Techniques and Innovations in Gastrointestinal Endoscopy最新文献

{"title":"Bridging Performance, Annotation, and Human-Machine Interaction Gaps in Artificial Intelligence-Assisted Diagnosis of Barrett’s Neoplasia","authors":"Zhonghan Xu,&nbsp;Qibing Huang,&nbsp;Guanyuan Tian,&nbsp;Qinghua Liu,&nbsp;Kefei Wu","doi":"10.1016/j.tige.2026.250988","DOIUrl":"10.1016/j.tige.2026.250988","url":null,"abstract":"<div><div>Artificial intelligence (AI)-assisted diagnosis of early neoplasia in Barrett’s esophagus now operates in real time during endoscopy, a step from the offline, patch-based image analysis that dominated earlier work. Three problems still limit its use in routine practice. The most physically detailed imaging methods, such as volumetric laser endomicroscopy, remain too slow and expensive for everyday use, whereas lightweight white-light systems that are easy to deploy generate frequent false-positive alerts. Most existing models depend on pixel-level annotation, an approach that is difficult to scale; weakly supervised attention methods have reduced this burden in histopathology but have not been tested on endoscopic video or flat, poorly defined lesions. Little is known about how interface design, operator experience, and diagnostic uncertainty jointly shape real-time decisions between clinicians and AI systems. This review reconstructs how AI-assisted Barrett’s esophagus diagnosis evolved and examines the 3 gaps in turn. It closes with 3 directions: a performance-accessibility index applicable across imaging modalities; self-supervised and weakly supervised learning adapted to endoscopic video; and validation frameworks that bring human-factors research alongside diagnostic accuracy.</div></div>","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 4","pages":"Article 250988"},"PeriodicalIF":1.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149140905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Re-evaluating the “Practical Randomized Trial” of Needle-Knife Fistulotomy: The Need for Broader Contextualization and Objective Performance Metrics","authors":"Parth Aphale,&nbsp;Himanshu Shekhar,&nbsp;Shashank Dokania","doi":"10.1016/j.tige.2025.250962","DOIUrl":"10.1016/j.tige.2025.250962","url":null,"abstract":"","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 2","pages":"Article 250962"},"PeriodicalIF":0.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Concurrent Colonoscopy Does Not Affect Results of Wireless Ambulatory pH Monitoring","authors":"Chasen Cottle ,&nbsp;Manar Al Jawish ,&nbsp;Swathi Eluri ,&nbsp;Maoyin Pang ,&nbsp;Andree Koop","doi":"10.1016/j.tige.2025.250943","DOIUrl":"10.1016/j.tige.2025.250943","url":null,"abstract":"","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 1","pages":"Article 250943"},"PeriodicalIF":0.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145420447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Training in Advanced Endoscopy: Current Methods, Challenges, and Emerging Innovations","authors":"Dennis Yang ,&nbsp;Maham Hayat ,&nbsp;Peter V. Draganov","doi":"10.1016/j.tige.2025.250958","DOIUrl":"10.1016/j.tige.2025.250958","url":null,"abstract":"<div><div>The field of advanced endoscopy is rapidly evolving, driven by technological advancements and the growing demand for complex therapeutic procedures. One-year advanced endoscopy fellowship programs were originally established to address the increasing complexity of these procedures, supplementing the limited exposure provided during standard gastroenterology training. However, challenges remain in defining and assessing competency in these technically and cognitively demanding procedures, inculcating innovative curriculum changes to accommodate emerging techniques while striving to maintain high standards in most common advanced endoscopy procedures. As the field continues to expand, and more novel procedures are being performed standardizing training, competency assessment, and credentialing processes is increasingly important. This review explores the evolving landscape of advanced endoscopy training, highlighting existing gaps and discussing strategies to enhance education, assessment, and credentialing to ensure high-quality, standardized training for future interventional endoscopists.</div></div>","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 2","pages":"Article 250958"},"PeriodicalIF":0.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Insight: How Time, Team, and Technique Shape Fistulotomy Safety and Efficacy","authors":"Avinash Tiwari","doi":"10.1016/j.tige.2025.250951","DOIUrl":"10.1016/j.tige.2025.250951","url":null,"abstract":"","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 1","pages":"Article 250951"},"PeriodicalIF":0.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145526515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Timing of Rectal Retroflexion Does Not Reduce Patient-Reported Pain: A Randomized Controlled Trial","authors":"Ahmed Al Obaidi ,&nbsp;Morten Rose ,&nbsp;Rasmus Kroijer ,&nbsp;Jakob Ravn Grimm ,&nbsp;Michael Festersen Nielsen ,&nbsp;Sisse Helle Njor ,&nbsp;Pernille Thordal Larsen ,&nbsp;Magnus Ploug","doi":"10.1016/j.tige.2026.250969","DOIUrl":"10.1016/j.tige.2026.250969","url":null,"abstract":"<div><h3>BACKGROUND AND AIMS</h3><div>A substantial proportion of patients experience moderate to severe discomfort during colonoscopy, which may reduce willingness to undergo future procedures. According to the “peak and end rule,” retrospective pain evaluations are disproportionately influenced by the final moments. Rectal retroflexion (“looping”) is a potentially painful maneuver typically performed at the end of colonoscopy. We aimed to investigate whether performing rectal retroflexion at the beginning rather than at the end of colonoscopy reduces patient-reported pain.</div></div><div><h3>METHODS</h3><div>A multicenter, single-blinded, randomized controlled trial was conducted at 2 hospital-based endoscopy units between September 2024 and January 2025. A total of 1118 patients scheduled for colonoscopy were randomized 1:1 to loop-first (n = 521) or loop-last (n = 529) groups. Retroflexion was performed either immediately upon rectal entry or as the final procedural step. All other aspects of colonoscopy followed routine practice. The primary outcome was pain recalled after colonoscopy, measured on a numerical rating scale (0-10). Secondary outcomes included need for supplemental sedation/analgesia, colonoscopy completion rates, and procedure times.</div></div><div><h3>RESULTS</h3><div>Median pain scores did not differ between groups (loop first vs loop last, 3 [IQR, 1-6] vs 3 [IQR, 1-5]; <em>P</em> = 0.10). Supplemental sedation/analgesia was required more frequently in the loop-first group (20.7% vs 14.9%; relative risk, 1.23; 95% CI, 1.03-1.48; <em>P</em> = 0.01). Completion rates were slightly lower in the loop-first group (91.2% vs 93.6%; relative risk, 0.83; 95% CI, 0.64-1.08; <em>P</em> = 0.14).</div></div><div><h3>CONCLUSION</h3><div>Timing of rectal retroflexion did not influence overall pain recall. However, looping at the end appears advantageous, being associated with reduced sedation use and higher completion rates. These findings support performing rectal retroflexion as the final step in colonoscopy. This trial is registered at ClinicalTrials.gov (NCT06521658).</div></div>","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 3","pages":"Article 250969"},"PeriodicalIF":0.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment and Competency in Advanced Endoscopy Training: Current Methods and Future Directions","authors":"Mohammad Bilal,&nbsp;Sridevi K. Pokala,&nbsp;Sachin Wani","doi":"10.1016/j.tige.2026.250985","DOIUrl":"10.1016/j.tige.2026.250985","url":null,"abstract":"<div><div>Advanced endoscopy fellowship (AEF) programs traditionally followed an apprenticeship model of training and assessment that focused on trainees’ volume of endoscopic retrograde cholangiopancreatography (ERCP) and endoscopic ultrasound (EUS) procedures. In 2012, the Accreditation Council for Graduate Medical Education shifted its focus from this apprenticeship model to a competency-based model of medical education, and there has since been greater emphasis on competency-based training and assessment of AEF trainees. No structured curriculum exists for AEF programs. Methods that contribute to achieving competency may include participation in a high volume of procedures, ex vivo and simulation-based training, as well as video-based coaching. Minimum standards for training in ERCP, EUS, endoscopic mucosal resection, and enteral stent placement have been established by the American Society of Gastrointestinal Endoscopy for AEF trainees within structured training programs. The standards include a target number of procedures with hands-on experience during AEF as well as recommendations for trainees to track procedure-specific quality metrics throughout their training. Additionally, multiple competency-based assessment tools have been developed and validated to assess and track a trainee’s progress over time for ERCP, EUS, and endoscopic mucosal resection. However, AEF trainees are now being exposed to a myriad of other advanced endoscopy procedures such as interventional EUS procedures, third-space endoscopy, and endobariatrics. Minimum standards and validated competency-based assessment tools have yet to be established for these procedures. Future work is necessary to determine the status of competency-based assessment trainees’ performance during AEF, develop standardized curriculum for AEF trainees to ensure competency, and develop minimum standards for competency and validated competency assessment tools for emerging endoscopic procedures.</div></div>","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 4","pages":"Article 250985"},"PeriodicalIF":1.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148845492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Preoperative Prediction of Subtype and Artificial Intelligence–Driven Endomicroscopy Detection of Advanced Neoplasia in Intraductal Papillary Mucinous Neoplasms","authors":"Bryn D. Koehler ,&nbsp;Wei Chen ,&nbsp;Ashwini K. Esnakula ,&nbsp;Wendy L. Frankel ,&nbsp;Ahmed Abdelbaki ,&nbsp;Stacey Culp ,&nbsp;Ziwei Li ,&nbsp;Wei-Lun Chao ,&nbsp;Phil A. Hart ,&nbsp;Timothy M. Pawlik ,&nbsp;Zarine K. Shah ,&nbsp;Somashekar G. Krishna","doi":"10.1016/j.tige.2025.250956","DOIUrl":"10.1016/j.tige.2025.250956","url":null,"abstract":"<div><h3>Background and Aims</h3><div>Nongastric subtypes of branch duct (BD)-intraductal papillary mucinous neoplasms (IPMNs) are associated with high-grade dysplasia/invasive adenocarcinoma (HGD/IC) and disease progression. We evaluated preoperative prediction of gastric vs nongastric BD-IPMN subtypes and assessed a needle-based confocal laser endomicroscopy–guided artificial intelligence (nCLE-AI) algorithm for detecting HGD/IC in pathologist-reclassified BD-IPMNs.</div></div><div><h3>METHODS</h3><div>Participants with resected BD-IPMNs were enrolled from prospective studies (2015-2024). Phase 1: lesions were reclassified by subtype and dysplasia grade through blinded pathologist review, with discordant cases receiving mucin immunostaining and consensus review. Phase 2: using this reclassified pathology data, preoperative clinical and morphological features were analyzed to predict BD-IPMN subtypes. Phase 3: nCLE-AI performance in detecting HGD/IC within reclassified gastric and nongastric BD-IPMNs was evaluated using preoperative endomicroscopy videos.</div></div><div><h3>RESULTS</h3><div>Among 63 resected BD-IPMNs (mean diameter, 35.0 ± 10.1 mm), 38% were classified as HGD/IC. Phase 1: the interobserver agreement among pathologists for subtype classification was moderate (k = 0.52; 95% CI, 0.27-0.77). Phase 2: multivariable analysis of preoperative variables revealed that Kyoto high-risk stigmata (adjusted odds ratio [aOR], 11.568; <em>p</em> = 0.007), unifocal lesions (aOR, 8.354; <em>p</em> = 0.041), and lower body mass index (aOR, 1.37; <em>p</em> = 0.04) predicted nongastric subtype. Phase 3: the nCLE-AI algorithm using presurgical endomicroscopy imaging showed comparable sensitivity for detecting HGD/IC in nongastric and gastric IPMN subtypes (83% vs 82%; <em>p</em> = 0.92), but significantly higher specificity (100% vs 44%; <em>p</em> = 0.06) and accuracy (87% vs 53%; <em>p</em> &lt; 0.02) in the nongastric subtype.</div></div><div><h3>CONCLUSION</h3><div>Moderate interobserver variability in BD-IPMN subtype classification among pathologists highlights the need for immunohistochemistry and consensus review in challenging cases. Preoperative clinical variables can predict the nongastric subtype, which is associated with a less favorable prognosis. nCLE-AI shows improved performance in detecting HGD/IC in nongastric BD-IPMNs, where accurate risk stratification is particularly important due to the higher risk of progression.</div></div>","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 2","pages":"Article 250956"},"PeriodicalIF":0.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145876251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reporting of PROGRESS-Plus Equity Characteristics in Randomized Trials of Artificial Intelligence in Gastroenterology","authors":"Tasnim Ahmed,&nbsp;Maryam R. Hussain,&nbsp;Tia Andrade,&nbsp;Mohanad Awadalla,&nbsp;Chris Labaki,&nbsp;Rachel S. Hicklen,&nbsp;Nicolette J. Rodriguez,&nbsp;Mark Enrik Geissler,&nbsp;Tyler M. Berzin,&nbsp;Faisal S. Ali","doi":"10.1016/j.tige.2026.250980","DOIUrl":"10.1016/j.tige.2026.250980","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;BACKGROUND AND AIMS&lt;/h3&gt;&lt;div&gt;As artificial intelligence (AI) tools in gastroenterology become more integrated into diagnostic modalities, it is important that the studies used to validate them reflect the demographic diversity of the patient populations they will serve. This systematic review serves to assess the degree of representation of PROGRESS-Plus (Place of Residence, Race, Occupation, Gender, Religion, Education, Socioeconomic Status, Social Capital) domains in randomized controlled trials (RCTs) of AI tools in gastroenterology.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;As artificial intelligence (AI) tools in gastroenterology become more integrated into diagnostic modalities, it is important that the studies used to validate them reflect the demographic diversity of the patient populations they will serve. This systematic review serves to assess the degree of representation of PROGRESS-Plus (Place of Residence, Race, Occupation, Gender, Religion, Education, Socioeconomic Status, Social Capital) domains in randomized controlled trials (RCTs) of AI tools in gastroenterology.&lt;/div&gt;&lt;div&gt;&lt;h3&gt;METHODS&lt;/h3&gt;&lt;div&gt;We queried Ovid Embase and Ovid MEDLINE for all RCTs on AI tools in gastroenterology published from inception to March 1, 2025. Data extraction included variables adapted from the CONSORT-Equity (Consolidated Standards of Reporting Trials-Equity) extension and PROGRESS-Plus framework to assess health equity considerations, including reporting practices, measured in proportion, and subgroup representation evaluation using population prevalence ratios (PPRs), defined as the proportion of subgroup participants experiencing an event relative to their study representation.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;We queried Ovid Embase and Ovid MEDLINE for all RCTs on AI tools in gastroenterology published from inception to March 1, 2025. Data extraction included variables adapted from the CONSORT-Equity (Consolidated Standards of Reporting Trials-Equity) extension and PROGRESS-Plus framework to assess health equity considerations, including reporting practices, measured in proportion, and subgroup representation evaluation using population prevalence ratios (PPRs), defined as the proportion of subgroup participants experiencing an event relative to their study representation.&lt;/div&gt;&lt;div&gt;&lt;h3&gt;RESULTS&lt;/h3&gt;&lt;div&gt;Seventy-four RCTs were included in this study. Thirty-four reported data for 1 PROGRESS-Plus domain, 30 reported data for 2 domains, and 8 reported data for 3 domains. There was adequate representation of female patients and elderly patients (age &gt; 65 gt; 65 years), with PPRs between 0.8 and 1.2 in both groups. Only 13% of studies included data on race and 11% included data on ethnicity, though none provided data to compute PPRs. Reporting across all the modified CONSORT-Equity domains was &lt; 10%; the highest reporting was for domains concerning generalizability of findings (7%), whereas the lowest adherence was for reporting of participant recruitment criteria across the PROG","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 4","pages":"Article 250980"},"PeriodicalIF":1.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149043844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Raising the BARS: First US Experience of the Bariatric Anastomotic Reduction System (BARS) for Endoscopic Gastrojejunal Anastomosis Revision","authors":"Stephen A. Firkins ,&nbsp;Leandro Sierra ,&nbsp;Akash Khurana ,&nbsp;Arjun Chatterjee ,&nbsp;Roma Patel ,&nbsp;Bailey Flora ,&nbsp;Erika Staneff ,&nbsp;Roberto Simons-Linares","doi":"10.1016/j.tige.2025.250944","DOIUrl":"10.1016/j.tige.2025.250944","url":null,"abstract":"","PeriodicalId":36169,"journal":{"name":"Techniques and Innovations in Gastrointestinal Endoscopy","volume":"28 1","pages":"Article 250944"},"PeriodicalIF":0.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145420448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}