New artificial intelligence software is four times more accurate at predicting ovarian cancer deaths than current methods, new research has found.

The technology, developed by researchers at Imperial College London and the University of Melbourne in Australia, can also tell clinicians the best course of treatment for a patient depending on the severity on their disease.

Researchers used a mathematical software tool called TEXLab to identify how aggressive a tumour was from a CT scan and tissue samples from 364 women with ovarian cancer.

The software examined four biological characteristics of the tumours – structure, shape, size and genetic makeup – which significantly influence a patient’s overall survival rate.

Patients were then given Radiomic Prognostic Vector (RPV) score, which indicates how severe the disease is.

Researchers then compared the results with blood tests, which are currently used to diagnose ovarian cancer, and other prognostic scores to estimate a patient’s survival rate.

The new method was four times more accurate.

High RPV scores were also associated with chemotherapy resistance and poor surgical outcomes, meaning RPV could be used to predict how well patients will respond to treatments and allow clinicians to explore alternatives.

Lead author Professor Eric Aboagye, professor of cancer pharmacology and molecular imaging at Imperial College London, said: “The long-term survival rates for patients with advanced ovarian cancer are poor despite the advancements made in cancer treatments.

“Our technology is able to give clinicians more detailed and accurate information on how patients are likely to respond to different treatments, which could enable them to make better and more targeted treatment decisions.”

Professor Andrea Rockall, co-author and honorary consultant radiologist at Imperial College Healthcare NHS Trust, added: “Artificial intelligence has the potential to transform the way healthcare is delivered and improve patient outcomes.”

Ovarian cancer is the sixth most common cancer in woman, with more than 6,000 new cases in the UK each year.

As the disease is often diagnosed at a late stage the survival rate is just 35-40%, but early detection could drastically improve those odds.

Researchers hope this new software can be used to stratify ovarian cancer patients into groups based on the differences in the texture of their cancer on CT scans, rather than classification based on what type of cancer they have, or how advanced it is.

Health Minister Nicola Blackwood said: “Artificial intelligence has huge potential to revolutionise healthcare by offering more accurate and earlier diagnoses – it could transform the lives of cancer patients in the future.

“We must embrace this type of technology to enable clinicians to provide the best possible care on the NHS which is personalised to individuals.”