Therapy Areas: Cardiovascular
NHS hospitals to have access to AI heart disease and lung cancer diagnosis tool
3 January 2018 -

Researchers at an Oxford hospital have successfully developed an artificial intelligence (AI) system that can provide patients with a diagnosis of heart disease and lung cancer much earlier than human doctors.

By enabling the diseases to be picked up at less advanced stages, patients could be saved from the fatal diseases and the system could save billions of pounds.

According to the British Heart Foundation, there are an estimated seven million people living with cardiovascular disease in the UK, and it is the cause of more than a quarter (26%) of all deaths in the UK.

Meanwhile, lung cancer is the most common cause of cancer death in the UK. According to Cancer Research UK, lung cancer accounts for over a fifth (22%) of all cancer deaths in males and females combined.

Scientists at the John Radcliffe Hospital have developed the AI system, called Ultromics. They trained the system to identify potential problems after being fed scans of 1,000 patients seen by cardiologist Professor Paul Leeson, who helped develop the system, over the last seven years. It was also told information on whether they had gone on to have heart problems.

As BBC News explains, cardiologists currently use the timing of the heartbeat in scans to determine if there is a problem. But this isn't always accurate.

Speaking the to Huffington Post, CEO of Ultromics, Ross Upton, said: "Currently one in five patients are misdiagnosed. We'll be able to reduce the number of patients being misdiagnosed by more than 50% which will save thousands of lives."

This means that, of the 60,000 patients scanned annually, 12,000 are sent home when they are at risk or undergo unnecessary surgery, costing the NHS an estimated GBP600m every year.

The AI system, however, is able to pick up details in the scans, invisible to the doctors, and provides them with a recommendation if it believes there is the risk of a heart attack.

So far, the system has been tested in clinical trials in six cardiology units. Once checked by experts, the results from the trials will be published in a peer-reviewed journal, expected later this year. However, it is suggested from the trial that it could save the NHS over GBP300m a year.

Commenting on the technology, the research team told the Huffington Post: "Making a diagnosis from echo relies on experienced clinicians having to make qualitative judgements based on only a fraction of the data that is potentially available to them from a typical scan.

"But our technology extracts more than 80,000 data points from a single echocardiogram image to overcome subjectivity and increase diagnostic accuracy."

If all goes well in a secondary round of testing, the company plans to provide the NHS with the technology for free later this year.

Oxford University Professor of Medicine, John Bell, described the technology as having the potential to "save" the NHS.

Meanwhile, a start-up company called Optellium will commercialise another system that looks for signs of lung cancer. While doctors are unable to tell if large clumps of cells, called nodules, are harmless or will become cancerous, the AI system can rule out the harmless cases.

This will help patients to avoid undergoing more scans to see how the nodules develop and save them months of anxiety, reduce costs for the NHS, and diagnose lung cancer much earlier.

The company's chief science and technology officer, Dr Timor Kadir, told the BBC that clinical trials of the system in Manchester suggest that over 4,000 lung cancer patients a year could receive earlier diagnosis, increasing the chance of survival.

Dr Kadir added: "Rather than focus on cost savings, within a resource-constrained system such as the NHS, we're really looking at how to offer better healthcare to more people for the same proportion of GDP. This is the potential of AI in the UK."



Related Headlines