Researchers from Imperial College London and the University of Melbourne have created artificial intelligence (AI) software that can predict the prognosis of ovarian cancer patients more accurately than current methods and determine which treatments would be most effective for each individual.
A trial of the AI took place at Hammersmith Hospital in the UK and a research article detailing the findings has been published in Nature Communications.
According to researchers behind the software, this new technology could pave the way for more personalised medicine and could be used to organise ovarian cancer patients into groups based on subtle differences in the texture of their cancer on CT scans rather than classification based on the type of cancer or how advanced it is.
Imperial College London professor of cancer pharmacology and molecular imaging and lead author of the study Eric Aboagye said: “The long-term survival rates for patients with advanced ovarian cancer are poor despite the advancements made in cancer treatments. There is an urgent need to find new ways to treat the disease.
“Our technology is able to give clinicians more detailed and accurate information on the how patients are likely to respond to different treatments, which could enable them to make better and more targeted treatment decisions.”
Imperial College Healthcare NHS Trust consultant radiologist and co-author Professor Andrea Rockall added: “Artificial intelligence has the potential to transform the way healthcare is delivered and improve patient outcomes. Our software is an example of this and we hope that it can be used as a tool to help clinicians with how to best manage and treat patients with ovarian cancer.”
The researchers used a software tool called TEXLab to identify the aggressiveness of tumours in CT scans and tissue samples from 364 female participants with ovarian cancer between 2004 and 2015.
They compared the results with blood tests and prognostic scores currently used by doctors to estimate survival and found the software was four times more accurate at predicting deaths than the other methods.
A larger study will now be carried out to test how accurately the software can predict the outcomes of surgery and drug therapies for each individual patient.
