A new AI tool could show which advanced bowel cancer patients will respond to bevacizumab, a drug recently introduced by the NHS.
Researchers at London’s Institute of Cancer Research (ICR) and the RCSI University of Medicine and Health Sciences in Dublin developed the PhenMap tool with the goal of sparing potentially thousands of patients from being given drugs that would be ineffective in fighting their cancers.
Anguraj Sadanandam, a professor in stratification and precision medicine at the ICR, said: “Once bowel cancer spreads to other parts of the body, there are very few treatment options available for patients. It is therefore positive that patients can now access the targeted drug bevacizumab on the NHS.
“However, we know that the majority of patients won’t benefit from the drug, meaning thousands of people in England could be facing unpleasant side effects unnecessarily.
“Until now, we haven’t been able to identify these patients.”
In the UK alone, nearly 10,000 cases of advanced bowel cancer are identified every year, with young adults seeing a particular rise in diagnoses.
Bowel cancer has the second highest mortality rate of any cancer, behind only lung cancer, and while survival rates can be as high as 98 per cent when caught early, the five-year survival rate for advanced bowel cancer can be as low as 10 per cent.
The study tracked 117 European bowel cancer patients who had been treated with chemotherapy and bevacizumab, a drug that was approved by the NHS in December.
Bevacizumab works by slowing the rate at which cancer develops by depriving tumours of the proteins they need to grow, but is only effective for a small pool of patients and carries serious side effects such as blood clots and gastrointestinal issues.
Using PhenMap, an AI tool whose name combines “phenotype”, meaning an organism’s observable traits, and “mapping”, researchers said they were able to integrate complex data on the genetic make-up of the tumour.
This allowed them to track patterns of how different patients reacted to the drug, as well as identify a group of patients who all had the same gene mutation and were at high risk of negative reactions.
Following this, the scientists behind the work hope to expand the number of patient samples, as well as see whether the results from the study can be used in the treatment of other types of cancer.
Sadanandam said: “Our research uses advanced AI methods to pull together large amounts of complex data, helping us to spot patterns that would otherwise be impossible for a human to see, and to uncover the clues hidden within a patient’s tumour.
“In our research, we have shown that this allows us to identify the patients least likely to respond to treatment with bevacizumab.”
But while he said the findings were encouraging, he added that the tool would need to be tested on a larger cohort to be validated.
“In future, I hope this approach will lead to a test that can be used by clinicians, to ensure patients receive personalised care that has the highest chance of working against their cancer,” Sadanandam said.
