Sheba Medical Center at Tel Hashomer is launching a collaboration with Intel Corporation to help doctors improve the diagnosis and treatment of people with Crohn’s disease, the medical center announced Tuesday.
Sheba has developed a first-of-its-kind application that it reports can quickly and accurately analyzing extensive video data of a patient’s digestive system captured on capsule video cameras, providing valuable insights to aid medical professionals.
The solution’s artificial intelligence-based algorithm, powered by Intel hardware and software technologies, is designed to help clinicians identify Crohn’s symptoms such as inflammation and ulcers as well as predict the severity of a case and help identify the patient’s treatment needs.
According to Sheba, not only will this predictive capability help medical teams provide optimal, personalized care for Crohn’s patients, it can help lower the risks of severe medical complications, hospitalization, and invasive surgical procedures for these patients.
Professor Uri Kopylov, Director of IBD in the Department of Gastroenterology at Sheba, explains that “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.”
“The Gastro Institute at Sheba has conducted ongoing and extensive research to identify and improve tools for diagnosis, follow-up and treatment,” Kopylov said.
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 10,000-12,000 images, making it 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 10,000-12,000 images in about two 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.”
Yaniv Gerty, general manager of Intel Israel, said, “It’s inspiring to see how technology can help to bolster the great work being done each day by scientists and health care professionals. 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 new technology 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 plan is for the app to be made available to Sheba doctors in the coming months and expanded to wider array of medical centers in Israel and abroad in the future.
Published July 26, 2022 Israel Hayom