New AI system for lung cancer and heart disease could save NHS billions
pharmafile | January 4, 2018 | News story | Research and Development, Sales and Marketing | Optellum, Oxford, Sir John Bell, heart disease, lung cancer, pharma
A team of researchers at Oxford’s John Radcliffe Hospital have unveiled a new artificial intelligence system which they claim could cut operational costs by billions of pounds at NHS hospitals by helping to detect heart disease and lung cancer early, even suggesting the health service could benefit from the platform for free by as early as the summer.
Currently, cardiologists are able to diagnose heart problems by scanning and monitoring the timing of heartbeats, but this method can prove to be inaccurate in an estimated 20% of cases, leading to later heart attacks or unnecessary operations. This represents 12,000 misdiagnoses of the 60,000 heart scans every year, tallying up a cost of £600 million for the NHS in unnecessary operations and treatment of patients who had previously been given the all-clear.
Ultromics, as the system is known, provides a much more accurate form of scanning, picking up on details which doctors are prone to miss, and then gives a recommendation based on its assessment of cardiovascular event risk. The system has already been tested in clinical trials across six cardiology units, trained through the analysis of 1,000 patient scans, with results due to be published later this year; it is thought that its use could generate more than £300 million savings for the NHS per year.
“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,” the team said. “But our technology extracts more than 80,000 data points from a single echocardiogram image to overcome subjectivity and increase diagnostic accuracy.”
Alongside Ultromics is another AI system focused on the detection of lung cancer. Clinical trials suggest that the system can eliminate unnecessary patient scans by determining which cases are harmless and ruling them out, as well as diagnosing the disease earlier. The technology is being commercialised by start-up Optellum. The company’s Chief Science and Technology Officer Dr Timor Kadir claims the system could allow for 4,000 more much earlier cancer diagnoses a year, and potentially save £10 billion if adopted in the US and EU.
Government healthcare tsar Sir John Bell, who authored the Life Sciences: Industrial Strategy last year, has argued that the use artificial intelligence could be transformative for the NHS, telling the BBC: “There is about £2.2 billion spent on pathology services in the NHS. You may be able to reduce that by 50%. AI may be the thing that saves the NHS.”
Matt Fellows
Related Content
J&J gains positive CHMP opinion for Rybrevant for treatment of lung cancer
Janssen, a Johnson & Johnson (J&J) company, has announced that the Committee for Medicinal Products …
Roche’s Alecensa approved by FDA as lung cancer treatment
Roche has announced that the US Food and Drug Administration (FDA) has approved Alecensa (alectinib) …
FDA clears Oryzon’s phase 1/2 trial for lung cancer treatment
Oryzon Genomics has announced that the US Food and Drug Administration (FDA) has approved its …
