Leveraging existing mid-end ultrasound machine for point-of-care intestinal ultrasound in low-resource settings: Prospective, real-world impact on clinical decision-making.

BACKGROUND: Point-of-care ultrasound (POCUS) has transformed inflammatory bowel disease (IBD) management, but the cost to purchase high-end equipment can be prohibitive. AIM: To assess prospectively the feasibility of POCUS using pre-existing mid-end ultrasound equipment without incurring additional cost. METHODS: Consecutive IBD patients underwent POCUS with or without faecal calprotectin (FCP) using a mid-end ultrasound machine. If POCUS with or without FCP could not guide management, we performed additional ileocolonoscopy or cross-sectional imaging. We evaluated the impact of POCUS on IBD management and its correlation with ileocolonoscopy or cross-sectional imaging. We analysed pregnant, paediatric and post-operative patients separately. RESULTS: Among 508 patients with IBD, we analysed 419 (60.4% Crohn's disease [CD]; 61.3% male, age [years]: 36 [18-78]) undergoing 556 POCUS sessions. POCUS with or without FCP independently influenced clinical management in 42.8% of patients with CD and 49.7% with ulcerative colitis (UC). POCUS helped avoid colonoscopy in 51.4% of patients with CD and 51.8% with UC, and cross-sectional imaging in 38.1% of suspected active small bowel CD. In patients with additional diagnostics, POCUS-based decisions remained unchanged in 81.2% with CD and 85% with UC. Sensitivity and specificity of POCUS compared to ileocolonoscopy were 80% and 94.4% for CD and 80.8% and 92.8% for UC, respectively. Sensitivity and specificity compared to cross-sectional imaging were 87.2% and 87.5%, respectively. CONCLUSION: POCUS using existing mid-end ultrasound equipment in low-resource settings influenced IBD clinical decision-making with excellent accuracy, often avoiding colonoscopy and cross-sectional imaging.

Artificial intelligence in endoscopy related to inflammatory bowel disease: A systematic review.

BACKGROUND AND OBJECTIVES: In spite of rapid growth of artificial intelligence (AI) in digestive endoscopy in lesion detection and characterization, the role of AI in inflammatory bowel disease (IBD) endoscopy is not clearly defined. We aimed at systematically reviewing the role of AI in IBD endoscopy and identifying future research areas. METHODS: We searched the PubMed and Embase database using keywords ("artificial intelligence" OR "machine learning" OR "computer-aided" OR "convolutional neural network") AND ("inflammatory bowel disease" OR "ulcerative colitis" OR "Crohn's") AND ("endoscopy" or "colonoscopy" or "capsule endoscopy" or "device assisted enteroscopy") between 1975 and September 2023 and identified 62 original articles for detailed review. Review articles, consensus guidelines, case reports/series, editorials, letter to the editor, non-peer-reviewed pre-prints and conference abstracts were excluded. The quality of the included studies was assessed using the MI-CLAIM checklist. RESULTS: The accuracy of AI models (25 studies) to assess ulcerative colitis (UC) endoscopic activity ranged between 86.54% and 94.5%. AI-assisted capsule endoscopy reading (12 studies) substantially reduced analyzable images and reading time with excellent accuracy (90.5% to 99.9%). AI-assisted analysis of colonoscopic images can help differentiate IBD from non-IBD, UC from non-UC and UC from Crohn's disease (CD) (three studies) with 72.1%, 98.3% and > 90% accuracy, respectively. AI models based on non-invasive clinical and radiologic parameters could predict endoscopic activity (three studies). AI-assisted virtual chromoendoscopy (four studies) could predict histologic remission and long-term outcomes. Computer-assisted detection (CADe) of dysplasia (two studies) is feasible along with AI-based differentiation of high from low-grade IBD neoplasia (79% accuracy). AI is effective in linking electronic medical record data (two studies) with colonoscopic videos to facilitate widespread machine learning. CONCLUSION: AI-assisted IBD endoscopy has the potential to impact clinical management by automated detection and characterization of endoscopic lesions. Large, multi-center, prospective studies and commercially available IBD-specific endoscopic AI algorithms are warranted.