A new artificial intelligence technique could help us realize the dream of personalized medicine for cancer.
Researchers from The Institute of Cancer Research, London and the University of Edinburgh (both UK) have used artificial intelligence (AI) to predict how cancers will grow and spread. The findings have the potential to help clinicians determine the most effective, personalized treatments.
Tumors often evolve unpredictably, and can develop resistance. The team used a new technique, REVOLVER (repeated evolution of cancer), to find patterns in DNA mutation and use them to forecast genetic changes.
This would allow clinicians to stay one step ahead of the cancer, allowing earlier intervention with the right treatment, and preventing resistance.
“Cancer evolution is the biggest challenge we face in creating treatments that will work more effectively for patients. If we are able to predict how a tumor will evolve, the treatment could be altered before adaptation and drug resistance ever occur, putting us one step ahead of the cancer,” explained Paul Workman (The Institute of Cancer Research, London)
“This new approach using AI could allow treatment to be personalized in a more detailed way and at an earlier stage than is currently possible, tailoring it to the characteristics of each individual tumor and to predictions of what that tumor will look like in the future,” he continued.
REVOLVER involves a machine learning method that includes information from various similar patients, and overcomes problems with data noise that have hindered past research. It identifies patterns in the order mutations occur that are repeated between and within patients. 768 samples from 178 patients with lung, breast, kidney or bowel cancer were included in the study.
“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. 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,” noted Andrea Sottoriva (The Institute of Cancer Research, London).
Certain sequences of mutations were also linked to survival outcome, and thus could be used in prognosis.