise in data science and advanced analytics to complement the work of the Alan Turing Institute.
AI to understand patient flow
A more immediate objective of the partnership is to improve the flow of patients and staff through the hospital. Researchers will apply AI and machine learning techniques to existing large data sets to ascertain where bottlenecks are forming, to help patients get seen faster and more effectively.
The partners are also looking at deploying machine learning techniques across hospital appointment data to help staff understand which patients may attend or miss outpatient neurology clinics or MRI scans. The technology could also help staff examine the CT scans of 25,000 former smokers as part of an ongoing research project, and automate cervical smear tests.
Sir Alan Wilson, chief executive of the Alan Turing Institute, said that data science and AI will revolutionise healthcare, not only by improving diagnosis and treatment, but also by applying new algorithms to the everyday problems facing the NHS.
“We are very proud to be working with UCLH to begin a multi-year research partnership, driving the outputs of our research forward to deliver real impact across the whole NHS,” he said.
Plus: US university deploys quantum tumour detection
In related news, Case Western Reserve University is partnering with Microsoft’s Quantum team to use quantum-computing-inspired algorithms to enhance its approach to detecting cancer.
To improve the accuracy and speed of MRI tests, Case Western has introduced a technique called magnetic resonance fingerprinting. Microsoft will help optimise the process by mapping the problem onto a form suitable for quantum computers, and then run the resulting quantum-inspired algorithm on classical computers.
Internet of Business says
This week has seen a number of announcements concerning the transformational application of AI in the NHS.
Yesterday, Prime Minister Theresa May announced plans to commit millions of pounds to a new artificial intelligence strategy for early-stage cancer diagnosis. The aim is to reduce deaths from prostate, ovarian, lung, and bowel cancer by 10 percent within 15 years – saving an estimated 22,000 lives a year.
Meanwhile, the Royal Liverpool and Broadgreen University Hospitals NHS Trust announced that it has embarked on a new AI programme to improve the treatment of patients who have had a heart attack, in a project that could see wider use of AI to inform treatment decisions across the organisation.
In April, the British government announced a new Sector Deal for Artificial Intelligence, along with a comprehensive review of the health service, with the long-term strategy of training NHS workers in technologies such as AI and robotics.
Dr Eric Topol, executive VP of private US healthcare research group, Scripps Research Institute, is leading the review, looking at opportunities to train existing staff, while also considering the impact that AI, robotics, genomics, and big data analysis may have on skills.
- Read more: AI in the NHS: the great health and citizen enabler? | In-depth report
- Read more: Consumer wearables can detect major heart problem
- Read more: Machine learning improves dementia, stroke diagnosis
- Read more: Fitbit and Apple Watch can help predict diabetes, says report
Additional reporting: Chris Middleton