Researchers have developed a new test using artificial intelligence (AI) that could help bowel cancer patients avoid unnecessary chemotherapy.

The test helps clinicians determine the risk of bowel cancers recurring by analysing the presence in early-stage tumours of critical immune cells.

Developed by an international team led by researchers at the University of Leeds, the new test draws on an AI algorithm to accurately assess the presence and number of the cells, known as CD3.

Previous studies have shown that tumours containing high numbers of such cells are less likely to return after surgery, as CD3 cells can attack the cancer, helping the body defend itself.

“This has the potential to be the most important test patients with early-stage bowel cancer ask for; it’s fast, accurate and simple, and we hope it will make conversations about chemotherapy after surgery much more straightforward for patients and their doctors,” explained the study’s lead author, Dr Christopher Williams, a research fellow in the University of Leeds’ School of Medicine.

Bowel cancer can occur anywhere in the large bowel, which includes the colon and rectum, and is one of the most diagnosed cancers in the world. In Australia, one in 15 people will develop the disease in their lifetime, with treatments including surgery, chemotherapy, radiation or a combination of such things.

In this latest study, the CD3 “score” derived by the AI-led test reliably showed which cancers were most likely to recur within five years of surgery, helping clinicians decide which patients may need further treatment such as chemotherapy.

“Our study underscores the potential importance of the CD3 score test to bowel cancer patients, providing a critical insight to physicians in driving chemotherapy options for their patients,” said Kandavel Shanmugam, from Roche Tissue Diagnostics in Arizona, who collaborated on the work. Roche has patented the test.

Dr Williams added: “Current methods for deciding which patients with early-stage bowel cancer need chemotherapy, and which do not are unreliable. Many people receive chemotherapy when they don’t need it, and unfortunately some of the people who are not offered chemotherapy go on to experience cancer recurrence.

“It is very difficult to decide whether people with stage II colon cancer, in particular, need chemotherapy after their surgery as there is generally a lower risk that this cancer will come back.”

However, the AI test gave the best possible indication of whether a recurrence was likely.

For their study, the researchers examined tissue from almost 900 bowel tumours at stage II and III to determine the numbers of CD3 cells present, with the AI algorithm calculating a CD3 score based on cell numbers in different areas of the tumour. High-risk scores reflected lower numbers of immune cells, while low-risk scores showed increased numbers of immune cells.

The researchers discovered that tumours with a high-risk CD3 score were three times more likely to have come back five years after surgery than those with a low-risk score. Recurrence rates were reduced in both groups when patients underwent chemotherapy, but the study also showed that patients with lower numbers of immune cells were the most likely to benefit from chemotherapy.

The test results were also found to be reliable for a second set of patients, according to the researchers who said they believed there was a clear rationale for its adoption by health authorities and made available to patients “as soon as possible”.

“The assessment method we trialled gave a stronger indication than any feature we currently assess as to whether a stage II cancer might come back,” said Dr Williams. “This is very useful information for doctors and their patients facing difficult decisions about whether or not to proceed with chemotherapy after surgery.”

Published: August 5, 2024

Latest Articles