Artificial Intelligence to Predict Cancer Growth

By Urenna Ukiwe |   04 September 2018   |   12:00 pm  

One of the major challenges faced in treating cancer is the constantly changing nature of tumours hence proposed treatment at a particular time may not be effective because tumours become resistant to drugs or proposed treatment.

Artificial Intelligence in a new development has come in useful in predicting how cancers will progress and evolve, and this will go a long way in helping doctors propose the most effective treatment for each patient.

Advertisement
Advertisement

A team led by the Institute of Cancer Research London[ICR] and the University of Edinburgh developed a new technique known as Revolver [Repeated Evolution of Cancer]

This technique notes and selects the system in DNA mutation within cancers and uses the information to predict future genetic changes.

Cancer evolves unpredictably but if doctors can predict how the tumours evolve, they could step in and stop it before it advances or develops and increase the patient’s chances of survival.

Cancer-cells-dividing. Photo: Medical News Today

The team also discovered a link between a certain pattern of recurrent tumour mutations and survival outcomes.
This indicates that repeating patterns of DNA mutations could be used as a means of prognosis, helping to build future treatment.

The research team developed a new machine learning technique which identifies patterns in genetic mutations that happen in tumours and applying the patterns to predict another.

Dr Andrea Sottoriva who is a team leader in evolutionary genomics and modelling at the ICR said: “We’ve developed a powerful artificial intelligence tool which can make predictions about the future steps in the evolution of tumours based on certain patterns of mutation that have so far remained hidden within complex data sets.”
“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.”

Advertisement
Advertisement

You may also like