International Digestive Endoscopy Network consensus on the management of antithrombotic agents in patients undergoing gastrointestinal endoscopy.

Antithrombotic agents, including antiplatelet agents and anticoagulants, are widely used in Korea because of the increasing incidence of cardiocerebrovascular disease and the aging population. The management of patients using antithrombotic agents during endoscopic procedures is an important clinical challenge. The clinical practice guidelines for this issue, developed by the Korean Society of Gastrointestinal Endoscopy, were published in 2020. However, new evidence on the use of dual antiplatelet therapy and direct anticoagulant management has emerged, and revised guidelines have been issued in the United States and Europe. Accordingly, the previous guidelines were revised. Cardiologists were part of the group that developed the guideline, and the recommendations went through a consensus-reaching process among international experts. This guideline presents 14 recommendations made based on the Grading of Recommendations, Assessment, Development, and Evaluation methodology and was reviewed by multidisciplinary experts. These guidelines provide useful information that can assist endoscopists in the management of patients receiving antithrombotic agents who require diagnostic and elective therapeutic endoscopy. It will be revised as necessary to cover changes in technology, evidence, or other aspects of clinical practice.

Computer-aided diagnosis in real-time endoscopy for all stages of gastric carcinogenesis: Development and validation study.

OBJECTIVE: Using endoscopic images, we have previously developed computer-aided diagnosis models to predict the histopathology of gastric neoplasms. However, no model that categorizes every stage of gastric carcinogenesis has been published. In this study, a deep-learning-based diagnosis model was developed and validated to automatically classify all stages of gastric carcinogenesis, including atrophy and intestinal metaplasia, in endoscopy images. DESIGN: A total of 18,701 endoscopic images were collected retrospectively and randomly divided into train, validation, and internal-test datasets in an 8:1:1 ratio. The primary outcome was lesion-classification accuracy in six categories: normal/atrophy/intestinal metaplasia/dysplasia/early /advanced gastric cancer. External-validation of performance in the established model used 1427 novel images from other institutions that were not used in training, validation, or internal-tests. RESULTS: The internal-test lesion-classification accuracy was 91.2% (95% confidence interval: 89.9%-92.5%). For performance validation, the established model achieved an accuracy of 82.3% (80.3%-84.3%). The external-test per-class receiver operating characteristic in the diagnosis of atrophy and intestinal metaplasia was 93.4 ± 0% and 91.3 ± 0%, respectively. CONCLUSIONS: The established model demonstrated high performance in the diagnosis of preneoplastic lesions (atrophy and intestinal metaplasia) as well as gastric neoplasms.

Antibiotic Resistance of Helicobacter pylori: Mechanisms and Clinical Implications.

Helicobacter pylori is a pathogenic bacterium associated with various gastrointestinal diseases, including chronic gastritis, peptic ulcers, mucosa-associated lymphoid tissue lymphoma, and gastric cancer. The increasing rates of H. pylori antibiotic resistance and the emergence of multidrug-resistant strains pose significant challenges to its treatment. This comprehensive review explores the mechanisms underlying the resistance of H. pylori to commonly used antibiotics and the clinical implications of antibiotic resistance. Additionally, potential strategies for overcoming antibiotic resistance are discussed. These approaches aim to improve the treatment outcomes of H. pylori infections while minimizing the development of antibiotic resistance. The continuous evolution of treatment perspectives and ongoing research in this field are crucial for effectively combating this challenging infection.

Characteristics of microbiome-derived metabolomics according to the progression of alcoholic liver disease.

BACKGROUND AND AIM: The prevalence and severity of alcoholic liver disease (ALD) are increasing. The incidence of alcohol-related cirrhosis has risen up to 2.5%. This study aimed to identify novel metabolite mechanisms involved in the development of ALD in patients. The use of gut microbiome-derived metabolites is increasing in targeted therapies. Identifying metabolic compounds is challenging due to the complex patterns that have long-term effects on ALD. We investigated the specific metabolite signatures in ALD patients. METHODS: This study included 247 patients (heathy control, HC: n = 62, alcoholic fatty liver, AFL; n = 25, alcoholic hepatitis, AH; n = 80, and alcoholic cirrhosis, AC, n = 80) identified, and stool samples were collected. 16S rRNA sequencing and metabolomics were performed with MiSeq sequencer and liquid chromatography coupled to time-of-flight-mass spectrometry (LC-TOF-MS), respectively. The untargeted metabolites in AFL, AH, and AC samples were evaluated by multivariate statistical analysis and metabolic pathotypic expression. Metabolic network classifiers were used to predict the pathway expression of the AFL, AH, and AC stages. RESULTS: The relative abundance of Proteobacteria was increased and the abundance of Bacteroides was decreased in ALD samples (p = 0.001) compared with that in HC samples. Fusobacteria levels were higher in AH samples (p = 0.0001) than in HC samples. Untargeted metabolomics was applied to quantitatively screen 103 metabolites from each stool sample. Indole-3-propionic acid levels are significantly lower in AH and AC (vs. HC, p = 0.001). Indole-3-lactic acid (ILA: p = 0.04) levels were increased in AC samples. AC group showed an increase in indole-3-lactic acid (vs. HC, p = 0.040) level. Compared with that in HC samples, the levels of short-chain fatty acids (SCFAs: acetic acid, butyric acid, propionic acid, iso-butyric acid, and iso-valeric acid) and bile acids (lithocholic acids) were significantly decreased in AC. The pathways of linoleic acid metabolism, indole compounds, histidine metabolism, fatty acid degradation, and glutamate metabolism were closely associated with ALD metabolism. CONCLUSIONS: This study identified that microbial metabolic dysbiosis is associated with ALD-related metabolic dysfunction. The SCFAs, bile acids, and indole compounds were depleted during ALD progression. CLINICAL TRIAL: Clinicaltrials.gov, number NCT04339725.

Changing trends and characteristics of peptic ulcer disease: A multicenter study from 2010 to 2019 in Korea.

BACKGROUND: The clinical trend and characteristics of peptic ulcer disease (PUD) have not fully been investigated in the past decade. AIM: To evaluate the changing trends and characteristics of PUD according to age and etiology. METHODS: We analyzed seven hospital databases converted into the Observational Medical Outcomes Partnership-Common Data Model between 2010 and 2019. We classified patients with PUD who underwent rapid urease tests or Helicobacter pylori (H. pylori) serology into three groups: H. pylori-related, drug [nonsteroidal anti-inflammatory drugs (NSAIDs) or aspirin]-related, and idiopathic (H. pylori/NSAID/aspirin-negative) PUD and compared the yearly trends and characteristics among the three groups. RESULTS: We included 26785 patients in 7 databases, and the proportion of old age (≥ 65 years) was 38.8%. The overall number of PUD exhibited no decrease, whereas PUD in old age revealed an increasing trend (P = 0.01 for trend). Of the 19601 patients, 41.8% had H. pylori-related, 36.1% had drug-related, and 22.1% had idiopathic PUD. H. pylori-related PUD exhibited a decreasing trend after 2014 (P = 0.01), drug-related PUD demonstrated an increasing trend (P = 0.04), and idiopathic PUD showed an increasing trend in the old-age group (P = 0.01) during 10 years. Patients with drug-related PUD had significantly more comorbidities and concomitant ulcerogenic drugs. The idiopathic PUD group had a significantly higher number of patients with chronic liver disease. CONCLUSION: With the aging population increase, the effects of concomitant ulcerogenic drugs and preventive strategies should be investigated in drug-induced PUD. Further studies are required to clarify the relationship between idiopathic PUD and chronic liver disease.

Efficacy comparison of 7- and 14-day P-CAB based bismuth-containing quadruple regimen with PPI based bismuth-containing quadruple regimen for Helicobacter pylori infection: rationale and design of an open-label, multicenter, randomized controlled trial.

BACKGROUND: Owing to its strong acid inhibition, potassium-competitive acid blocker (P-CAB) based regimens for Helicobacter pylori (H. pylori) eradication are expected to offer clinical advantages over proton pump inhibitor (PPI) based regimens. This study aims to compare the efficacy and adverse effects of a 7-day and a 14-day P-CAB-based bismuth-containing quadruple regimen (PC-BMT) with those of a 14-day PPI-based bismuth-containing quadruple regimen (P-BMT) in patients with high clarithromycin resistance. METHODS: This randomized multicenter controlled clinical trial will be performed at five teaching hospitals in Korea. Patients with H. pylori infection who are naive to treatment will be randomized into one of three regimens: 7-day or 14-day PC-BMT (tegoprazan 50 mg BID, bismuth subcitrate 300 mg QID, metronidazole 500 mg TID, and tetracycline 500 mg QID) or 14-day P-BMT. The eradication rate, treatment-related adverse events, and drug compliance will be evaluated and compared among the three groups. Antibiotic resistance testing by culture will be conducted during the trial, and these data will be used to interpret the results. A total of 366 patients will be randomized to receive 7-day PC-BMT (n = 122), 14-day PC-BMT (n = 122), or 14-day P-BMT (n = 122). The H. pylori eradication rates in the PC-BMT and P-BMT groups will be compared using intention-to-treat and per-protocol analyses. DISCUSSION: This study will demonstrate that the 7-day or 14-day PC-BMT is well tolerated and achieve similar eradication rates to those of 14-day P-BMT. Additionally, the 7-day PC-BMT will show fewer treatment-related adverse effects and higher drug compliance, owing to its reduced treatment duration. TRIAL REGISTRATION: Korean Clinical Research Information Service registry, KCT0007444. Registered on 28 June 2022, https://cris.nih.go.kr/cris/index/index.do .

Application of Machine Learning Based on Structured Medical Data in Gastroenterology.

The era of big data has led to the necessity of artificial intelligence models to effectively handle the vast amount of clinical data available. These data have become indispensable resources for machine learning. Among the artificial intelligence models, deep learning has gained prominence and is widely used for analyzing unstructured data. Despite the recent advancement in deep learning, traditional machine learning models still hold significant potential for enhancing healthcare efficiency, especially for structured data. In the field of medicine, machine learning models have been applied to predict diagnoses and prognoses for various diseases. However, the adoption of machine learning models in gastroenterology has been relatively limited compared to traditional statistical models or deep learning approaches. This narrative review provides an overview of the current status of machine learning adoption in gastroenterology and discusses future directions. Additionally, it briefly summarizes recent advances in large language models.

Clinical Decision Support System for All Stages of Gastric Carcinogenesis in Real-Time Endoscopy: Model Establishment and Validation Study.

BACKGROUND: Our research group previously established a deep-learning-based clinical decision support system (CDSS) for real-time endoscopy-based detection and classification of gastric neoplasms. However, preneoplastic conditions, such as atrophy and intestinal metaplasia (IM) were not taken into account, and there is no established model that classifies all stages of gastric carcinogenesis. OBJECTIVE: This study aims to build and validate a CDSS for real-time endoscopy for all stages of gastric carcinogenesis, including atrophy and IM. METHODS: A total of 11,868 endoscopic images were used for training and internal testing. The primary outcomes were lesion classification accuracy (6 classes: advanced gastric cancer, early gastric cancer, dysplasia, atrophy, IM, and normal) and atrophy and IM lesion segmentation rates for the segmentation model. The following tests were carried out to validate the performance of lesion classification accuracy: (1) external testing using 1282 images from another institution and (2) evaluation of the classification accuracy of atrophy and IM in real-world procedures in a prospective manner. To estimate the clinical utility, 2 experienced endoscopists were invited to perform a blind test with the same data set. A CDSS was constructed by combining the established 6-class lesion classification model and the preneoplastic lesion segmentation model with the previously established lesion detection model. RESULTS: The overall lesion classification accuracy (95% CI) was 90.3% (89%-91.6%) in the internal test. For the performance validation, the CDSS achieved 85.3% (83.4%-97.2%) overall accuracy. The per-class external test accuracies for atrophy and IM were 95.3% (92.6%-98%) and 89.3% (85.4%-93.2%), respectively. CDSS-assisted endoscopy showed an accuracy of 92.1% (88.8%-95.4%) for atrophy and 95.5% (92%-99%) for IM in the real-world application of 522 consecutive screening endoscopies. There was no significant difference in the overall accuracy between the invited endoscopists and established CDSS in the prospective real-clinic evaluation (P=.23). The CDSS demonstrated a segmentation rate of 93.4% (95% CI 92.4%-94.4%) for atrophy or IM lesion segmentation in the internal testing. CONCLUSIONS: The CDSS achieved high performance in terms of computer-aided diagnosis of all stages of gastric carcinogenesis and demonstrated real-world application potential.

Effect of Helicobacter pylori Eradication on Body Weight: A Multicenter Propensity Score-matched Analysis in Korea.

Background/Aims: There is growing interest in whether Helicobacter pylori eradication (HPE) can affect body weight. Methods: Data from 5 universities between January 2013 and December 2019 were analyzed retrospectively. H. pylori-positive subjects who had body weight measurements taken at least twice at intervals of 3 months or longer were included. Using propensity score (PS)-matched data, changes in body mass index (BMI) and the lipid profile after HPE were compared with the non-HPE group. Results: Among 363 eligible patients, 131 HPE patients were PS-matched to 131 non-HPE patients. The median intervals between the measurements were 610 (range, 154-1250) days and 606 (range, 154-1648) days in the HPE and non-HPE groups, respectively. In both groups, the mean BMI increased (from 24.5 kg/m2 to 24.7 kg/m2 in the HPE group, and from 24.4 kg/m2 to 24.5 kg/m2 in the non-HPE group). The 2 groups did not show significantly different changes (P = 0.921). In the lowest baseline BMI quartile, the BMI increased after HPE by 1.23 (standard deviation [SD], 3.72) kg/m2 (P = 0.060), and the non-HPE group showed a decreased BMI at the time of follow-up (by -0.24 [SD, 5.25] kg/m2; P = 0.937) (between-group P = 0.214). Triglyceride levels increased after HPE (mean: 135 [SD, 78] to 153 [SD, 100] mg/dL; between-group P = 0.053). Conclusion: The overall BMI change was not significantly different between the HPE and non-HPE groups, but patients with low BMI showed a tendency to gain weight after HPE. Triglyceride levels increased after HPE with marginal significance.

2022 Seoul Consensus on Clinical Practice Guidelines for Functional Constipation.

Chronic constipation is one of the most common digestive diseases encountered in clinical practice. Constipation manifests as a variety of symptoms, such as infrequent bowel movements, hard stools, feeling of incomplete evacuation, straining at defecation, a sense of anorectal blockage during defecation, and use of digital maneuvers to assist defecation. During the diagnosis of chronic constipation, the Bristol Stool Form Scale, colonoscopy, and a digital rectal examination are useful for objective symptom evaluation and differential diagnosis of secondary constipation. Physiological tests for functional constipation have complementary roles and are recommended for patients who have failed to respond to treatment with available laxatives and those who are strongly suspected of having a defecatory disorder. As new evidence on the diagnosis and management of functional constipation emerged, the need to revise the previous guideline was suggested. Therefore, these evidence-based guidelines have proposed recommendations developed using a systematic review and meta-analysis of the treatment options available for functional constipation. The benefits and cautions of new pharmacological agents (such as lubiprostone and linaclotide) and conventional laxatives have been described through a meta-analysis. The guidelines consist of 34 recommendations, including 3 concerning the definition and epidemiology of functional constipation, 9 regarding diagnoses, and 22 regarding managements. Clinicians (including primary physicians, general health professionals, medical students, residents, and other healthcare professionals) and patients can refer to these guidelines to make informed decisions regarding the management of functional constipation.

Clinical Practice Guideline for Gastritis in Korea.

Gastritis is a disease characterized by inflammation of the gastric mucosa. It is very common and has various classification systems such as the updated Sydney system. As there is a lot of evidence that Helicobacter pylori infection is associated with the development of gastric cancer and that gastric cancer can be prevented by eradication, H. pylori gastritis has been emphasized recently. The incidence rate of gastric cancer in Korea is the highest in the world, and due to the spread of screening endoscopy, atrophic gastritis and intestinal metaplasia are commonly diagnosed in the general population. However, there have been no clinical guidelines developed in Korea for these lesions. Therefore, this clinical guideline has been developed by the Korean College of Helicobacter and Upper Gastrointestinal Research for important topics that are frequently encountered in clinical situations related to gastritis. Evidence-based guidelines were developed through systematic review and de novo processes, and eight recommendations were made for eight key questions. This guideline needs to be periodically revised according to the needs of clinical practice or as important evidence about this issue is published in the future.

Deep learning-based clinical decision support system for gastric neoplasms in real-time endoscopy: development and validation study.

BACKGROUND : Deep learning models have previously been established to predict the histopathology and invasion depth of gastric lesions using endoscopic images. This study aimed to establish and validate a deep learning-based clinical decision support system (CDSS) for the automated detection and classification (diagnosis and invasion depth prediction) of gastric neoplasms in real-time endoscopy. METHODS : The same 5017 endoscopic images that were employed to establish previous models were used for the training data. The primary outcomes were: (i) the lesion detection rate for the detection model, and (ii) the lesion classification accuracy for the classification model. For performance validation of the lesion detection model, 2524 real-time procedures were tested in a randomized pilot study. Consecutive patients were allocated either to CDSS-assisted or conventional screening endoscopy. The lesion detection rate was compared between the groups. For performance validation of the lesion classification model, a prospective multicenter external test was conducted using 3976 novel images from five institutions. RESULTS : The lesion detection rate was 95.6 % (internal test). On performance validation, CDSS-assisted endoscopy showed a higher lesion detection rate than conventional screening endoscopy, although statistically not significant (2.0 % vs. 1.3 %; P = 0.21) (randomized study). The lesion classification rate was 89.7 % in the four-class classification (advanced gastric cancer, early gastric cancer, dysplasia, and non-neoplastic) and 89.2 % in the invasion depth prediction (mucosa confined or submucosa invaded; internal test). On performance validation, the CDSS reached 81.5 % accuracy in the four-class classification and 86.4 % accuracy in the binary classification (prospective multicenter external test). CONCLUSIONS : The CDSS demonstrated its potential for real-life clinical application and high performance in terms of lesion detection and classification of detected lesions in the stomach.

Outcomes of Endoscopic Retrograde Cholangiopancreatography in End-Stage Renal Disease Patients Undergoing Hemodialysis: A Systematic Review and Pooled Analysis.

Background/Aims: The adverse events associated with endoscopic retrograde cholangiopancreatography (ERCP) in end-stage renal disease (ESRD) patients undergoing hemodialysis (HD) have not been sufficiently evaluated. This study aimed to review the morbidity and mortality associated with ERCP in ESRD patients on HD using a systematic review and pooled analysis. Methods: A systematic review and pooled analysis were conducted on studies that evaluated the clinical outcomes of ERCP in patients on HD. Random-effect model meta-analyses with subgroup analyses were conducted. The methodological quality of the included publications was evaluated using the risk of bias assessment tool for nonrandomized studies. The publication bias was assessed. Results: A total of 239 studies were identified, and 12 studies comprising 7921 HD patients were included in the analysis. The pooled estimated frequency of bleeding associated with ERCP in HD patients was 5.8% (460/7921). In the subgroup analysis of seven comparative studies, the ERCP-related bleeding rate was significantly higher in HD patients than in non-HD patients (5.5% (414/7544) vs. 1.5% (6734/456,833), OR 3.84; 95% CI 4.26−25.5; p < 0.001). The pooled frequency of post-ERCP pancreatitis was 8.3%. The pooled frequency of bowel perforation was 0.3%. The pooled estimated mortality associated with ERCP was 7.1% The publication bias was minimal. Conclusion: This pooled analysis showed that ERCP-related morbidity and mortality are higher in HD patients than in non-dialysis patients.

Use of Proton Pump Inhibitors and the Risk for the Development of Gastric Cancers: A Nationwide Population-Based Cohort Study Using Balanced Operational Definitions.

OBJECTIVES: Previous cohort studies using national claim data in Korea have shown conflicting results about the association between the use of proton pump inhibitors (PPIs) and the risk of gastric cancer. This may be due to differences in the inclusion criteria or index dates of each study. This study aims to evaluate the association between PPI use and the risk of gastric cancer using balanced operational definitions. DESIGN: A population-based cohort analysis was conducted using the Korean National Health Insurance Service database. Subjects who used PPIs or histamine-2 receptor antagonist (H2RA) for more than 60 days after Helicobacter pylori eradication were included. The study subjects were those who had never used H2RAs (PPI users) and controls were those who had never used PPIs (H2RA users). For comparison, the index dates of previous studies were adopted and analyzed. The subjects were followed until the development of gastric cancer, death, or study end. RESULTS: A total of 10,012 subjects were included after propensity score matching. During a median follow-up of 6.56 years, PPI was not associated with an increased risk of gastric cancer (Hazard ratio: 1.30, 95% confidence interval: 0.75-2.27). This was consistent if the cumulative daily dose was adjusted (90/120/180 days), or if the index date was changed to the first day of PPI prescription or the last day of Helicobacter pylori eradication. There was no significant difference in mortality between both groups. CONCLUSION: PPI use was not associated with an increased risk of gastric cancer.

Impact of the Volume and Distribution of Training Datasets in the Development of Deep-Learning Models for the Diagnosis of Colorectal Polyps in Endoscopy Images.

BACKGROUND: Establishment of an artificial intelligence model in gastrointestinal endoscopy has no standardized dataset. The optimal volume or class distribution of training datasets has not been evaluated. An artificial intelligence model was previously created by the authors to classify endoscopic images of colorectal polyps into four categories, including advanced colorectal cancer, early cancers/high-grade dysplasia, tubular adenoma, and nonneoplasm. The aim of this study was to evaluate the impact of the volume and distribution of training dataset classes in the development of deep-learning models for colorectal polyp histopathology prediction from endoscopic images. METHODS: The same 3828 endoscopic images that were used to create earlier models were used. An additional 6838 images were used to find the optimal volume and class distribution for a deep-learning model. Various amounts of data volume and class distributions were tried to establish deep-learning models. The training of deep-learning models uniformly used no-code platform Neuro-T. Accuracy was the primary outcome on four-class prediction. RESULTS: The highest internal-test classification accuracy in the original dataset, doubled dataset, and tripled dataset was commonly shown by doubling the proportion of data for fewer categories (2:2:1:1 for advanced colorectal cancer: early cancers/high-grade dysplasia: tubular adenoma: non-neoplasm). Doubling the proportion of data for fewer categories in the original dataset showed the highest accuracy (86.4%, 95% confidence interval: 85.0-97.8%) compared to that of the doubled or tripled dataset. The total required number of images in this performance was only 2418 images. Gradient-weighted class activation mapping confirmed that the part that the deep-learning model pays attention to coincides with the part that the endoscopist pays attention to. CONCLUSION: As a result of a data-volume-dependent performance plateau in the classification model of colonoscopy, a dataset that has been doubled or tripled is not always beneficial to training. Deep-learning models would be more accurate if the proportion of fewer category lesions was increased.

Deep-Learning for the Diagnosis of Esophageal Cancers and Precursor Lesions in Endoscopic Images: A Model Establishment and Nationwide Multicenter Performance Verification Study.

BACKGROUND: Suspicion of lesions and prediction of the histology of esophageal cancers or premalignant lesions in endoscopic images are not yet accurate. The local feature selection and optimization functions of the model enabled an accurate analysis of images in deep learning. OBJECTIVES: To establish a deep-learning model to diagnose esophageal cancers, precursor lesions, and non-neoplasms using endoscopic images. Additionally, a nationwide prospective multicenter performance verification was conducted to confirm the possibility of real-clinic application. METHODS: A total of 5162 white-light endoscopic images were used for the training and internal test of the model classifying esophageal cancers, dysplasias, and non-neoplasms. A no-code deep-learning tool was used for the establishment of the deep-learning model. Prospective multicenter external tests using 836 novel images from five hospitals were conducted. The primary performance metric was the external-test accuracy. An attention map was generated and analyzed to gain the explainability. RESULTS: The established model reached 95.6% (95% confidence interval: 94.2-97.0%) internal-test accuracy (precision: 78.0%, recall: 93.9%, F1 score: 85.2%). Regarding the external tests, the accuracy ranged from 90.0% to 95.8% (overall accuracy: 93.9%). There was no statistical difference in the number of correctly identified the region of interest for the external tests between the expert endoscopist and the established model using attention map analysis (P = 0.11). In terms of the dysplasia subgroup, the number of correctly identified regions of interest was higher in the deep-learning model than in the endoscopist group, although statistically insignificant (P = 0.48). CONCLUSIONS: We established a deep-learning model that accurately classifies esophageal cancers, precursor lesions, and non-neoplasms. This model confirmed the potential for generalizability through multicenter external tests and explainability through the attention map analysis.

No-Code Platform-Based Deep-Learning Models for Prediction of Colorectal Polyp Histology from White-Light Endoscopy Images: Development and Performance Verification.

BACKGROUND: The authors previously developed deep-learning models for the prediction of colorectal polyp histology (advanced colorectal cancer, early cancer/high-grade dysplasia, tubular adenoma with or without low-grade dysplasia, or non-neoplasm) from endoscopic images. While the model achieved 67.3% internal-test accuracy and 79.2% external-test accuracy, model development was labour-intensive and required specialised programming expertise. Moreover, the 240-image external-test dataset included only three advanced and eight early cancers, so it was difficult to generalise model performance. These limitations may be mitigated by deep-learning models developed using no-code platforms. OBJECTIVE: To establish no-code platform-based deep-learning models for the prediction of colorectal polyp histology from white-light endoscopy images and compare their diagnostic performance with traditional models. METHODS: The same 3828 endoscopic images used to establish previous models were used to establish new models based on no-code platforms Neuro-T, VLAD, and Create ML-Image Classifier. A prospective multicentre validation study was then conducted using 3818 novel images. The primary outcome was the accuracy of four-category prediction. RESULTS: The model established using Neuro-T achieved the highest internal-test accuracy (75.3%, 95% confidence interval: 71.0-79.6%) and external-test accuracy (80.2%, 76.9-83.5%) but required the longest training time. In contrast, the model established using Create ML-Image Classifier required only 3 min for training and still achieved 72.7% (70.8-74.6%) external-test accuracy. Attention map analysis revealed that the imaging features used by the no-code deep-learning models were similar to those used by endoscopists during visual inspection. CONCLUSION: No-code deep-learning tools allow for the rapid development of models with high accuracy for predicting colorectal polyp histology.

Incidence and Survival Outcomes of Colorectal Cancer in Long-Term Metformin Users with Diabetes: A Population-Based Cohort Study Using a Common Data Model.

BACKGROUND AND AIMS: Previous studies have reported that metformin use in patients with diabetes mellitus may reduce the risk of colorectal cancer (CRC) incidence and prognosis; however, the evidence is not definite. This population-based cohort study aimed to investigate whether metformin reduces the risk of CRC incidence and prognosis in patients with diabetes mellitus using a common data model of the Korean National Health Insurance Service database from 2002 to 2013. METHODS: Patients who used metformin for at least 6 months were defined as metformin users. The primary outcome was CRC incidence, and the secondary outcomes were the all-cause and CRC-specific mortality. Cox proportional hazard model was performed and large-scaled propensity score matching was used to control for potential confounding factors. RESULTS: During the follow-up period of 81,738 person-years, the incidence rates (per 1000 person-years) of CRC were 5.18 and 8.12 in metformin users and non-users, respectively (p = 0.001). In the propensity score matched cohort, the risk of CRC incidence in metformin users was significantly lower than in non-users (hazard ratio (HR), 0.58; 95% CI (confidence interval), 0.47-0.71). In the sensitivity analysis, the lag period extending to 1 year showed similar results (HR: 0.63, 95% CI: 0.51-0.79). The all-cause mortality was significantly lower in metformin users than in non-users (HR: 0.71, 95% CI: 0.64-0.78); CRC-related mortality was also lower among metformin users. However, there was no significant difference (HR: 0.55, 95% CI: 0.26-1.08). CONCLUSIONS: Metformin use was associated with a reduced risk of CRC incidence and improved overall survival.

Computer-Aided Diagnosis of Gastrointestinal Protruded Lesions Using Wireless Capsule Endoscopy: A Systematic Review and Diagnostic Test Accuracy Meta-Analysis.

BACKGROUND: Wireless capsule endoscopy allows the identification of small intestinal protruded lesions, such as polyps, tumors, or venous structures. However, reading wireless capsule endoscopy images or movies is time-consuming, and minute lesions are easy to miss. Computer-aided diagnosis (CAD) has been applied to improve the efficacy of the reading process of wireless capsule endoscopy images or movies. However, there are no studies that systematically determine the performance of CAD models in diagnosing gastrointestinal protruded lesions. OBJECTIVE: The aim of this study was to evaluate the diagnostic performance of CAD models for gastrointestinal protruded lesions using wireless capsule endoscopic images. METHODS: Core databases were searched for studies based on CAD models for the diagnosis of gastrointestinal protruded lesions using wireless capsule endoscopy, and data on diagnostic performance were presented. A systematic review and diagnostic test accuracy meta-analysis were performed. RESULTS: Twelve studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of protruded lesions were 0.95 (95% confidence interval, 0.93-0.97), 0.89 (0.84-0.92), 0.91 (0.86-0.94), and 74 (43-126), respectively. Subgroup analyses showed robust results. Meta-regression found no source of heterogeneity. Publication bias was not detected. CONCLUSION: CAD models showed high performance for the optical diagnosis of gastrointestinal protruded lesions based on wireless capsule endoscopy.