Risk Perception, Acceptance, and Trust of Using AI in Gastroenterology Practice in the Asia-Pacific Region: Web-Based Survey Study.

BACKGROUND: The use of artificial intelligence (AI) can revolutionize health care, but this raises risk concerns. It is therefore crucial to understand how clinicians trust and accept AI technology. Gastroenterology, by its nature of being an image-based and intervention-heavy specialty, is an area where AI-assisted diagnosis and management can be applied extensively. OBJECTIVE: This study aimed to study how gastroenterologists or gastrointestinal surgeons accept and trust the use of AI in computer-aided detection (CADe), computer-aided characterization (CADx), and computer-aided intervention (CADi) of colorectal polyps in colonoscopy. METHODS: We conducted a web-based questionnaire from November 2022 to January 2023, involving 5 countries or areas in the Asia-Pacific region. The questionnaire included variables such as background and demography of users; intention to use AI, perceived risk; acceptance; and trust in AI-assisted detection, characterization, and intervention. We presented participants with 3 AI scenarios related to colonoscopy and the management of colorectal polyps. These scenarios reflect existing AI applications in colonoscopy, namely the detection of polyps (CADe), characterization of polyps (CADx), and AI-assisted polypectomy (CADi). RESULTS: In total, 165 gastroenterologists and gastrointestinal surgeons responded to a web-based survey using the structured questionnaire designed by experts in medical communications. Participants had a mean age of 44 (SD 9.65) years, were mostly male (n=116, 70.3%), and mostly worked in publicly funded hospitals (n=110, 66.67%). Participants reported relatively high exposure to AI, with 111 (67.27%) reporting having used AI for clinical diagnosis or treatment of digestive diseases. Gastroenterologists are highly interested to use AI in diagnosis but show different levels of reservations in risk prediction and acceptance of AI. Most participants (n=112, 72.72%) also expressed interest to use AI in their future practice. CADe was accepted by 83.03% (n=137) of respondents, CADx was accepted by 78.79% (n=130), and CADi was accepted by 72.12% (n=119). CADe and CADx were trusted by 85.45% (n=141) of respondents and CADi was trusted by 72.12% (n=119). There were no application-specific differences in risk perceptions, but more experienced clinicians gave lesser risk ratings. CONCLUSIONS: Gastroenterologists reported overall high acceptance and trust levels of using AI-assisted colonoscopy in the management of colorectal polyps. However, this level of trust depends on the application scenario. Moreover, the relationship among risk perception, acceptance, and trust in using AI in gastroenterology practice is not straightforward.

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.

Healthcare in the era of climate change and the need for environmental sustainability.

ABSTRACT: Climate change is an existential threat to humanity. While the healthcare sector must manage the health-related consequences of climate change, it is a significant contributor to greenhouse gas emissions, responsible for up to 4.6% of global emission, aggravating global warming. Within the hospital environment, the three largest contributors to greenhouse gas emissions are the operating theatre, intensive care unit and gastrointestinal endoscopy. Knowledge of the health-related burden of climate change and the potential transformative health benefits of climate action is important to all health professionals, as they play crucial roles in effecting change. This article summarises the available literature on the impact of healthcare on climate change and efforts in mitigation, focusing on the intrinsic differences and similarities across the operating theatre complex, intensive care unit and gastrointestinal endoscopy unit. It also discusses strategies to reduce carbon footprint.

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.

Development and validation of a deep learning system for detection of small bowel pathologies in capsule endoscopy: a pilot study in a Singapore institution.

INTRODUCTION: Deep learning models can assess the quality of images and discriminate among abnormalities in small bowel capsule endoscopy (CE), reducing fatigue and the time needed for diagnosis. They serve as a decision support system, partially automating the diagnosis process by providing probability predictions for abnormalities. METHODS: We demonstrated the use of deep learning models in CE image analysis, specifically by piloting a bowel preparation model (BPM) and an abnormality detection model (ADM) to determine frame-level view quality and the presence of abnormal findings, respectively. We used convolutional neural network-based models pretrained on large-scale open-domain data to extract spatial features of CE images that were then used in a dense feed-forward neural network classifier. We then combined the open-source Kvasir-Capsule dataset (n = 43) and locally collected CE data (n = 29). RESULTS: Model performance was compared using averaged five-fold and two-fold cross-validation for BPMs and ADMs, respectively. The best BPM model based on a pre-trained ResNet50 architecture had an area under the receiver operating characteristic and precision-recall curves of 0.969±0.008 and 0.843±0.041, respectively. The best ADM model, also based on ResNet50, had top-1 and top-2 accuracies of 84.03±0.051 and 94.78±0.028, respectively. The models could process approximately 200-250 images per second and showed good discrimination on time-critical abnormalities such as bleeding. CONCLUSION: Our pilot models showed the potential to improve time to diagnosis in CE workflows. To our knowledge, our approach is unique to the Singapore context. The value of our work can be further evaluated in a pragmatic manner that is sensitive to existing clinician workflow and resource constraints.

CEACAM5 and TROP2 define metaplastic and dysplastic transitions in human antral gastric precancerous lesions and tumors.

BACKGROUND: Mucosal gastric atrophy and intestinal metaplasia (IM) increase the risk for the development of gastric cancer (GC) as they represent a field for development of dysplasia and intestinal-type gastric adenocarcinoma. METHODS: We have investigated the expression of two dysplasia markers, CEACAM5 and TROP2, in human antral IM and gastric tumors to assess their potential as molecular markers. RESULTS: In the normal antral mucosa, weak CEACAM5 and TROP2 expression was only observed in the foveolar epithelium, while inflamed antrum exhibited increased expression of both markers. Complete IM exhibited weak CEACAM5 expression at the apical surface, but no basolateral TROP2 expression. On the other hand, incomplete IM demonstrated high levels of both CEACAM5 and TROP2 expression. Notably, incomplete IM with dysplastic morphology (dysplastic incomplete IM) exhibited higher levels of CEACAM5 and TROP2 expression compared to incomplete IM without dysplastic features (simple incomplete IM). In addition, dysplastic incomplete IM showed diminished SOX2 and elevated CDX2 expression compared to simple incomplete IM. CEACAM5 and TROP2 positivity in incomplete IM was similar to that of gastric adenomas and GC. Significant association was found between CEACAM5 and TROP2 positivity and histology of GC. CONCLUSIONS: These findings support the concept that incomplete IM is more likely associated with GC development. Overall, our study provides evidence of the heterogeneity of gastric IM and the distinct expression profiles of CEACAM5 and TROP2 in dysplastic incomplete IM. Our findings support the potential use of CEACAM5 and TROP2 as molecular markers for identifying individuals with a higher risk of GC development in the context of incomplete IM.

Use of artificial intelligence in the management of T1 colorectal cancer: a new tool in the arsenal or is deep learning out of its depth?

The field of artificial intelligence is rapidly evolving, and there has been an interest in its use to predict the risk of lymph node metastasis in T1 colorectal cancer. Accurately predicting lymph node invasion may result in fewer patients undergoing unnecessary surgeries; conversely, inadequate assessments will result in suboptimal oncological outcomes. This narrative review aims to summarize the current literature on deep learning for predicting the probability of lymph node metastasis in T1 colorectal cancer, highlighting areas of potential application and barriers that may limit its generalizability and clinical utility.

Partially covered versus uncovered pyloro-duodenal stents for unresectable malignant gastric outlet obstruction: Randomized controlled study.

OBJECTIVES: The aim of the current study was to compare the efficacy of partially covered duodenal stent (PCDS) vs. uncovered duodenal stent (UCDS) in patients suffering from unresectable primary malignant gastric outlet obstruction (GOO). METHODS: This was a prospective international randomized controlled study conducted in 10 high-volume institutions. Consecutive patients suffering from malignant GOO were recruited. The primary outcome measurement was the reintervention rate. Secondary outcomes included technical and clinical success, 30-day adverse events, 30-day mortality, causes of stent dysfunction, and the duration of stent patency. RESULTS: Between March 2017 and October 2020, 115 patients (59 PCDS, 56 UCDS) were recruited. The 1-year reintervention was not significantly different (PCDS vs. UDCS = 12/59, 20.3% vs. 14/56, 25%, P = 0.84). There was a trend to fewer patients with tumor ingrowth in the PCDS group (6/59 [10.2%]) vs. 13/56 [23.2%], P = 0.07). There were no significant differences in the technical success (100% vs. 100%, P = 1), clinical success (91.5% vs. 98.2%, P = 0.21), procedural time (21.5 [interquartile range [IQR] 17-30] vs. 20.0 [IQR 15-34.75], P = 0.62), hospital stay (4 [IQR 3-12] vs. 5 [IQR 3-8] days, P = 0.81), 30-day adverse events (18.6% vs. 14.3%, P = 0.62), or 30-day mortality (6.8% vs. 5.2%, P = 1.00). CONCLUSION: The use of PCDS was associated with a lower risk of tumor ingrowth but did not improve on reintervention rates or stent patency. Both kinds of stents could be used in this group of patients.

Current Status of Diagnosis and Treatment of Colorectal Cancer in Asian Countries: A Questionnaire Survey.

INTRODUCTION: Diagnostic and therapeutic methods for colorectal cancer (CRC) have advanced; however, they may be inaccessible worldwide, and their widespread use is challenging. This questionnaire survey investigates the current status of diagnosis and treatment of early-stage CRC in Asian countries. METHODS: Responses to the questionnaire were obtained from 213 doctors at different institutions in 8 countries and regions. The questionnaire consisted of 39 questions on the following four topics: noninvasive diagnosis other than endoscopy (6 questions), diagnosis by magnification and image-enhanced endoscopy (IEE) including artificial intelligence (AI) (10 questions), endoscopic submucosal dissection (ESD), proper use among other therapeutic methods (11 questions), and pathologic diagnosis and surveillance (12 questions). RESULTS: Although 101 of 213 respondents were affiliated with academic hospitals, there were disparities among countries and regions in the dissemination of advanced technologies, such as IEE, AI, and ESD. The NICE classification is widely used for the diagnosis of colorectal tumors using IEE, while the JNET classification with magnification was used in countries such as Japan (65/70, 92.9%) and China (16/22, 72.7%). Of the 211 respondents, 208 (98.6%) assumed that en bloc resection should be achieved for carcinomas, and 180 of 212 (84.9%) believed that ESD was the most suitable in cases with a diameter larger than 2 cm. However, colorectal ESD is not widespread in countries such as Thailand, the Philippines, and Indonesia. CONCLUSION: The promotion of advanced technologies and education should be continual to enable more people to benefit from them.

Asia-Pacific survey on green endoscopy.

BACKGROUND AND AIM: Greenhouse gas emissions are the fundamental cause of global warming, with CO2 being the most contributive. Carbon reduction has been widely advocated to mitigate the climate crisis. The endoscopy unit is the third highest waste-generating department in a hospital. The awareness and acceptance of the practice of green endoscopy among healthcare workers is unclear. METHOD: An online survey was conducted over a 5-week period from July to August 2023 in the Asia-Pacific region, which targeted endoscopists, nurses, and other healthcare professionals of the endoscopy unit. The primary outcome was the agreement to adopt green endoscopy. The secondary outcomes included views on sustainable practices, factors associated with increased acceptance of green endoscopy, the acceptance of different carbon reduction measures, and the perceived barriers to implementation. RESULTS: A total of 259 valid responses were received. Overall, 79.5% of participants agreed to incorporate green endoscopy into their practice. Nevertheless, existing green policies were only reported by 12.7% of respondents. The level of understanding of green endoscopy is the only significant factor associated with its acceptance (odds ratio 3.10, P < 0.007). Potential barriers to implementation include healthcare cost increment, infection risk, inadequate awareness, and lack of policy and industrial support. CONCLUSION: Green endoscopy is well accepted among healthcare workers but not widely implemented. The level of understanding is highly associated with its acceptance, highlighting the importance of education. A reliable assessment tool is needed to quantify the environmental impact of endoscopy. Further studies are needed to ascertain its benefit and cost effectiveness.

Spatiotemporal genomic profiling of intestinal metaplasia reveals clonal dynamics of gastric cancer progression.

Intestinal metaplasia (IM) is a pre-malignant condition of the gastric mucosa associated with increased gastric cancer (GC) risk. Analyzing 1,256 gastric samples (1,152 IMs) across 692 subjects from a prospective 10-year study, we identify 26 IM driver genes in diverse pathways including chromatin regulation (ARID1A) and intestinal homeostasis (SOX9). Single-cell and spatial profiles highlight changes in tissue ecology and IM lineage heterogeneity, including an intestinal stem-cell dominant cellular compartment linked to early malignancy. Expanded transcriptome profiling reveals expression-based molecular subtypes of IM associated with incomplete histology, antral/intestinal cell types, ARID1A mutations, inflammation, and microbial communities normally associated with the healthy oral tract. We demonstrate that combined clinical-genomic models outperform clinical-only models in predicting IMs likely to transform to GC. By highlighting strategies for accurately identifying IM patients at high GC risk and a role for microbial dysbiosis in IM progression, our results raise opportunities for GC precision prevention and interception.

Cronkhite-Canada Syndrome Masquerading as Inflammatory Bowel Disease.

Cronkhite-Canada syndrome (CCS) is a rare nonhereditary gastrointestinal polyposis syndrome. We illustrate a case with clinical presentation of dysgeusia, chronic diarrhea and weight loss, and endoscopic features of diffuse gastric mucosa nodularity with circumferential nodular pancolitis and a solitary colonic polyp initially mimicking inflammatory bowel disease. After multidisciplinary discussion, the diagnosis of CCS was made. The patient received steroids with resultant clinical, endoscopic, and histological improvement. We discuss the treatment and risk of neoplasia in CCS.