Researchers from Imperial College London and the University of Melbourne have created an artificial intelligence (AI) software that can predict the prognosis of patients with cancer. ovary with more precision than current methods and determine the most effective treatments for each individual.

An AI trial was held at Hammersmith Hospital in the UK and a research article detailing the findings was published in Nature Communications.

According to the software researchers, this new technology could usher in a more personalized medicine and could be used to organize ovarian cancer patients into groups based on subtle differences in the texture of their cancer on the skin. CT scans rather than a clbadification based on the type of cancer. cancer or how advanced it is.

Eric Aboagye, Professor of Pharmacology and Molecular Imaging of Cancer at Imperial College London and lead author of the study, said, "The long-term survival rates of patients with cancer advanced ovarian are mediocre, despite the advances made in the treatment of cancer. It is urgent to find new ways to treat the disease.

"Our technology is able to provide clinicians with more detailed and accurate information about the likely response of patients to different treatments, which may enable them to make better and more targeted treatment decisions."

Professor Andrea Rockall, radiologist, consultant, NHS Trust Specialist for the NHS Trust, added, "Artificial intelligence has the potential to transform the way health care is delivered and improve outcomes for the patients. Our software is one example and we hope it can be used as a tool to help clinicians better manage and treat ovarian cancer patients. "

Researchers used software called TEXLab to identify the aggressiveness of tumors in CT scans and tissue samples from 364 participants with ovarian cancer between 2004 and 2015.

They compared the results with blood tests and prognostic scores currently used by physicians to estimate survival and found that the software was four times more accurate in predicting death than other methods.

A larger study will now be conducted to ascertain how accurately the software can predict the results of surgery and drug treatments for each patient.

<! –

->