Artificial Intelligence (AI) is now being used to check for colorectal cancer in people with Lynch syndrome, who are more likely to have a hereditary risk of colon cancer.
Even with regular endoscopic surveillance, the risk of colon cancer in people with Lynch syndrome remains elevated. Researchers from the National Center for Hereditary Tumor Diseases (NZET) at Bonn University Hospital are now using AI to improve the efficacy of colonoscopies in the presence of Lynch syndrome.
The results of the study have been published in the United European Gastroenterology Journal.
What is Lynch syndrome?
Lynch syndrome, also known as hereditary non-polyposis colorectal cancer, is the most common hereditary colorectal cancer syndrome. It is understood to affect around 300,000 people in Germany alone.
Lynch syndrome is responsible for about 2-3% of all colon-related cancers. The disease is triggered by defects in the genes responsible for repairing the human genetic material DNA.
The offspring of affected individuals have a 50% risk of having the same pathologically altered hereditary disposition. This is technically known as a mutation, therefore a high risk of developing colon cancer at a young age is present.
Due to the high risk, regular monitoring via colonoscopy is recommended every one to two years.
“However, despite such regular endoscopic monitoring, the risk of colorectal cancer remains elevated in those affected,” said Professor Jacob Nattermann, head of the Hepatogastroenterology Section at UKB’s Medical Clinic.
According to the researchers, colonoscopy still misses a considerable number of adenomas, the potential precursors of colorectal cancer.
“Small and flat adenomas in particular are at risk of being overlooked even by experienced gastroenterologists,” added Professor Nattermann.
Recent data has suggested that AI-assisted colonoscopies, also known as computer-aided detection (CADe), could help improve rates of adenoma detection in the general population.
“Therefore, the aim of our study was to evaluate the diagnostic performance of AI-assisted colonoscopy in patients with Lynch syndrome,” said Robert Hüneburg, senior physician at the University of Bonn’s Medical Clinic.
AI-assisted colonoscopies are more effective than traditional colonoscopies
The University of Bonn researchers worked in close collaboration with the Institute of Medical Informatics, Statistics and Epidemiology at the University of Leipzig on the study. The team examined 46 Lynch syndrome patients who used standard endoscopy and 50 Lynch syndrome patients who used AI-assisted colonoscopy between December 2021 and December 2022.
Results showed that significantly more of the AI-assisted examinations (36%) detected adenomas than the standard examinations (26.1%).