‘Never done before’ AI study could improve early detection of pancreatic cancer

Scientists are investiging if artificial intelligence (AI) could be used to improve early diagnosis of pancreatic cancer.

A new study led by Edge Hill University researchers – made possible by a £100,000 start-up grant funded in part by Cancer Research UK – will investigate for the first time whether AI is capable of detecting early signs of pancreatic cancer before symptoms even appear.

Pancreatic Cancer UK and the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI), are also funding the grant.

Desperate need for a breakthrough

There are around 10,300 new pancreatic cancer cases in the UK every year, with around 8 in 10 being diagnosed at a late stage in England and Scotland. And just 1 in 10 GPs say they have the tools needed to diagnose the disease early enough for treatment to be possible, a poll for Pancreatic Cancer UK also revealed.

Dr Ardhendu Behera, reader in Computer Vision & AI at Edge Hill and lead researcher on the project, said pancreatic cancer progresses very rapidly and is one of the most dangerous types of cancer, due in part to the lack of early detection technology.

“Symptoms are usually very vague and do not appear until the cancer is in its later stages, at which point it is sadly too late to treat effectively in most cases.”

As a result, scientists have been attempting to unearth ways to detect early stages of pancreatic cancer for many years – and are now looking to AI.

The team – led by researchers at Edge Hill with the help of co-ordinator institution Queen Mary University of London and involving researchers from University College London, Manchester Metropolitan University and the University of Hertfordshire – will spend a year investigating whether it’s possible to use AI to identify possible predictors of pancreatic cancer.

“In those areas of cancer research where progress has been particularly difficult, bringing together researchers across different disciplines is the way forward,” said Mitchell.

Dr Chris MacDonald, Head of Research at Pancreatic Cancer UK, pointed out that applying AI to pancreatic cancer detection has “never been done before” until now.

A potentially life-saving study

Researchers will use data from patients already diagnosed with pancreatic cancer, allowing them to use AI to identify potential biomarkers and risk groups who are more likely to develop the disease in the future.

Behera said: “Using routinely collected data such at CT/MRI, health conditions, pathology and blood tests, the AI can identify the possible predictors of pancreatic cancer and will screen out people at high risk.

“The potential of AI is incredible, and in this instance could help to save and extend the lives of patients.”

MacDonald said AI could play a critical role in predicting which of the thousands of people a year who visit their GP with vague symptoms – like back pain, weight loss and indigestion – are at risk of having pancreatic cancer.

“Helping to determine whether people need closely monitoring, or even urgently referring for scans, could save lives,” he said.

“I’m hopeful this innovative project might bring us closer to being able to diagnose cancer at an early stage, and with it the hope of better outcomes for people with pancreatic cancer,” added Mitchell.