Ustekinumab and vedolizumab for extraintestinal manifestations in inflammatory bowel disease - a retrospective study.

INTRODUCTION: Extraintestinal manifestations (EIM) are associated with diminished quality of life. The efficacy of Ustekinumab and vedolizumab for EIM treatment is not well established. The aim was to compare the effectiveness of ustekinumab and vedolizumab for treatment of EIM in IBD. METHODS: We included IBD patients treated with vedolizumab or ustekinumab in the Gastroenterology department, Sheba Medical Center, for up to 52 weeks between 2015 and 2021. Patients with active EIM before treatment initiation were included. RESULTS: 111 patients were included. 53 patients (48%) were treated with ustekinumab; 88% (n-99) had CD. The most common EIM was arthralgia (95/111, 84%). Patients treated with ustekinumab were more likely to be anti-TNF experienced (n-51/53 [96%] compared with vedolizumab n = 36/58 [62%], p < 0.001). Clinical response of EIM at week 52 was achieved in 36% of patients treated with ustekinumab (n-18/50) and 34% of patients (n-19/54) treated with vedolizumab, with no statistically significant difference (p = 0.9). No statistical significance was achieved for patients presented with arthralgia. Clinical response of arthralgia at week 52 was seen in 34% (n-19/55) and 36% (n-18/46) of the patients treated with vedolizumab and ustekinumab, respectively, (p = 0.3). CONCLUSION: In this study, no difference was found between vedolizumab and ustekinumab regarding their effect on EIM in IBD patients for up to 52 weeks.

Deep Learning Multi-Domain Model Provides Accurate Detection and Grading of Mucosal Ulcers in Different Capsule Endoscopy Types.

BACKGROUND AND AIMS: The aim of our study was to create an accurate patient-level combined algorithm for the identification of ulcers on CE images from two different capsules. METHODS: We retrospectively collected CE images from PillCam-SB3's capsule and PillCam-Crohn's capsule. ML algorithms were trained to classify small bowel CE images into either normal or ulcerated mucosa: a separate model for each capsule type, a cross-domain model (training the model on one capsule type and testing on the other), and a combined model. RESULTS: The dataset included 33,100 CE images: 20,621 PillCam-SB3 images and 12,479 PillCam-Crohn's images, of which 3582 were colonic images. There were 15,684 normal mucosa images and 17,416 ulcerated mucosa images. While the separate model for each capsule type achieved excellent accuracy (average AUC 0.95 and 0.98, respectively), the cross-domain model achieved a wide range of accuracies (0.569-0.88) with an AUC of 0.93. The combined model achieved the best results with an average AUC of 0.99 and average mean patient accuracy of 0.974. CONCLUSIONS: A combined model for two different capsules provided high and consistent diagnostic accuracy. Creating a holistic AI model for automated capsule reading is an essential part of the refinement required in ML models on the way to adapting them to clinical practice.

[ACUTE RENAL FAILURE INDUCED BY METAMIZOLE].

INTRODUCTION: Sodium metamizole (Optalgin) is one of the most prevalent analgesic and anti-pyretic medications used in Israel. We describe a case of acute kidney injury subsequent to the use of metamizole in a healthy young patient. Metamizole may cause kidney injury in a number of different mechanisms and it is vital that this fact will be emphasized due to the widespread use of this medication.