Let’s take a look at some of the latest use cases and research around artificial intelligence (AI) across the NHS.
Predicting disease development at Imperial College
An AI model designed to help predict the risk of developing disease using an electrocardiogram (ECG) has been developed by researchers from Imperial College London and Imperial College Healthcare NHS Trust.
The team used datasets from international sources to train the AI model to analyse an ECG by designing it to ‘read’ the flow of electrical signals depicted by the ECG and identify any patterns.
The research states that the model – called AI-ECG risk estimation or ‘AIRE’ – could “correctly identify” the risk of death in the ten years following the ECG in 78 percent of cases. The model was also found to be able to predict future health risks such as heart rhythm problems, heart attacks or heart failures “with a high level of accuracy”, according to Imperial College Healthcare.
In addition, the team analysed imaging and genetic information to help confirm that the AI predictions were linked to biological factors in the heart’s structure and function, which they called “crucial for the credibility of the model with clinicians”, as it demonstrates how the model can “pick up subtle changes in the heart’s structure over time, which are early signs of risk of disease or death”.
Detecting lung cancer in the North East
Seven trusts in the North East are to deploy AI technology as part of efforts to support lung cancer detection and diagnosis, following a successful bid for funding through NHS England’s AI Diagnostic Fund from the region’s imaging network and provider collaborative.
South Tyneside snd Sunderland NHS Foundation Trust describes the tech as acting “like a second pair of eyes for clinicians” and designed to help prioritise cases where the X-ray has identified something that may indicate possible lung cancer. It has reportedly been shown to improve diagnostic accuracy by 45 percent; and increase diagnostic efficiency by 12 percent.
The trusts in question are North Cumbria Integrated Care; Gateshead Health; Northumbria Healthcare; South Tyneside and Sunderland; North Tees and Hartlepool; South Tees; and County Durham and Darlington.
Ken Bremner MBE, chair of the provider collaborative and senior responsible officer for the region’s imaging network, comments that through the AI tool “we will be able to improve the time it takes for treatment to begin for anyone who receives a lung cancer diagnosis. It will help us to save people’s lives and, importantly, catch more cases quickly.”
Analysing brain tumours in London
Researchers from University College London and University College London Hospitals have developed an AI-based imaging tool designed to assess brain tumour scans and provide analysis of the different components, with the aim of providing “patient-personalised detail” to support an individual’s treatment.
The tool was reportedly tested on 1172 patients and found to perform analysis “effectively and efficiently”, along with displaying accuracy “across patients of all ages and sexes”.
The trust states that according to a workforce analysis forecast, national deployment could potentially save more than £1.5 million in NHS costs across the next three years.
The lead author of the study Dr James Ruffle comments that with imaging appearances varying “greatly” for different patients’ brain tumours, AI tech can “provide an innovative solution to enhance healthcare workers’ data-driven decision making, improving and personalising care for each individual affected”.
AI in the spotlight
We explored other use cases for AI in the NHS here, looking in particular at Bolton, East Suffolk and North Essex; and we also examined AI use in Coventry and Warwickshire here.
Last week we noted how the UK government has awarded £12 million in funding for projects utilising innovative technologies such as AI, VR and wearable sensors in supporting people with drug addictions and reducing drug-related deaths.
NHS England has shared guidance on evaluating artificial intelligence projects and technologies with learnings from the ‘Artificial Intelligence (AI) in Health and Care Award’, which ran for four years until 2024 and supported the design, development and deployment of “promising” AI technologies; HTN explores the guidance here.
Other recent news includes DeepHealth, provider of a portfolio of AI solutions designed to support breast, lung, prostate and neurological care, acquiring London-based cancer diagnostic company Kheiron Medical Technologies Limited, as part of efforts to expand its portfolio of AI-powered diagnostic and screening solutions.
And HTN hosted a panel discussion exploring whether the reality of AI will live up to current hype along with examining how bias in healthcare data can be managed, featuring experts from the field: Puja Myles, director at MHRA Clinical Practice Research Datalink; Shanker Vijayadeva, GP lead and digital transformation for the London region at NHS England; and Ricardo Baptista Leite, M.D., CEO at HealthAI, the global agency for responsible AI in health.
