Therapeutic Advances in Gastrointestinal Endoscopy最新文献

The diagnostic procedure of gastrointestinal endoscopy serves essential functions in handling gastrointestinal disorders. Classic endoscopic approaches encounter multiple problems because they depend on human operators and yield ambiguous results during lesion detection. The development of artificial intelligence systems has risen as an efficient technology to enhance diagnosis precision and procedural efficiency during endoscopic procedures. The objective of this review is to assess how artificial intelligence (AI) technology influences gastrointestinal (GI) endoscopic procedures for both lesion identification and classification, and malignant polyp identification, as well as clinical intervention operations. The research investigates obstacles that exist alongside AI implementation problems in clinical gastroenterological practices and determines forthcoming guidelines. A thorough literature survey was conducted through accessing databases, including PubMed alongside Scopus as well as ScienceDirect, Elsevier, and Springer. Studies after 2019 were evaluated for the AI performance in GI endoscopic examination. The use of AI in endoscopic visual examinations boosts both the diagnostic accuracy of esophagogastroduodenoscopy and colonoscopy lesions and exceeds traditional analysis methods. AI technology enhances predictions of malignant polyp status, which helps doctors make treatment decisions while lowering the number of unnecessary biopsies. Several obstacles, including technical boundaries and biased data, and regulatory obstacles, together with clinical implementation obstacles, still continue to exist. The advancement of artificial intelligence through GI endoscopy has led to an improvement of diagnostic outcomes and treatment efficiency alongside better clinical choice capabilities. AI will implement its complete role in routine clinical practice, but needs research about current challenges and regulatory adjustments, and technological improvements to boost patient outcomes.

Background: Malignant bowel obstruction (MBO) is a frequent and debilitating complication in advanced abdominal cancers, particularly ovarian, colorectal, and gastric malignancies associated with peritoneal carcinomatosis. Surgery is often not feasible, and conventional decompression carries substantial morbidity. Endoscopic ultrasound-guided enterocolostomy (EUS-EC) with lumen-apposing metal stents (LAMS) has emerged as a minimally invasive alternative, but the evidence remains limited.

Objectives: To systematically evaluate the feasibility, safety, and clinical outcomes of EUS-EC with LAMS for the palliation of MBO.

Design: Systematic review and meta-analysis.

Methods: A comprehensive literature search was performed across PubMed, Embase, Cochrane Library, and Web of Science from database inception through August 2025. Studies were eligible for inclusion if they involved patients with MBO undergoing EUS-EC using LAMS. Statistical analysis was performed using a random-effects model with Hartung-Knapp adjustments. Primary outcomes were technical success (defined as successful stent deployment) and clinical success (defined as relief of obstruction and restoration of bowel function).

Results: Twenty-three studies (78 patients) were included. Pooled technical and clinical success rates were 96.1% and 88.4%, respectively. The mean hospital stay was 10.6 days, and oral intake resumed after a mean of 3.1 days. Mean post-procedure survival was 91 days, consistent with the advanced disease stage of most included patients. Adverse events were uncommon: diarrhea (6.4%), perforation (3.8%), bleeding (2.5%), and aspiration (1.2%). Stent misdeployment occurred in one cohort (26.6%), but all cases were managed endoscopically without major sequelae. Among 33 deaths reported, most (78.8%) were due to disease progression, with only 6.1% procedure-related.

Conclusion: EUS-EC with LAMS demonstrates high technical and clinical success, rapid symptom relief, and low procedure-related morbidity, supporting its potential as an emerging palliative option for carefully selected patients with MBO. Evidence remains limited to small retrospective cohorts and case reports, highlighting the need for prospective comparative trials with patient-centered outcomes.

Background: Insulinomas are the most common functional pancreatic neuroendocrine tumors (pNETs). Minimally invasive approaches like endoscopic ultrasound-guided radiofrequency ablation (EUS-RFA) and ethanol ablation (EUS-EA) are emerging treatment options for small insulinomas (<2 cm).

Objectives: To assess the safety, efficacy, and long-term outcomes of EUS-RFA and EUS-EA in treating small pancreatic insulinomas.

Design: A retrospective, single-center study of nine patients diagnosed with insulinomas and treated with EUS ablation methods.

Methods: Nine lesions (mean size 11 mm; range: 6-19 mm) were treated with EUS-RFA (n = 7) or EUS-EA (n = 2). EUS-RFA procedures had a mean ablation time of 31 s (range: 17-69 s), while EUS-EA used a mean ethanol volume of 1.4 ml and 0.5 ml for respective patients. All patients were followed up radiologically with CT and/or EUS for a median of 25 months (range: 6-46 months).

Results: All patients had immediate hypoglycemia relief after a single treatment. The median clinical follow-up was 40 months (range: 22-60 months), with all patients remaining asymptomatic. Complete radiologic regression was observed in six patients. Two patients had minor adverse events; no severe complications occurred.

Conclusion: EUS-guided ablation (RFA or EA) is a safe and effective treatment for small pancreatic insulinomas, providing symptom relief and radiologic regression. Further studies are needed to evaluate long-term efficacy and recurrence rates.

Background and aims: Endoscopic assessment of the regular arrangement of collecting venules (RAC) is a simple and reliable tool for predicting the absence of Helicobacter pylori (H. pylori) infection in the stomach, particularly in Asian populations. While initial studies in Western countries have yielded similar findings, RAC assessment has not yet been widely adopted in these settings. This study aims to evaluate the diagnostic accuracy of RAC in determining H. pylori status in a non-Asian population.

Methods: This prospective, multicenter study was conducted in 12 hospitals across non-Asian countries. Patients with no history of H. pylori infection or eradication were included, regardless of proton pump inhibitor (PPI) use. All participants underwent high-definition upper endoscopy without magnification or virtual chromoendoscopy. Endoscopists were trained using a 20-image test to identify the RAC pattern. H. pylori status was determined by histology and/or immunohistochemistry.

Results: A total of 648 patients were included, with an H. pylori infection prevalence of 34.7%. The RAC+ pattern was observed in 31.5% of patients, with no significant differences between those receiving PPI treatment and those who were not (p = 0.55). Absence of pathological endoscopic findings was significantly associated with a RAC+ pattern (p = 0.01). The sensitivity and negative predictive value (NPV) of RAC+ for ruling out H. pylori infection were 0.97 (95% CI: 0.94-0.99), reaching 1.00 when discordant images were reviewed by a blinded expert endoscopist. No significant differences in sensitivity or NPV were found between PPI users and non-users, or between regions with high and low H. pylori prevalence.

Conclusion: The presence of the RAC pattern along the minor gastric curvature, as assessed with white-light endoscopy, accurately identifies patients without H. pylori infection in non-Asian countries, regardless of PPI use.

Background: Primary small intestinal lymphoma (PSIL) is a rare malignancy with heterogeneous clinical and pathological features, making accurate diagnosis challenging.

Objectives: To investigate the clinical value of double-balloon enteroscopy (DBE) combined with endoscopic ultrasonography (EUS) in the diagnosis of small intestinal lymphoma.

Design: Retrospective cohort study.

Methods: We retrospectively reviewed 21 patients with pathologically confirmed PSIL who underwent both DBE and EUS at the Department of Small Intestinal Endoscopy, The Sixth Affiliated Hospital of Sun Yat-sen University, between September 2022 and May 2025. Clinical data were collected and analyzed in combination with pathological findings.

Results: A total of 21 patients were included (12 males, 9 females; median age of 52 years, range 31-87 years. Subtypes of B-cell lymphomas included diffuse large B-cell lymphoma (n = 5), follicular lymphoma (n = 3), and mucosa-associated lymphoid tissue lymphoma (n = 6). T-cell lymphomas included peripheral T-cell lymphoma (n = 7). Endoscopic findings were classified into five categories (1): hypertrophic type (2), exophytic tumor type (3), follicular/polypoid type (4), ulcerative type, and (5) diffusion type. EUS classification included superficial spreading (38.1%, 8/21), diffuse infiltrative (42.9%, 9/21), and nodular (19.0%, 4/21).

Conclusion: DBE combined with EUS provides complementary morphological and structural information for the diagnosis of PSIL, improving clinical recognition and subtype characterization. Future multicenter studies with larger cohorts are warranted to validate these findings and establish standardized diagnostic protocols.

Background: Bile leakage following hepatectomy is a challenging issue that poses difficulties for hepatobiliary surgeons. Endoscopic treatment is the primary method for managing this complication, although its effectiveness is still uncertain.

Objectives: The aim of this study was to assess the effectiveness and risk factors of endoscopic treatment for bile leakage after hepatectomy.

Design: A retrospective cohort study.

Methods: A retrospective study was performed on 15 patients who experienced bile leakage following hepatectomy and were successfully treated with endoscopic retrograde cholangiography (ERCP). The primary focus was to examine how factors like the site of bile leakage, the position of biliary drainage, and late-set leakage impact early clinical success (ECS).

Results: Out of the 15 cases, 10 successfully achieved ECS through endoscopic treatment. The highest success rate (80.0%, 4 out of 5) was seen when biliary drainage was performed by bridging, while drainage placed near the leakage site had a success rate of 75.0% (6 out of 8). The best outcomes occurred when bile leakage was located in the tertiary or higher branch bile ducts, with an 83.3% success rate (5 out of 6). Additionally, early-onset leakage had a higher ECS success rate compared to late-onset bile leakage (75.0% (6/8) vs 57.1% (4/7)). Among the 15 cases, 12 involved extensive liver resections of more than two segments, 14 included segments 7 or 8, 11 had received preoperative adjuvant therapy, and 9 had undergone transarterial chemoembolization (TACE). In cases with late-onset bile leakage, 6 out of 7 (85.7%) had undergone TACE. Bile leakage caused by TACE was more likely to be accompanied by bile duct-bronchial fistula, and the healing process took significantly longer.

Conclusion: Endoscopic management of bile leakage following liver resection is both safe and effective, making it a preferred first-line treatment. Improved results can be obtained by placing a stent to bridge and drain near the leakage site. Extensive liver resection, resection involving segments 7 or 8 of the liver, and preoperative adjuvant therapies are significant risk factors for bile leakage, particularly TACE, which may lead to bile duct-bronchial fistulas and extended recovery periods.

Background: The optimal choice between fully covered self-expandable metallic stents (FCSEMSs) and uncovered self-expandable metallic stent (USEMS) for managing inoperable malignant distal biliary obstruction (MDBO) remains debatable. This study aims to compare the efficacy of CSEMS and USEMS in patients with MDBO.

Method: A retrospective analysis was conducted with inoperable MDBO between January 2017 to December 2021 who underwent either USEMS or FCSEMS implantations via endoscopic retrograde cholangiopancreatography (ERCP). Primary outcomes were overall survival and stent patency. Secondary outcomes were stent occlusion rates and postoperative complications.

Results: This study included 310 patients (235 patients received FCSEMS implantations and 75 received USEMS implantations). Median follow-up duration was 5.2 months. No significant difference was observed in overall survival between the FCSEMS and USEMS groups (167 vs 169 days, p = 0.566). The mean stent patency duration was longer in the FCSEMS group compared to the USEMS group (445 vs 348 days, p = 0.020). There were no significant differences in postoperative complications between the two groups. Multivariate analysis indicated that endoscopic sphincterotomy (EST) (HR = 1.259, 95% CI: 1.167-1.358, p < 0.001), USEMS (HR = 2.277, 95% CI: 1.750-2.963, p < 0.001), stent length (HR = 1.804, 95% CI: 1.662-1.959, p < 0.001), preoperative biliary stent (HR = 1.166, 95% CI: 1.070-1.271, p < 0.001) and non-pancreatic cancer (HR = 1.404, 95% CI: 1.299-1.516, p < 0.001) were independent risk factors for stent occlusion, while BMI ⩾ 24 kg/m² (HR = 0.600, 95% CI: 0.548-0.657, p < 0.001) was identified as a protective factor. In the subgroup analysis for pancreatic cancer, patients with FCSEMS (n = 109) had an average survival time of 154.14 ± 93.93 days, while those with USEMS (n = 34) had an average survival time of 130.32 ± 57.31 days (p = 0.21). For non-pancreatic cancer, patients with FCSEMS (n = 115) had an average survival time of 194.10 ± 93.40 days, and patients with USEMS (n = 34) had an average survival time of 204.97 ± 93.40 days (p = 0.67).

Conclusion: Compared to USEMS, FCSEMS provides a longer stent patency duration for patients with MDBO. However, no significant differences were found in overall survival and postoperative complications in this retrospective study.

Background: Colorectal cancer (CRC) incidence is rising globally, intensifying pressure on endoscopy services. Colon capsule endoscopy (CCE) offers a non-invasive alternative. Despite several systematic reviews showing reasonable polyp detection rates, clinical scepticism remains.

Objectives: This meta-review and umbrella meta-analysis aim to synthesise evidence on CCE's diagnostic accuracy in polyp and CRC detection, using CT colonography or colonoscopy as the reference standard.

Methods: We conducted a systematic search of EMBASE, MEDLINE and PubMed for systematic reviews evaluating the diagnostic accuracy of CCE in detecting polyps and CRC. A qualitative thematic review and synthesis were conducted following PRISMA guidelines. A bivariate generalised linear mixed model with random effects was used for pooled diagnostic accuracy estimates, and meta-regression was performed using restricted maximum likelihood estimation.

Results: Nine systematic reviews encompassing 28 unique studies (3472 participants) were included. For polyps of any size, the pooled per-patient sensitivity was 0.79 (95% CI: 0.69-0.86), specificity was 0.77 (95% CI: 0.71-0.82), and the area under the curve (AUC) was 0.81. For polyps ⩾6 mm, sensitivity and specificity were 0.80 and 0.87 (AUC 0.81), and for polyps ⩾10 mm, 0.88 and 0.95 (AUC 0.95), respectively. Second-generation CCE (CCE2) improved diagnostic accuracy across all polyp sizes. For polyps of any size, CCE2 achieved a sensitivity of 0.90, specificity of 0.81 and AUC of 0.82. For polyps ⩾ 6 mm and ⩾10 mm, AUCs were 0.92 and 0.94, respectively. CCE2 showed high sensitivity for detecting any polyp size and polyps ⩾6 mm, with low heterogeneity (p > 0.05, I ² < 25%). CRC detection sensitivity was 0.96 (95% CI: 0.73-1.00) after excluding cases where the capsule failed to reach the rectum due to battery exhaustion.

Conclusion: CCE2 has high diagnostic accuracy for polyps and colorectal cancer detection. While technical challenges persist, CCE2 shows promise as a complementary diagnostic tool to help address the increasing demands for endoscopy services.

Background: Patients with inflammatory bowel disease (IBD) have an increased risk of colorectal cancer. Endoscopic surveillance is recommended but is challenging due to the presence of active inflammation, flat dysplasia and inflammatory pseudopolyposis. CAD-EYE, an artificial intelligence (AI) powered endoscopic module by FUJIFILM, optically characterises lesions in real time. The aim of this study was to evaluate the accuracy of CAD-EYE in IBD surveillance.

Methods: Ninety-seven lesions were identified from 38 patients with IBD, undergoing surveillance at a single centre. Non-magnified, still images of lesions identified during the procedure were captured, followed by characterisation by CAD-EYE as neoplastic or hyperplastic (non-neoplastic) prior to resection. Inflammatory pseudopolyps were imaged and only resected based on the physician's discretion. Images of lesions identified were characterised by two expert IBD clinicians. The accuracy of CAD-EYE was assessed for all lesions (composite of histology for resected lesions and expert-verified non-resected pseudopolyps). For the resected lesions, the accuracy of CAD-EYE was compared to expert characterisation.

Results: CAD-EYE correctly characterised 92/97 lesions (94.8%) with a sensitivity of 80.0%, specificity of 97.6%, positive predictive value of 85.7% and negative predictive value of 96.4% for neoplastic lesions. For resected lesions, diagnostic accuracy was similar between CAD-EYE (93.0%) and expert characterisation (88.4%), with no statistically significant differences in sensitivity.

Conclusion: CAD-EYE demonstrated its utility in IBD surveillance with excellent accuracy in the characterisation of lesions, including inflammatory pseudopolyps. Larger studies are required to confirm these findings, particularly for flat dysplasia.