The Effect of Novel AI-based Cecum Recognition System on Adenoma Detection Metrics at Screening Colonoscopy Setting.

BACKGROUND AND AIMS: Cecal intubation of colonoscopy relies on self-reporting. We developed an artificial intelligence-based cecum recognition system (AI-CRS) for post hoc verification of cecal intubation and explored its impact on adenoma metrics. METHODS: Quality metrics, including cecal intubation rate (CIR), adenoma detection rate (ADR), and other ADR-related metrics were compared both before (2015-2018) and after (2019-2022) the implementation of AI-CRS. RESULTS: While CIR did not change significantly after the implementation of AI-CRS, ADR and AADR significantly increased. While ADR significantly increased in all segments, the most significant increase in AADR was observed in the proximal colon. Implementation of AI-CRS was associated with a higher likelihood of detecting adenoma (aOR=1.35, 95%CI=1.26-1.45) and advanced adenoma (aOR=1.23, 95%CI=1.07-1.41), respectively. CONCLUSIONS: Implementation of a post hoc verification of cecal intubation using an AI-CRS significantly improved various adenoma metrics in screening colonoscopy.

Sessile serrated lesion prevalence and factors associated with their detection: a post-hoc analysis of a multinational randomized controlled trial from Asia.

BACKGROUND: Sessile serrated lesions (SSLs) are associated with an increased risk of colorectal cancer. Data on the prevalence of SSLs in Asia are limited. We performed this study to estimate the prevalence of SSLs in Asia and to explore endoscopic factors that are associated with SSL detection. METHODS: This is a post-hoc analysis of a multicenter randomized controlled trial from four Asian countries/regions that compared adenoma detection rates using linked-color imaging (LCI) and white-light imaging. Colonoscopies were performed in an average-risk population for screening, diagnostic examination, or polyp surveillance. Patients with SSLs were compared against those without SSLs to evaluate for possible predictors of SSL detection using Firth's logistic regression. RESULTS: 2898 participants (mean age 64.5 years) were included in the analysis. The estimated prevalence of SSLs was 4.0% (95%CI 3.4%-4.8%), with no sex or age group differences. On multivariable analysis, use of LCI (adjusted odds ratio [aOR] 1.63, 95%CI 1.10-2.41), experienced endoscopists (aOR 1.94, 95%CI 1.25-3.00), use of transparent cap (aOR 1.75, 95%CI 1.09-2.81), and longer withdrawal time (aOR 1.06, 95%CI 1.03-1.10) were independently associated with SSL detection. Synchronous adenoma detection (aOR 1.89, 95%CI 1.20-2.99) was also predictive of SSL detection. CONCLUSION: The prevalence of SSLs in Asia is 4.0%. Use of LCI or a transparent cap, greater endoscopist experience, and longer withdrawal time were all associated with increased SSL detection.

Seven-Day Vonoprazan-Based Triple Therapy as First-Line Helicobacter pylori Treatment in Comparison With Extended Sequential Therapy: A Randomized Controlled Trial.

BACKGROUND: Vonoprazan, a potassium-competitive acid blocker, has demonstrated greater potency and a longer duration of acid suppression when compared to the proton pump inhibitors. However, data regarding the comparison between vonoprazan-based triple therapy with standard treatment for first-line Helicobacter pylori treatment are limited. This study aimed to compare the efficacy between 7-day vonoprazan-based triple therapy with high-dose amoxicillin (VAC-7) and 14-day extended sequential therapy (S-14). MATERIALS AND METHODS: This was a single-center prospective randomized controlled trial following a noninferiority design. Subjects over 20 years old with confirmed H. pylori infection were enrolled prospectively from Fu Jen Catholic University Hospital. They were randomly assigned to the VAC-7 or S-14 group. The primary endpoint was the eradication rate in first-line treatment, evaluated by urea breath test, with noninferiority determined using the Farrington-Manning method. The secondary outcome included adverse effect rates and compliance, assessed through self-administered questionnaires. RESULTS: Between December 2021 and June 2023, a total of 628 patients were recruited. The eradication rates by per-protocol analysis and intention-to-treat analysis were 88.6%/81.8% for VAC-7 and 90.3%/81.4% for S-14, respectively. The VAC-7 was non-inferior to S-14 in terms of ITT analysis. Subjects experienced fewer incidences of nausea, anorexia, dizziness, fatigue, and any severe adverse events in the VAC-7 group. Compliance was higher in the VAC-7 group, with 94% taking all the pills correctly. CONCLUSIONS: Our findings supported the use of 7-day vonoprazan triple therapy with high-dose amoxicillin as the standard first-line treatment for H. pylori infection. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT05371249.

Linked color imaging improves colorectal lesion detection especially for low performance endoscopists: An international trial in Asia.

BACKGROUND AND AIM: Linked color imaging (LCI) is an image-enhanced endoscopy technique that accentuates the color difference between red and white, potentially improving the adenoma detection rate (ADR). However, it remains unclear whether LCI performance in detecting colorectal lesions differs based on endoscopists' experience levels. We aimed to evaluate the differences in LCI efficacy based on the experience levels of endoscopists by conducting an exploratory analysis. METHODS: In this post hoc analysis of an international randomized controlled trial comparing the detection of adenoma and other lesions using colonoscopy with LCI and high-definition white light imaging (WLI), we included patients from 11 institutions across four countries/regions: Japan, Thailand, Taiwan, and Singapore. We retrospectively reviewed differences in the lesion detection of LCI according to endoscopists' colonoscopy history or ADR. RESULTS: We included 1692 and 1138 patients who underwent colonoscopies performed by 54 experts (experience of ≥ 5000 colonoscopies) and by 43 non-experts (experience of < 5000 colonoscopies), respectively. Both expert and non-expert groups showed a significant improvement in ADR with LCI compared to WLI (expert, 61.7% vs 46.4%; P < 0.001; non-expert, 56.6% vs 46.4%; P < 0.001). LCI had no effect on sessile serrated lesion detection rate in non-experts (3.1% vs 2.5%; P = 0.518). LCI significantly improved detection rates in endoscopists with relatively low detection performance, defined as an ADR < 50%. CONCLUSIONS: This exploratory study analyzed data from a previous trial and revealed that LCI is useful for both experts and non-experts and is even more beneficial for endoscopists with relatively low detection performance using WLI.

Analysis of the Characteristics of Coexisting Lesions in Colorectal Cancer Patients in an International Study: A Subgroup Analysis of the ATLAS Trial.

INTRODUCTION: We investigated coexisting lesion types in patients with invasive colorectal cancer (CRC) in a multinational study for comprehending the adenoma-carcinoma and serrated pathway about the development of CRC. METHODS: We retrospectively reviewed 3,050 patients enrolled in the international randomized controlled trial (ATLAS study) to evaluate the colorectal polyp detection performance of image-enhanced endoscopy in 11 institutions in four Asian countries/regions. In the current study, as a subgroup analysis of the ATLAS study, 92 CRC patients were extracted and compared to 2,958 patients without CRC to examine the effects of age, sex, and coexisting lesion types (high-grade adenoma [HGA], low-grade adenoma with villous component [LGAV], 10 adenomas, adenoma ≥10 mm, sessile serrated lesions [SSLs], and SSLs with dysplasia [SSLD]). Additional analyses of coexisting lesion types were performed according to sex and location of CRC (right- or left-sided). RESULTS: A multivariate analysis showed that HGA (odds ratio [95% confidence interval] 4.29 [2.16-8.18]; p < 0.01), LGAV (3.02 [1.16-7.83], p = 0.02), and age (1.04 [1.01-1.06], p = 0.01) were independently associated with CRC. According to sex, the coexisting lesion types significantly associated with CRC were LGAV (5.58 [1.94-16.0], p < 0.01) and HGA (4.46 [1.95-10.20], p < 0.01) in males and HGA (4.82 [1.47-15.80], p < 0.01) in females. Regarding the location of CRC, SSLD (21.9 [1.31-365.0], p = 0.03) was significant for right-sided CRC, and HGA (5.22 [2.39-11.4], p < 0.01) and LGAV (3.46 [1.13-10.6], p = 0.02) were significant for left-sided CRC. CONCLUSIONS: The significant coexisting lesions in CRC differed according to sex and location. These findings may contribute to comprehending the pathogenesis of CRC.

Linked-Color Imaging Detects More Colorectal Adenoma and Serrated Lesions: An International Randomized Controlled Trial.

BACKGROUND & AIMS: 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. METHODS: 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. RESULTS: 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 advanced ADR was not significantly different (13.2% vs 11.0%; P = .06). Significantly more patients in the LCI group had shorter recommended surveillance schedules than the WLI group (P < .01). CONCLUSIONS: 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. TRIAL REGISTRATION NUMBER: UMIN000042432 (https://www.umin.ac.jp/ctr/index.htm).

Implementing precision medicine in endoscopy practice.

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.

Application of artificial intelligence in gastroenterology: Potential role in clinical 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.

Seven-day vonoprazan-based triple therapy as first-lineHelicobacter pylori treatment in comparison with extended sequential therapy.

Background and Aim: Vonoprazan as a new acid blocker has more potency and longer lasting acid suppression than proton pump inhibitors. Whether the efficacy of vonoprazan-based triple therapy is comparable with or even better than that of currently recommended first-line therapies is still unknown. Our study aims to compare the eradication rate and major adverse effects between 7-day vonoprazan-based triple therapy with high-dose amoxicillin and 14-day extended sequential therapy. Methods: We performed a retrospective analysis from the database of 13C-urea breath test at Fu Jen Catholic University Hospital. All patients with a definite diagnosis of Helicobacter pylori infection by rapid urease test, urea breath test, stool antigen test, or pathology report were recruited. Patients receiving first-line regimens with vonoprazan-based triple therapy or extended sequential therapy were included. The respective eradication rate determined by 13C-urea breath test and major adverse effects were demonstrated. Results: Totally, 106 patients were recruited in the vonoprazan-based triple therapy group and 357 in the extended sequential therapy group. There was no significant difference in eradication rate between vonoprazan-based triple therapy with high-dose amoxicillin and extended sequential therapy (83.0 vs 88.8%, P = 0.12). Major adverse effects occurred in 13 of the extended sequential therapy group but none in the other group (0% vs 3.6%, P = 0.046). Conclusions: Seven-day vonoprazan-based triple therapy with high-dose amoxicillin is a potential first-line anti-Helicobacter pylori regimen alternative to current standard treatment, with the advantages of simplicity, short treatment duration, low pill burden, and fewer major adverse effects.

Dedicated staff for patient education improves bowel preparation quality and reduces the cecal intubation time of colonoscopy: A single institution retrospective study.

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.