Researchers have developed an artificial intelligence software that can predict the prognosis of patients with ovarian cancer more accurately than current methods, according to a study published in Nature Communications.
The researchers, from Imperial College London in the U.K. and the University of Melbourne in Australia, used a mathematical software tool called TEXLab to determine the aggressiveness of tumors in CT scans and tissue samples from 364 women with ovarian cancer between 2004 and 2015.
The AI software analyzed four biological characteristics of the tumors that significantly affect overall survival (structure, shape, size and genetic makeup) to evaluate patients' prognosis. The patients then received a score called the Radiomic Prognostic Vector, which shows disease severity.
The researchers compared the results with blood tests and current prognostic scores physicians use to estimate survival. They found the software was up to four times more accurate for predicting deaths from ovarian cancer than standard protocols.
They also found 5 percent of patients with high Radiomic Prognostic Vector scores had a survival rate of less than two years. High scores were also linked to chemotherapy resistance and poor surgical outcomes, suggesting that these scores can be used as a potential biomarker to predict how patients would respond to treatments.
The researchers said this technology also can be used to find patients who are unlikely to respond to standard treatments and offer them alternative treatments.