New AI Algorithm Can Accurately Predict Biological Therapy Needs for Crohn’s Disease, Sheba Medical Center Study Finds
Research conducted at Sheba Medical Center at Tel Hashomer has revealed that machine-learning analysis of complete capsule endoscopy (CE) videos at the initial diagnosis can accurately predict the need for biological therapy to treat Crohn’s disease (CD). This breakthrough could potentially revolutionize the way this gastroenterological disorder is diagnosed and managed.
The study, led by Prof. Uri Kopylov, director of the irritable bowel disease unit at Sheba, Prof. Shomron Ben-Horin, director of the gastroenterology department, and Intel engineering director Amit Bleiweiss, utilized an artificial intelligence (AI) algorithm to analyze CE videos of CD patients. The algorithm achieved an impressive 81% accuracy rate, surpassing the accuracy of gastroenterologists who rely on doctoral analysis of stool samples’ inflammatory index.
Crohn’s disease is a chronic condition characterized by inflammation in sections of the digestive system. It affects individuals of all ages, with symptoms typically beginning in childhood or early adulthood. Common symptoms include diarrhea, fatigue, stomach aches, cramps, weight loss, and blood in the stool.
The potential of AI in improving the diagnosis and treatment of CD is highlighted by Prof. Kopylov, who states, “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. 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.”
In the study, the Sheba doctors and data researchers utilized a newly developed deep learning model to analyze CE videos from 101 CD patients, achieving the 81% accuracy level. Capsule endoscopy allows for a comprehensive analysis of the entire digestive system using a microscopic device equipped with a transmitter and camera. However, due to the large amount of visual information captured in each video, it becomes challenging for doctors to discern all necessary details. This is where AI algorithms can step in and provide a more comprehensive and accurate analysis.
The research builds upon a trial conducted last year, where the AI algorithm proved its ability to scan a film containing up to 12,000 images in just two minutes. Additionally, the study found that AI analysis was highly effective in diagnostic tasks, achieving 86% accuracy in image and data analysis compared to the 68% accuracy achieved by experienced gastroenterologists. Furthermore, AI analysis showed superior performance compared to the analysis of the inflammatory index in stool samples.
Dr. Eyal Klang, head of the Sami Sagol AI Hub at Sheba’s ARC Innovation Center, emphasizes the potential of AI in transforming healthcare systems and improving patient outcomes. “Our findings are further proof of the powerful impact that AI can have in transforming our health systems and driving positive patient outcomes,” says Dr. Klang. “Building on our successful collaboration with Intel, we are looking ahead to further validations of this technology and seeing it implemented in hospitals and clinics worldwide.”
Crohn’s disease impacts over 10 million people worldwide, and current predictors of disease prognosis and treatment response remain unknown. The introduction of AI algorithms in analyzing CE videos could provide valuable insights for physicians and help tailor personalized treatment plans for CD patients. The implementation of these findings in clinical practice has the potential to improve patient outcomes and revolutionize the management of this chronic disease.