For the treatment of the gastroenterological ailment known as Crohn’s disease (CD), research at the Sheba Medical Centre in Tel Hashomer has demonstrated that machine-learning analysis of entire capsule endoscopy (CE) videos at initial diagnosis can reliably identify the need for biological therapy.
A gastroenterologist utilising a doctoral study of the inflammatory index in stool samples (calprotectin) had a diagnosis of CD that was 81% accurate, but the artificial intelligence algorithm using such movies to diagnose CD had a diagnosis that was 81% accurate.
People of all ages are affected by CD, a chronic disorder in which certain parts of the digestive system become inflamed. The symptoms of CD typically appear in infancy or early adulthood. Diarrhoea, exhaustion, stomach aches, cramps, weight loss, and blood in the stool are a few of these symptoms.
The team, led by Professor Uri Kopylov, Director of the IBD Unit at Sheba, Professor Shomron Ben-Horin, Director of the Gastroenterology Department, and Intel Engineering Director Amit Bleiweiss, published a paper in the journal Therapeutic Advances in Gastroenterology with the title “Spatiotemporal analysis of small bowel capsule endoscopy videos for outcomes prediction in Crohn’s disease.”
“Predicting disease course and patient outcomes for the disease is one of the most critical clinical challenges in inflammatory bowel disease treatment, but our research highlights the potential impact of AI on this process,” said Kopylov.
“By adopting AI in clinical practice, we can begin to use our wealth of knowledge and research in personalized medicine to drive improved patient outcomes and open the door to new possibilities for diagnosis and treatment.”
Every capsule film created for capsule endoscopy, which uses a microscopic device with a transmitter and camera, provides 10,000 to 12.000 images for interpretation. The doctors can make the appropriate deductions with the aid of the AI algorithms.
| Read More news: Click here |
