Artificial intelligence may be useful in predicting how tumors could evolve, the Telegraph reports. This, it adds, could help physicians decide on which treatment options to pursue.
An Institute of Cancer Research-led team of researchers developed a machine-learning approach they dubbed REVOLVER, for repeated evolution in cancer, that analyzes multi-region tumor sequencing data and runs through all the ways in which tumors could have evolved. As they report in Nature Methods this week, ICR's Andrea Sottoriva and his colleagues report that when they applied this approach to 768 tumor samples from 178 patients, they uncovered recurrent evolutionary paths among the tumors. Further, they found these different trajectories correlated with prognosis, suggesting the tool could have clinical relevance.
"With this tool we hope to remove one of cancer's trump cards — the fact that it evolves unpredictably, without us knowing what is going to happen next," Sottoriva tells the Telegraph. "By giving us a peek into the future, we could potentially use this AI tool to intervene at an earlier stage, predicting cancer's next move."