Artificial intelligence developed by researchers at University College London has revealed a promising combination of cancer treatments that could help patients with locally advanced rectal cancer live longer, according to a July 27 announcement.
A study published in eBioMedicine found that combining the chemotherapy drug irinotecan with standard chemoradiotherapy improved survival for patients whose tumors had a high concentration of cancerous cells. The AI system was trained to distinguish patients based on their tumor cell density using biopsy samples taken at diagnosis. For those with high tumor cell density, adding irinotecan reduced the risk of cancer recurrence by about 43% and reduced the risk of death by about 50% compared to those who received typical treatment with capecitabine and radiation therapy. No benefit was observed for patients with low concentrations of cancer cells.
Irinotecan is commonly used to treat advanced bowel cancer. Although it has been considered a potential option for advanced rectal cancer when combined with chemoradiotherapy, previous studies did not show improved outcomes. The AI allowed researchers to efficiently sort patient samples into high and low concentration groups, revealing which individuals benefited from the treatment. The team also developed an online tool called Octopath, enabling clinicians to upload biopsy slides for analysis.
Lead author Dr. Zhuoyan Shen said, "While the original trial showed little benefit from adding irinotecan, by using artificial intelligence we found that we could distinguish patients who actually benefitted from those who did not. This demonstrates how AI can reveal tumor biology that is difficult to measure consistently by conventional means, and hopefully can be used to reveal additional insights that could lead to future treatments." Colorectal cancer is noted as the fourth most fatal cancer in the UK and often recurs at advanced stages.
The research analyzed data from 414 biopsy samples collected during the ARISTOTLE trial across 75 UK hospitals. Of these, 188 were classified as having high concentrations of tumor cells while 226 had low concentrations. Automating cell identification through AI allows more efficient scaling so more patients might receive appropriate treatment without unnecessary side effects.
Senior author Professor Maria Hawkins said, "Intensifying already taxing treatments puts additional strain on patients suffering from cancer. Clinicians need reliable ways to identify who is most likely to benefit before such treatments begin so potential side effects are avoided. Our findings show that doctors assisted by AI can pinpoint which patients will likely benefit from the more intensive treatment before it begins." Researchers stated further clinical studies are needed before widespread use.
