Othman, Mohamed O
Mayo Clinic
Department of Gastroenterology and Hepatology, Baylor College of Medicine, Houston, Texas, USA .
Citations 2
Artificial Intelligence in Gastroenterology Education: DeepSeek Passes the Gastroenterology Board Examination and Outperforms Legacy ChatGPT Models
Ibrahim, Andrew , Danpanichkul, Pojsakorn , Hayek, Alberto , Paul, Elahna , Farag, Annmarie , Mansoor, Masab , Cheungpasitporn, Wisit , Othman, Mohamed O. , Ibrahim, Andrew F , Hayek, Alexander , Paul, Edwin , Cheungpasitporn, Wisit , Othman, Mohamed O , Danpanichkul, Pojsakorn , Thongprayoon, Charat
American Journal of Gastroenterology | May 20, 2025 | Volume: 121 | Issue: 4 | Pages: 1041-1043
INTRODUCTION: DeepSeek was evaluated in gastroenterology board examination performance against legacy ChatGPT offline models, which previously showed failing performance. METHODS: The performances of the DeepSeek base R1 model and search-augmented R1 model were assessed using American College of Gastroenterology self-assessments (455 questions). RESULTS: DeepSeek exceeded the passing threshold. Search-augmented DeepSeek scored 81.5% across all questions, and the R1 base model scored 77.1%. Both search-augmented and offline DeepSeek models surpassed offline ChatGPT-3 (65.1%) and ChatGPT-4 (62.4%) ( P < 0.001). DISCUSSION: DeepSeek exhibited passing performance on the gastroenterology board examination but had gaps in niche topics and image exclusion limit utility. It may supplement education if validated by specialists.
A novel through-the-scope helix tack-and-suture device for mucosal defect closure following colorectal endoscopic submucosal dissection: a multicenter study
Farha, Jad , Ramberan, Hemchand, Aihara, Hiroyuki , Zhang, Linda Y. , Mehta, Amit , Hage, Camille , Schlachterman, Alexander , Kumar, Anand , Shinn, Brianna , Canakis, Andrew , Kim, Raymond E., Buscaglia, Jonathan M. , Samarasena, Jason , Chang, Kenneth J. , Friedland, Shai , Qumseya, Bashar , Jawaid, Salmaan , Othman, Mohamed O. , Hasan, Muhammad K. , Khashab, Mouen A., Ngamruengphong, Saowanee , group, ESD-Closure working, Storm, Andrew C , Othman, Mohamed O , Canakis, Andrew , D'Souza, Lionel S. , Storm, Andrew C. , Draganov, Peter V. , Yang, Dennis J. , Khashab, Mouen A. , group, ESD-Closure working
Endoscopy | November 3, 2022 | Volume: 55 | Issue: 06 | Pages: 571-577
Background Complete closure of large mucosal defects following colorectal endoscopic submucosal dissection (ESD) with through-the-scope (TTS) clips is oftentimes not possible. We aimed to report our early experience of using a novel TTS suturing system for the closure of large mucosal defects after colorectal ESD. Methods We performed a retrospective multicenter cohort study of consecutive patients who underwent attempted prophylactic defect closure using the TTS suturing system after colorectal ESD. The primary outcome was technical success in achieving complete defect closure, defined as a < 5 mm residual mucosal defect in the closure line using TTS suturing, with or without adjuvant TTS clips. Results 82 patients with a median defect size of 30 (interquartile range 25–40) mm were included. Technical success was achieved in 92.7 % (n = 76): TTS suturing only in 44 patients (53.7 %) and a combination of TTS suturing to approximate the widest segment followed by complete closure with TTS clips in 32 (39.0 %). Incomplete/partial closure, failure of appropriate TTS suture deployment, and the need for over-the-scope salvage closure methods were observed in 7.3 % (n = 6). One intraprocedural bleed, one delayed bleed, and three intraprocedural perforations were observed. There were no adverse events related to placement of the TTS suture. Conclusion The TTS suture system is an effective and safe tool for the closure of large mucosal defects after colorectal ESD and is an alternative when complete closure with TTS clips alone is not possible.