Capsule endoscopy is ideally suited to artificial intelligencebased interpretation given its reliance on pattern recognition in still images. Time saving viewing modes and lesion detection features currently available rely on machine learning algorithms, a form of artificial intelligence. Current software necessitates close human supervision given poor sensitivity relative to an expert reader. However, with the advent of deep learning, artificial intelligence is becoming increasingly reliable and will be increasingly relied upon. We review the major advances in artificial intelligence for capsule endoscopy in recent publications and briefly review artificial intelligence development for historical understanding. Importantly, recent advancements in artificial intelligence have not yet been incorporated into practice and it is immature to judge the potential of this technology based on current platforms. Remaining regulatory and standardization hurdles are being overcome and artificial intelligence-based clinical applications are likely to proliferate rapidly.
Background
Nonpharmacologic factors, including patient education, affect bowel preparation for colonoscopy. Optimal cleansing increases quality and reduces repeat procedures. This study prospectively analyzes use of an individualized online patient education module in place of traditional patient education.
Aims
To determine the effectiveness of online education for patients, measured by the proportion achieving sufficient bowel preparation. Secondary measures include assessment of patient satisfaction.
Methods
Prospective, single-center, observational study. Adults aged 19 years and over, with an e-mail account, scheduled for nonurgent colonoscopy, with English proficiency (or someone who could translate for them) were recruited. Demographics and objective bowel preparation quality were collected. Patient satisfaction was assessed via survey to assess clarity and usefulness of the module.
Results
Nine hundred consecutive patients completed the study. 84.6% of patients achieved adequate bowel preparation as measured by Boston bowel preparation score ≥ 6 and 90.1% scored adequately using Ottawa bowel preparation score ≤7. 94.2% and 92.1% of patients rated the web-education module as ‘very useful’ and ‘very clear’, respectively (≥8/10 on respective scales).
Conclusions
Our analysis suggests that internet-based patient education prior to colonoscopy is a viable option and achieves adequate bowel preparation. Preparation quality is comparable to previously published trials. Included patients found the process clear and useful. Pragmatic benefits of a web-based protocol such as time and cost savings were not formally assessed but may contribute to greater satisfaction for endoscopists and patients.
Non-Alcoholic fatty liver disease (NAFLD) is common with widely ranging severity. Non-invasive risk scores for risk stratification are recommended but misclassify a significant proportion of patients. In situations where non-invasive risk scores do not provide guidance, referral is typically made to a Hepatologist for transient elastography or liver biopsy. Serum ferritin is elevated in many patients with NAFLD related to dysmetabolic and inflammatory hyperferritinemia. Ferritin is widely available and part of a standard workup for chronic liver disease. Methods: To explore the association of ferritin and risk of fibrosis in NAFLD, we reviewed patients diagnosed with NAFLD at the hepatology clinic of the Vancouver General Hospital between the years of 2015–2018. We collected data on 317 patients retrospectively assessing for a relationship between serum ferritin and elastography score. Results: 224 patients were included in the final analysis. Median ferritin was 145 µg/L (IQR 249). Median liver stiffness was 5.2 kPa with 14.3% of patients having liver stiffness ≥8.7 kPa and 17.4% ≥ 8.0 kPa. ROC curve analysis using a liver stiffness ≥8.0kPa as a cutoff for F2 fibrosis showed an AUROC of 0.54 for serum ferritin levels. At a cut-off of both 300 µg/L and 450 µg/L median liver stiffness did not differ significantly in those with ferritin above the cutoff (ferritin ≥300 µg/L p = 0.099, ferritin ≥450 µg/L p = 0.12). Ferritin was significantly higher in male patients (198 µg/L vs 91 µg/L p = 0.0001). There was a weak linear association between AST and ferritin levels. Conclusion: In this cohort of 224 patients with NAFLD, serum ferritin was not predictive of significant liver fibrosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.