Predict the results
Determining the survival rate of cancer patients is based on a number of tests and it may be difficult for clinicians to determine the prognosis. But a new artificial intelligence could give them a length in advance.
Scientists from Imperial College London and the University of Melbourne have developed a machine learning software capable of predicting the prognosis of patients with ovarian cancer – and with greater precision than conventional methods.
Their research and the results of a first trial were published in the journal Nature Communications yesterday.
The researchers found that the survival rate of epithelial ovarian cancer was about 35 to 40%, despite the existence of many treatment options. Each year, around 6,000 new cases appear in the United Kingdom.
But developing a personalized treatment for the patient is essential – and the sooner the better.
"Radiomic prognosis vector"
The researchers developed a "Radiologic Prognostic Vector" (RPV) – a software that examines four biological characteristics of tumors, including the structure, shape, size and genetic makeup of CT scans – which has been revealed four times more accurate results compared to conventional methods in an initial trial that examined samples from 364 women.
RPV "also reliably identifies" the five percent of patients who normally have only two years to live. By identifying them early, they could improve the prognosis and optimize treatment plans for these patients.
Transforming health care
"Artificial intelligence has the potential to transform the way health care is delivered and improve outcomes for patients," co-authored the NHS Trust study co-author and radiologist. NHS Trust, in a press release. "Our software is an example of this and we hope it can be used as a tool to help clinicians better manage and treat ovarian cancer patients."