Published: 28 July 2023
A new NIHR Evidence Collection has identified 10 promising AI interventions addressing five key healthcare challenges.
The Collection demonstrates the potential of AI in addressing these challenges, and highlights how AI can support the NHS and transform healthcare in future. The innovations could one day benefit the NHS and patients by saving time, money, resources. They could improve care and save lives.
The healthcare challenges addressed by AI are:
- Detecting heart disease
- Diagnosing lung cancer
- Predicting the progression of disease
- Personalising cancer and surgical treatment
- Reducing pressures on A&E
Dr Jemma Kwint, NIHR Senior Research Fellow and author of the report, said: "The Collection will be helpful to the healthcare community, patients and members of the public. We all need to be able to trust AI and ensure that it does not increase inequalities in care. The high quality studies are useful examples of the evidence we need to build trust in this advancing technology.
Further research is needed to deepen our understanding of how these tools could work in routine clinical practice, their long-term effect on patient outcomes and their overall value for money."
What the research says
Smart stethoscope detects heart failure
Around 1 in 100 adults have heart failure, and it becomes more common as we age. It is usually diagnosed in hospital. An easy-to-use smart stethoscope, could screen for heart failure in primary care. Research found that the stethoscope identified people with heart failure correctly 9 out of 10 times. It could help GPs prioritise referrals, improve outcomes for patients and save the NHS money.
Has an A&E patient had a heart attack?
In England, around 1,000 people a day attend A&E for a heart-related reason. An AI application used routine clinical data along with a blood test that measures heart muscle damage. Research found that the application could determine whether people attending A&E had experienced a heart attack or not. It could help to reduce the time spent in A&E, improve early treatment of heart attacks, and prevent unnecessary admissions. This could benefit both patients and the NHS.
Two studies help diagnose lung cancer
Lung cancer is the most common cause of cancer death in the UK, with around 35,000 deaths every year. Two studies found that AI could help determine whether abnormal growths seen on a CT scan are cancerous. The studies used different types of AI, and focused on different size growths, but both predicted cancer more accurately than the standard Brock score recommended by a professional organisation. AI could therefore help diagnose patients earlier and save lives.
Will wet age-related macular degeneration (wet AMD) progress?
Wet AMD is the biggest cause of sight loss in the UK. 1 in 4 people with wet AMD are expected to develop it in their second eye. Research found that AI can predict whether people with wet AMD in one eye will develop it in the other. A study included scans from more than 2,500 people, and showed that AI outperformed 5 out of 6 experts in predicting the development of wet AMD.
AI predicts ulcerative colitis flare-ups
Around 296,000 people in the UK have been diagnosed with ulcerative colitis. This is a long-term condition that causes inflammation and ulcers in the bowel. Researchers developed an AI tool that could detect disease activity and predict the risk of flare-ups in people with ulcerative colitis. The technology could speed up and standardise assessment of ulcerative colitis, and provide accurate information about prognosis to doctors.
Personalised cancer and surgical treatment
Which drugs are effective for an individual with lung cancer?
AI could help doctors decide which specific drug combinations are likely to benefit a patient with lung cancer in as little as 12 to 48 hours. This could help to personalise care for lung cancer patients. If developed further, it could potentially improve the outcomes of patients with lung cancer treated with targeted anticancer drugs.
Should people with COVID-19 go ahead with surgery?
People who have COVID-19 around the time of surgery are more likely to die than those without the virus. An international study involving almost 8,500 patients developed and checked an AI tool that used routine clinical data (such as a patient’s age and whether they needed respiratory support). It found that the tool could predict the risk of death in the month after surgery for people with COVID-19.
Reducing pressures on A&E
Who does not need to go to A&E?
Ambulances in England take around 350,000 people a month to A&E. Reducing unnecessary attendance at A&E would relieve pressure on the NHS. Researchers developed an AI model which correctly predicted, 8 out of 10 times, which people did not need to attend A&E. This was based on more than 100,000 linked ambulance and A&E care records from across Yorkshire.
AI could help managers predict demand for emergency beds
Researchers developed an AI tool to help hospital managers predict how many A&E patients need to be admitted. They used real-time data from more than 200,000 A&E visits to a busy London teaching hospital. The AI tool predicted how many hospital beds were needed in 4 and 8 hours’ time. The estimates outperformed the hospital’s usual planning of emergency admissions, which is based on the number of beds needed in the previous 6 weeks.
Professor Mike Lewis, NIHR Scientific Director for Innovation, said: “Over just the last few months, our awareness of the potential of artificial intelligence to change our lives – in both good and bad ways – has risen to new heights. The noise around this issue has become increasingly loud. But as is so often the case with new technologies, how we choose to use AI will determine whether this brings benefit or risk to our lives. And to understand that properly, we need to gather robust evidence.
“The research shared in this Collection aims to do just that. Collectively they demonstrate the potential of AI to positively enhance our ability to treat disease and efficiently manage our vital health service. Although the AI innovations here are not yet being used in practice yet, they nevertheless illustrate the advantages that AI could bring to the NHS in the near future.”
Steve Barclay, Health and Social Care Secretary said: “Artificial intelligence is already having a positive impact across the NHS, from helping to diagnose patients more quickly to saving staff valuable time, and I am focussed on making sure we can harness the best technological tools to deliver the highest quality care for patients.
“It is encouraging to see the results of these studies, which show that with the help of AI, doctors could soon be able to detect heart disease more quickly, predict the progression of diseases, and personalise cancer treatments. This will help to improve care and cut waiting lists, one of the government’s top five priorities.”