Abraham R. Eliakim

KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes

Background and aims  Capsule endoscopy (CE) has revolutionized small-bowel (SB) investigation. Computational methods can enhance diagnostic yield (DY); however, incorporating machine learning algorithms (MLAs) into CE reading is difficult as large amounts of image annotations are required for training. Current databases lack graphic annotations of pathologies and cannot be used. A novel database, KID, aims to provide a reference for research and development of medical decision support systems (MDSS) for CE. Methods  Open-source software was used for the KID database. Clinicians contribute anonymized, annotated CE images and videos. Graphic annotations are supported by an open-access annotation tool (Ratsnake). We detail an experiment based on the KID database, examining differences in SB lesion measurement between human readers and a MLA. The Jaccard Index (JI) was used to evaluate similarity between annotations by the MLA and human readers. Results  The MLA performed best in measuring lymphangiectasias with a JI of 81 ± 6 %. The other lesion types were: angioectasias (JI 64 ± 11 %), aphthae (JI 64 ± 8 %), chylous cysts (JI 70 ± 14 %), polypoid lesions (JI 75 ± 21 %), and ulcers (JI 56 ± 9 %). Conclusion  MLA can perform as well as human readers in the measurement of SB angioectasias in white light (WL). Automated lesion measurement is therefore feasible. KID is currently the only open-source CE database developed specifically to aid development of MDSS. Our experiment demonstrates this potential.

Su1121 Anti-TNF and Anti-Drug Antibodies Levels Predict the Outcomes of Interventions After Loss of Response to Adalimumab and Infliximab

Background: Anti-TNFalpha agents are commonly used for ulcerative colitis (UC) therapy in the event of non-response to conventional strategies or as colon-salvaging therapy. The objectives were to assess the appropriateness of biological therapies for UC patients and to study treatment discontinuation over time, according to appropriateness of treatment, as a measure of outcome. Methods: We selected adult ulcerative colitis patients from the Swiss IBD cohort who had been treated with anti-TNFalpha agents. Appropriateness of the firstline anti-TNFalpha treatment was assessed using detailed criteria developed during the European Panel on the Appropriateness of Therapy for UC. Treatment discontinuation as an outcome was assessed for categories of appropriateness. Results: Appropriateness of the first-line biological treatment was determined in 186 UC patients. For 64% of them, this treatment was considered appropriate. During follow-up, 37% of all patients discontinued biological treatment, 17% specifically because of failure. Time-to-failure of treatment was significantly different among patients on an appropriate biological treatment compared to those for whom the treatment was considered not appropriate (p=0.0007). Discontinuation rate after 2 years was 26% compared to 54% between those two groups. Patients on inappropriate biological treatment were more likely to have severe disease, concomitant steroids and/or immunomodulators. They were also consistently more likely to suffer a failure of efficacy and to stop therapy during follow-up. Conclusion: Appropriateness of first-line anti-TNFalpha therapy results in a greater likelihood of continuing with the therapy. In situations where biological treatment is uncertain or inappropriate, physicians should consider other options instead of prescribing anti-TNFalpha agents.

Su1224 Small Bowel Mucosal Healing and Deep Remission in Patients With Known Small Bowel Crohn's Disease

Small bowel mucosal healing and deep remission in patients with known small bowel Crohns disease. U. Kopylov*1, D. Yablecovitch2, A. Lahat2, S. Neuman2, N. Levhar2, E. Klang3, M.M. Amitai3, S. Ben-Horin2, R. Eliakim2 1Sheba Medical Center, Gastroenterology, Tel Hashomer, Israel, 2Chaim Sheba Medical Center, Gastroenterology, Ramat Gan, Israel, 3Sheba Medical Center, Department of Diagnostic Imaging, Tel Hashomer, Israel