AI opens pathway to improved targeting of bowel cancer treatment

Scientists in the UK and Ireland have developed a method to help identify patients whose metastatic bowel cancer is most likely to respond to a targeted drug – potentially sparing many patients from futile treatments.

The drug, bevacizumab, is available in Australia and is used to treat several cancers. Although it can slow the growth of cancer, it can carry the risk of serious side effects including hypertension, gastrointestinal problems and blood clots.

Bowel cancer is Australia’s fourth most common cancer, with 15,000 people diagnosed annually, with around 2500 being stage 4 (metastatic) at diagnosis.

The new method for identifying which patients would best respond to bevacizumab  was developed by scientists at London’s Institute of Cancer Research (ICR) and RCSI University of Medicine and Health Sciences, Dublin, using artificial intelligence (AI). They studied 117 European patients who had been treated with the drug and chemotherapy, looking to identify patterns linked to resistance.

The team used an AI tool developed at the ICR called PhenMap – an abbreviation of phenotype mapping – to integrate complex data on the genetic make-up of the tumour with clinical information such as a patient’s gender and age, and which side of the body carried the tumour. They used this to search for new biological signals – patterns relevant to a patient’s response to bevacizumab.

The AI tool was able to pick up more complicated patterns than the scientists had previously been able to identify, leading to the ranking of patients according to the risk of dying after treatment with bevacizumab and chemotherapy. 

Based on clinical outcomes, the researchers noted that none of the patients in the “high risk” group responded to the treatment. Their findings were reported in the journal Scientific Reports.

“Once bowel cancer spreads to other parts of the body, there are very few treatment options available for patients,” noted Anguraj Sadanandam, Professor in Stratification and Precision Medicine at ICR.

“However, we know that the majority of patients won’t benefit from [bevacizumab], meaning thousands of people could be facing unpleasant side effects unnecessarily. Until now, we haven’t been able to identify these patients …

“While these findings are encouraging, they will need to be validated in a larger cohort, to ensure they are applicable to all patients. 

“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.”

The researchers will also explore whether the AI tool can predict responses to other targeted therapies, and they believe that the method could be applied to other cancer types.

Understanding why certain patients won’t benefit from a particular treatment was crucial to improving outcomes, according to the ICR’s chief executive, Professor Kristian Helin.

“AI has revolutionised cancer research – by enabling us to rapidly analyse large, complex datasets and predict how patients will respond to treatment,” he said. “This research is a powerful example of how the ICR is leveraging AI to develop smarter, kinder therapies, and deliver them to patients sooner. 

“This approach also has the potential to be explored in many cancer types, and it will be interesting to see whether the method can predict responses to other targeted therapies across a range of cancer types.”