Magnetic resonance elastography (MRE) outperforms acoustic force radiation impulse (ARFI) in predicting oesophageal varices in obese NAFLD cirrhosis.

PURPOSE: Liver stiffness measurement (LSM) by transient elastography has been shown to underperform in high-risk varices (HRVs) prediction in obese non-alcoholic fatty liver disease (NAFLD) compensated cirrhosis (CC). LSM by magnetic resonance elastography (MRE) and acoustic force radiation impulse (ARFI) has been shown to be useful in prediction of oesophageal varices (EVs), but has limited evidence in obese NAFLD-CC. METHODS: Obese patients with NAFLD-CC who underwent MRE and ARFI for LSM and endoscopy for screening of varices were enrolled. Performance of MRE and ARFI for predicting EVs or HRVs was evaluated using area under receiver operating characteristics (AUROC) curves and regression analyses were performed for predictor variables. RESULTS: One hundred eight patients [mean age 54.7 ± 9.6 years, median BMI, 28.5 (26.4-30.0) kg/m2. 72.2% diabetics, 45.4% hypertensive] were enrolled. Fifty-two (48.1%) had no varices, while 29 (26.8%) and 27 (25%) had low-risk varices (LRVs) and HRVs, respectively. MRE-LSM was higher in patients with LRVs (p = 0.01) or HRVs (p = 0.001) against those without varices. ARFI-LSM did not differ significantly between those without and with LRVs or HRVs (p > 0.05 for all). There was a low correlation between ARFI-LSM and MRE-LSM in the overall cohort (r = 0.19). Only platelet count (PC) [0.98 (0.97-0.99)] and MRE-LSM [1.8 (1.26-2.79)] were predictors of HRVs. At a cut-off of 4.75, MRE showed a sensitivity of 96.3%. Model combining MRE-LSM with PC had a diagnostic AUROC of 0.77 and 0.76 for EVs and HRVs. CONCLUSION: In obese NAFLD-CC, MRE-LSM is significantly higher in patients with varices. MRE combined with PC predicts EVs and HRVs with better accuracy than ARFI.

Role of artificial intelligence-guided esophagogastroduodenoscopy in assessing the procedural completeness and quality.

BACKGROUND AND AIMS: The quality of esophagogastroduodenoscopy (EGD) can have great impact on the detection of esophageal and gastric lesions, including malignancies. The aim of the study is to investigate the use of artificial intelligence (AI) during EGD by the  endoscopists-in-training so that a real-time feedback can be provided, ensuring compliance to a pre-decided protocol for examination. METHODS: This is an observational pilot study. The videos of the EGD procedure performed between August 1, 2021, and September 30, 2021, were prospectively analyzed using AI system. The assessment of completeness of the procedure was done based on the visualizsation of pre-defined 29 locations. Endoscopists were divided into two categories - whether they are in the training period (category A) or have competed their endoscopy training (category B). RESULTS: A total of 277 procedures, which included 114 category-A and 163 category-B endoscopists, respectively, were included. Most commonly covered areas by the endoscopists were greater curvature of antrum (97.47%), second part of duodenum (96.75%), other parts of antrum such as the anterior, lesser curvature and the posterior aspect (96.75%, 94.95%, and 94.22%, respectively). Commonly missed or inadequately seen areas were vocal cords (99.28%), epiglottis (93.14%) and posterior, anterior, and lateral aspect of incisura (78.70%, 73.65%, and 73.53%, respectively). The good quality procedures were done predominantly by categoryB endoscopists (88.68% vs. 11.32%, p < 0.00001). CONCLUSION: AI can play an important role in assessing the quality and completeness of EGD and can be a part of training of endoscopy in future.