Using artificial intelligence and blood tests to detect the earliest signs of bowel cancer

​

Scientists can detect certain molecules in our blood – called biomarkers – to diagnose specific cancers. This approach has the potential to be cheaper and simpler than existing tests, which could enable health systems to screen more people for cancer.

 

Blood tests for cancer could also be less invasive than our current diagnostic tools, such as colonoscopies for bowel cancer, encouraging more people to attend their screening appointments.

 

While detecting cancer biomarkers in blood holds promise, the current state-of-the-art tests aren’t accurate enough and take too long to give results.

​

In London, Dr Oleg Blyuss is using the rich data that researchers collected during the UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS) to improve cancer blood tests.

 

UKCTOCS recruited over 200,000 women between 2001 and 2005 and collected a wide range of clinical and biomarker data on them over time. This unique resource recently became available for the first time, and Dr Blyuss is applying artificial intelligence (AI) technology to recognise patterns in data and make predictions based on those patterns.