Sheba Medical Center, Israel’s largest medical center, today announced a collaboration with Intel Corporation to help doctors improve the diagnosis and treatment of people with Crohn’s disease. Sheba developed a new, first-of-its-kind application capable of quickly and accurately analyzing extensive video data of a patient’s digestive system, providing valuable insights to aid medical professionals.
The solution’s artificial intelligence-based algorithm, powered by Intel hardware and software technologies, aids clinicians in the identification of Crohn’s symptoms such as inflammation and ulcers, helping to assist in early prediction of disease severity in order to identify treatment needs. Not only will this predictive capability help medical teams provide optimal and personalized care for millions of Crohn’s patients worldwide, it can help lower the risks of severe medical complications, hospitalization, and invasive surgical procedures for these patients. This is the first app that analyzes capsule videos from the digestive system of patients, and by presenting meaningful information to the doctors, helping them to recommend better treatment for the patient.
“Predicting the course of the disease in Crohn’s patients is one of the most important clinical challenges in the treatment of inflammatory bowel disease. However, currently available tools are limited and insufficiently accurate,” said Prof. Uri Kopylov, Director of IBD in the Department of Gastroenterology at Sheba Medical Center. “The Gastro Institute at Sheba has conducted ongoing and extensive research to identify and improve tools for diagnosis, follow-up and treatment.”
One of the primary tools used by gastroenterologists today is an endoscopic capsule, or “camera pill”. The capsule allows for the analysis of the entire digestive system using a microscopic device equipped with a transmitter and camera. However, every capsule film produced includes approximately 10 – 12 thousand images for interpretation. Due to the large amount of visual information in each video, it is difficult for a doctor to discern all necessary details.
Following recent joint research that analyzed capsule videos of 101 new Crohn’s patients at Sheba, an algorithm was developed to predict the need for biological treatment. The AI algorithm was the most accurate diagnostic tool, with 86% accuracy in prediction of treatment decisions compared to 70% accuracy achieved by manual reading by a capsule endoscopy expert, or 74% accuracy of the most accurate stool biomarker (fecal calprotectin). The algorithm can scan a film of 10 – 12 thousand images in about 2 minutes.
“Accelerate, Redesign and Collaborate (ARC) focuses on advanced technologies with the goal to make impact on medicine in Israel and globally through digital health solutions,” said Dr. Eyal Klang, Head of the Sami Sagol AI (Artificial Intelligence) Hub at the ARC Innovation Center. “This collaboration with Intel exceeded expectations and is further proof of the contribution of artificial intelligence to the medical field. Over the next decade we will see more and more advanced algorithms entering hospitals and supporting doctors’ work.”
“It is inspiring to see how technology can help to bolster the great work being done each day by scientists and health care professionals,” said Yaniv Garty, general manager of Intel Israel. “The integration of AI within a health system, like Sheba, has the capacity to convert vast amounts of data into actionable insights, helping medical professionals to improve the overall health and well-being of individuals across the globe.”
The technological achievement was presented at the annual conference of the Israeli Association of Gastroenterology and the annual conference of the European Organization for Inflammatory Bowel Diseases (ECCO). The app will be available for use by Sheba doctors in the coming months. In the future, it will be made available to a wider array of medical centers in Israel and abroad.
