Search

Adequate bowel preparation is an essential part of a high-quality colonoscopy. Recent studies showed that the small-volume bowel cleansing agent Bowklean performs better in terms of tolerability and acceptability. However, its split-dose regimen is sometimes confusing to the patient. To promote Bowklean in Fu Jen Catholic University Hospital, dedicated staff for patient education on bowel preparation were provided by Universal Integrated Corporation (Taiwan), but not in every period because of the clinic room availability and manpower capacity. This provided us an opportunity to compare the quality of colonoscopy between those with and without the dedicated patient education. This study aimed to compare various quality indices between the two groups. We set bowel preparation quality as the primary endpoint, assessed by modified Aronchick scale, and other quality indices including procedure time and adenoma detection rate as the secondary endpoints. We performed a single institution retrospective study. All patients who received colonoscopy from an outpatient setting with Bowklean as the bowel cleansing agent from October 2020 to November 2020 were reviewed. Primary and secondary endpoints were then compared between the conventional group and the dedicated staff group, with StataSE 14 by Wilcoxon rank sum test or logistic regression. Four hundred ten patients were recruited, including 217 patients with dedicated patient education and 193 without. The proportion of bowel preparation quality "Excellent + Good + Fair" was significantly higher in dedicated staff group than conventional group (97.7% vs 93.3%, P = .03; logistic regression coefficient = 1.12). The cecal intubation time was significantly shorter in the dedicated staff group (3.68 ± 2.02 minutes vs 4.52 ± 3.25 minutes, P.01). After excluding those with polypectomy or biopsy, the total procedure time tended to be shorter in the dedicated staff group (10.2 ± 3.35 minutes vs 9.40 ± 2.43 minutes, P = .06). There was no significant difference regarding adenoma detection rate between the two groups. Our study shows that patient education by dedicated staff can improve bowel preparation quality and has the potential to decrease procedure time. Further large-scale prospective trials are still needed to evaluate if it can also achieve a better adenoma detection rate.

Effects of linked-color imaging (LCI) on colorectal lesion detection and colonoscopy quality remain controversial. This study compared the detection rates of adenoma and other precursor lesions using LCI vs white-light imaging (WLI) during screening, diagnostic, and surveillance colonoscopies.This randomized controlled trial was performed at 11 institutions in 4 Asian countries/regions. Patients with abdominal symptoms, a primary screening colonoscopy, positive fecal immunochemical test results, or undergoing postpolypectomy surveillance were recruited and randomly assigned in a 1:1 ratio to either the LCI or high-definition WLI group. The primary outcome was adenoma detection rate (ADR). Secondary outcomes were polyp detection rate, advanced ADR, sessile serrated lesion (SSL) detection rate, and the mean number of adenomas per colonoscopy. The recommended surveillance schedule distribution after trial colonoscopy was analyzed.Between November 2020 and January 2022, there were 3050 participants (LCI, n = 1527; WLI, n = 1523) recruited. The LCI group ADR was significantly higher than the WLI group ADR using intention-to-treat (58.7% vs 46.7%; P.01) and per-protocol analyses (59.6% vs 46.4%; P.01). The LCI group polyp detection rates (68.6% vs 59.5%; P.01), SSL detection rates (4.8% vs 2.8%; P.01), and adenomas per colonoscopy (1.48 vs 1.02; P.01) also were significantly higher. However, the LCI group advanced ADR was nonsignificantly higher (13.2% vs 11.0%; P = .06). The LCI group was categorized in significantly shorter recommended surveillance schedules than the WLI group (P.01).Compared with WLI, LCI improved adenoma and other polyp detection rates, including SSLs, resulting in alteration of the recommended surveillance schedule after screening, diagnostic, and postpolypectomy surveillance colonoscopies.UMIN000042432 (https://www.umin.ac.jp/ctr/index.htm).

In contrast to the "one-size-fits-all" approach, precision medicine focuses on providing health care tailored to individual variabilities. Implementing precision medicine in endoscopy practice involves selecting the appropriate procedures among the endoscopic armamentarium in the diagnosis and management of patients in a logical sequence, jointly considering the pretest probabilities of possible diagnoses, patients' comorbidities and preference, and risk-benefit ratio of the individual procedures given the clinical scenario. The aim of this review is to summarize evidence-supported strategies and measures that may enhance precision medicine in general endoscopy practice.

Artificial intelligence (AI) based on deep learning boosted medical research in the past years and is expected to enormously change the style of health care in many aspects in the foreseeable future. Nowadays, there are exploding volumes of healthcare-related data being generated daily. Because of its time-sensitive characteristics, being able to process large amounts of data in real-time fashion is crucial in healthcare settings. In gastroenterology practice, AI can manage and interpret the sheer amount of data with different formats coming from a myriad of sources, including currently used endoscopic or imaging devices, digital record systems, and electronic health records, or from other sources such as governmental databases, social media, or wearable devices over a long period. Traditional gastroenterology is nowadays beginning to transform to a new personalized, predictive, and preventive paradigm. Evidence-based practices and recent studies are coming out every day, and big data-based approaches and the progress in basic sciences and its emerging applications are now becoming the indispensable part of precision medicine. In gastroenterology, AI can be applied in disease diagnosis, treatment guidance, outcome prediction, and reducing workload of the healthcare staff. As the healthcare community begins to embrace AI technology, how to seamlessly construct an interoperable platform to accommodate data with high variety and veracity with high velocity and implement AI in the clinical workflow would be the future challenges.