AI tool predicts survivability in ovarian cancer patients
Researchers from the Imperial College London and the University of Melbourne created a new AI algorithm that is four times more accurate in predicting survival rates among ovarian cancer patients. The tool was also able to determine the most effective treatment for patients who exhibit ovarian cancer. Research findings were published in Nature Communications.
“The long-term survival rates for patients with advanced ovarian cancer are poor despite the advancements made in cancer treatments,” Eric Aboagye, professor of cancer pharmacology and molecular imaging at Imperial College London, said in a prepared statement. “There is an urgent need to find new ways to treat the disease.”
The researchers developed an AI algorithm—TEXLab 2.0—to determine the aggressiveness of tumors in CT scans and tissue samples from 364 patients with ovarian cancer between 2004 and 2015.
TEXLab 2.0 assessed 657 radiomic features relating to tumor characteristics that impact overall survival—structure, shape, size and genetic makeup—to determine survivability. The AI tool then generated a Radiomic Prognostic Vector (RPV) score, which indicates the severity of ovarian cancer. Higher RPV scores indicated worse survival rates.
Aboagye and colleagues compared the results with blood tests and traditional prognosis scores currently used by physicians to estimate survival, and found the software was four times more accurate in predicting survivability.
Additionally, the researchers found 5 percent of patients with high RPV scores were associated with chemotherapy resistance, poor surgical outcomes and shockingly, had a survival rate of less than two years. The researchers noted RPVs can be used as potential biomarkers to predict patient response to ovarian cancer treatments. Aboagye said those who may not respond positively to standard treatments, may be offered alternative ones.
A prospective study or analysis of a retrospective randomized clinical trial data will be necessary to validate RPV in a more general cohort, the researchers wrote in their study.
“Artificial intelligence has the potential to transform the way healthcare is delivered and improve patient outcomes,” said study author Andrea Rockall, clinical chair of radiology, Imperial College London and honorary consultant radiologist at Imperial College Healthcare, National Health Service Trust, in the same statement. “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 will execute a larger study to determine how accurately TEXLab 2.0 can predict the outcomes of ovarian cancer surgery and/or drug therapies for individual patients.
“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,” Aboagye said.
As a senior news writer for TriMed, Subrata covers cardiology, clinical innovation and healthcare business. She has a master’s degree in communication management and 12 years of experience in journalism and public relations.