AI models could predict ulcerative colitis flare-ups and complications after reading biopsies taken during colonoscopies
Gastroenterology has today, Friday 3rd March, published a new paper from researchers supported by the National Institute for Health and Care Research Birmingham Biomedical Research Centre suggesting that an AI diagnostic tool that can read digitised biopsies taken during colonoscopy and help identify future ulcerative colitis flare-ups.
What is ulcerative colitis?
“Ulcerative colitis is a long-term condition where the colon and rectum become inflamed. The colon is the large intestine (bowel) and the rectum is the end of the bowel where faeces is stored. Small ulcers can develop on the colon’s lining, and can bleed and produce pus.”
Symptoms of ulcerative colitis
The main symptoms of ulcerative colitis include the following:
- Recurring diarrhoea, which may contain blood, mucus or pus
- Stomach pain
- Needing to go to the toilet frequently
- Extreme tiredness (fatigue)
- Loss of appetite
- Weight loss
However, symptoms and severity of symptoms can vary depending on how severely inflamed the rectum and colon is.
The condition is different for every individual, but in many circumstances, it can have a significant impact on a person’s day-to-day life.
What are the symptoms of an ulcerative colitis flare-up?
Naturally, flare-ups and their symptoms vary on an individual basis.
Some people may go for weeks or months with very mild symptoms or none (remission), followed by periods where the symptoms are particularly bad (flare-ups or relapses).
During a flare-up, some people with ulcerative colitis also experience symptoms elsewhere in their bodies. These symptoms are known as extra-intestinal symptoms.
Extra-intestinal symptoms include:
- Painful and swollen joints (arthritis)
- Mouth ulcers
- Swollen fat under the skin which causes bumps and patches (erythema nodosum)
- Irritated, red eyes
- Bones problems, such as osteoporosis
- Often there is no specific trigger of flare-ups identified, although a gut infection can occasionally be the cause
- Stress is another potential factor
Computer-Aided Diagnostic models can predict the risk of flare-ups
The Computer-Aided Diagnostic model predicted the risk of flare-ups for ulcerative colitis. This is especially useful for ulcerative colitis because it is a relapsing-remitting condition which makes the prognosis for the disease uncertain. In the trial, the model could predict patients at risk of an ulcerative colitis flare-up.
The system was trained on existing digitised biopsies and could detect activity related to ulcerative colitis with an impressive 89% accuracy for positive results. Like human pathologists, the AI could also identify markers of inflammation activity and healing in the same area as biopsies were taken with 80% accuracy.
The power of AI in healthcare
Professor Marietta Iacucci from the Institute of Immunology and Immunotherapy at the University of Birmingham and University College Cork in Ireland, and co-lead author of the paper concludes:
“The power of AI in healthcare is evident in trials like these, where a model can be used to standardize in real-time histological assessment of Ulcerative Colitis disease activity. But most importantly it provides analytical support and enables clinicians to support those at the greatest risk of relapsing symptoms and disease course.
“Ulcerative Colitis is a complex condition to predict”
“Ulcerative Colitis is a complex condition to predict, and developing machine learning-derived systems to make this diagnostic job quicker and more accurate could be a game changer. As models like this further develop, the predictive quality is likely to improve even more, and our paper demonstrates how beneficial such technology could be for clinicians and, crucially patients.”
