A tool that uses artificial intelligence to diagnose prostate cancer in men and make treatment decisions will be tested in the United States. National Health Service hospitals, the researchers said.
£1.9 million Vanguard Path study funded by Prostate Cancer In the UK and led by researchers at the University of Oxford, it is expected to last three years and will test an artificial intelligence tool called ArteraAI to analyze prostate biopsies. In total, biopsies from more than 4,000 men will be used.
The tool, which analyzes digitized biopsy images to produce a personalized risk score, is already in production. has been shown in clinical trials to determine which men with high-risk prostate cancer are most likely to benefit from the drug abiraterone.
However, US trials have shown that it can also be used in less aggressive forms of prostate cancer to predict which men are most likely to benefit from hormone therapy in addition to radiotherapy.
In addition, research has shown that this tool can help determine which patients can be monitored without the need for immediate treatment.
Dr Matthew Hobbs, director of Prostate Cancer Research UK, said: “If and when this comes to fruition, you will be able to use one tool, no matter where you are on the aggressiveness scale, to make a very clinical and life-improving decision for each of these men.” He added that the tool is already widely used in the United States.
The new study will first use prostate biopsy samples from men who have already been diagnosed and treated for prostate cancer, and who have relevant follow-up data, to see if the tool's predictive prowess holds true when applied to UK patients.
The tool will then be tested at three sites – North Bristol NHS Foundation Trust, Oxford University Hospitals NHS Foundation Trust and Greater Glasgow and Clyde NHS Foundation Trust – as men go through the usual prostate cancer diagnosis pathway.
“The biopsy will be analyzed, a treatment choice will be made and the man will start treatment. But at the same time, NHS doctors will get a reading from the tool and ask: 'If you had this, would you recommend the same treatment or not?'” Hobbs said, adding that part of the study would also look at the extent to which the tool affected the time between diagnosis and treatment choice.
Experts hope the tool will eventually help reduce under- and over-treatment.
“The good thing that comes out of this is that the tool is being rolled out across the NHS,” Hobbs said. However, for this to happen, he says it needs to be proven to be scientifically sound, cost-effective and impact treatment decisions.
Professor Gerhardt Attard from University College London, who was involved in the study of abiraterone but was not involved in the study, said the research was important because the approaches often work well in clinical trials.
“When you translate this into the real world of the NHS there are bound to be a number of issues and differences that arise and that is what this study will focus on,” he said.
Ashley Dalton, minister of public health and prevention, also welcomed the trial. “This groundbreaking research could be a huge step forward, demonstrating the power of technology to potentially change lives and improve cancer outcomes,” she said.
“That's why we're investing in digital health. By using artificial intelligence and moving beyond legacy systems, we can transform cancer care – diagnose earlier, treat more effectively and improve the patient experience.”
