The COLO-DETECT study will help doctors identify polyps during colonoscopy examinations, making sure that more patients benefit from early intervention
"AI could help reduce variation in colonoscopy, among endoscopists but also among individual doctor’s performance. It is well known that doctors tend to spot more polyps or adenomas in the morning than the afternoon, for example." Dr Tom Lee, consultant gastroenterologist at Northumbria Healthcare NHS Foundation Trust
Nine trusts are taking part in a clinical trial of an artificial intelligence (AI) device designed to save the lives of people with bowel cancer.
The COLO-DETECT study is investigating a device called GI Genius, which helps doctors identify polyps during colonoscopy examinations. The device, which is integrated with the colonoscopy equipment, analyses images from endoscopies in real-time and highlights areas it thinks may contain polyps. This then enables doctors to investigate those areas more closely.
Most bowel cancers develop from a type of polyp – called an adenoma – that becomes cancerous. It is important to identify as many polyps as possible to decide whether they need to be removed, as this may prevent a polyp becoming cancerous in the future.
So far, 500 patients have been recruited into the study, and the aim is to recruit more than 2,000 patients over the next year. The £896,000 trial is being funded by technology provider Medtronic.
The study is being led by led by Professor Colin Rees, a consultant gastroenterologist at South Tyneside and Sunderland NHS Foundation Trust. “Tragically around 16,000 people die from bowel cancer each year, making it the UK’s second biggest cancer killer,” Rees said. “Bowel cancer rates are very high in the North East – men in this region have the highest bowel cancer incidence rates in England with women also in the upper half of incidence rates.
“Sadly, survival rates for men and women in the North East are also amongst the lowest in the country and the survival rates in the UK are lower than in many other European countries. We want to reduce the number of deaths by diagnosing disease in the bowel before it even becomes cancerous and by finding cancer earlier.”
Dr Tom Lee, a consultant gastroenterologist at Northumbria Healthcare NHS Foundation Trust, has been using the AI technology for four months. He said: “It helps us to spot even very subtle polyps – smaller, flatter or partially hidden in a fold of the bowel. I believe that AI could help reduce variation in colonoscopy, among endoscopists but also among individual doctor’s performance. It is well known that doctors tend to spot more polyps or adenomas in the morning than the afternoon for example. When bowel cancer screening colonoscopies are of a consistently high standard, we can hope to improve bowel cancer outcomes across the NHS.”
The nine trusts taking part in the study are: Northumbria NHS Healthcare Trust, South Tyneside and Sunderland NHS Foundation Trust, North Tees and Hartlepool Hospitals NHS Foundation Trust, South Tees Hospitals NHS Foundation Trust, Newcastle-upon-Tyne Hospitals NHS Foundation Trust, Kettering General Hospital NHS Foundation Trust, The Royal Wolverhampton NHS Trust, Bolton NHS Foundation Trust and University Hospitals of Morecambe Bay NHS Foundation Trust.
“There is great potential for AI and associated techniques across health and care, particularly for image analysis using computer vision techniques. Ensuring tools are reliable, safe and robust is crucial for successful detection of clinical signs.
“Designing good tools and training them on datasets which represent all patients is also important. FCC’s work with NCIMI explored the ways imaging and associated datasets could be brokered with fair value. We are also contributing to the development of standard BSI 30440 for AI in healthcare, which will soon be released for consultation.”
Dr Peter Bloomfield, head of policy and research