Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement.

The number of artificial intelligence (AI) tools for colonoscopy on the market is increasing with supporting clinical evidence. Nevertheless, their implementation is not going smoothly for a variety of reasons, including lack of data on clinical benefits and cost-effectiveness, lack of trustworthy guidelines, uncertain indications, and cost for implementation. To address this issue and better guide practitioners, the World Endoscopy Organization (WEO) has provided its perspective about the status of AI in colonoscopy as the position statement. WEO Position Statement: Statement 1.1: Computer-aided detection (CADe) for colorectal polyps is likely to improve colonoscopy effectiveness by reducing adenoma miss rates and thus increase adenoma detection; Statement 1.2: In the short term, use of CADe is likely to increase health-care costs by detecting more adenomas; Statement 1.3: In the long term, the increased cost by CADe could be balanced by savings in costs related to cancer treatment (surgery, chemotherapy, palliative care) due to CADe-related cancer prevention; Statement 1.4: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADe to support its use in clinical practice; Statement 2.1: Computer-aided diagnosis (CADx) for diminutive polyps (≤5 mm), when it has sufficient accuracy, is expected to reduce health-care costs by reducing polypectomies, pathological examinations, or both; Statement 2.2: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADx to support its use in clinical practice; Statement 3: We recommend that a broad range of high-quality cost-effectiveness research should be undertaken to understand whether AI implementation benefits populations and societies in different health-care systems.

Artificial intelligence for gastric cancer in endoscopy: From diagnostic reasoning to market.

Recognition of gastric conditions during endoscopy exams, including gastric cancer, usually requires specialized training and a long learning curve. Besides that, the interobserver variability is frequently high due to the different morphological characteristics of the lesions and grades of mucosal inflammation. In this sense, artificial intelligence tools based on deep learning models have been developed to support physicians to detect, classify, and predict gastric lesions more efficiently. Even though a growing number of studies exists in the literature, there are multiple challenges to bring a model to practice in this field, such as the need for more robust validation studies and regulatory hurdles. Therefore, the aim of this review is to provide a comprehensive assessment of the current use of artificial intelligence applied to endoscopic imaging to evaluate gastric precancerous and cancerous lesions and the barriers to widespread implementation of this technology in clinical routine.

Endoscopic Imaging for the Diagnosis of Neoplastic and Pre-Neoplastic Conditions of the Stomach.

Gastric cancer is an aggressive disease with low long-term survival rates. An early diagnosis is essential to offer a better prognosis and curative treatment. Upper gastrointestinal endoscopy is the main tool for the screening and diagnosis of patients with gastric pre-neoplastic conditions and early lesions. Image-enhanced techniques such as conventional chromoendoscopy, virtual chromoendoscopy, magnifying imaging, and artificial intelligence improve the diagnosis and the characterization of early neoplastic lesions. In this review, we provide a summary of the currently available recommendations for the screening, surveillance, and diagnosis of gastric cancer, focusing on novel endoscopy imaging technologies.

Endoscopic ultrasound artificial intelligence-assisted for prediction of gastrointestinal stromal tumors diagnosis: A systematic review and meta-analysis.

BACKGROUND: Subepithelial lesions (SELs) are gastrointestinal tumors with heterogeneous malignant potential. Endoscopic ultrasonography (EUS) is the leading method for evaluation, but without histopathological analysis, precise differentiation of SEL risk is limited. Artificial intelligence (AI) is a promising aid for the diagnosis of gastrointestinal lesions in the absence of histopathology. AIM: To determine the diagnostic accuracy of AI-assisted EUS in diagnosing SELs, especially lesions originating from the muscularis propria layer. METHODS: Electronic databases including PubMed, EMBASE, and Cochrane Library were searched. Patients of any sex and > 18 years, with SELs assessed by EUS AI-assisted, with previous histopathological diagnosis, and presented sufficient data values which were extracted to construct a 2 × 2 table. The reference standard was histopathology. The primary outcome was the accuracy of AI for gastrointestinal stromal tumor (GIST). Secondary outcomes were AI-assisted EUS diagnosis for GIST vs gastrointestinal leiomyoma (GIL), the diagnostic performance of experienced endoscopists for GIST, and GIST vs GIL. Pooled sensitivity, specificity, positive, and negative predictive values were calculated. The corresponding summary receiver operating characteristic curve and post-test probability were also analyzed. RESULTS: Eight retrospective studies with a total of 2355 patients and 44154 images were included in this meta-analysis. The AI-assisted EUS for GIST diagnosis showed a sensitivity of 92% [95% confidence interval (CI): 0.89-0.95; P < 0.01), specificity of 80% (95%CI: 0.75-0.85; P < 0.01), and area under the curve (AUC) of 0.949. For diagnosis of GIST vs GIL by AI-assisted EUS, specificity was 90% (95%CI: 0.88-0.95; P = 0.02) and AUC of 0.966. The experienced endoscopists' values were sensitivity of 72% (95%CI: 0.67-0.76; P < 0.01), specificity of 70% (95%CI: 0.64-0.76; P < 0.01), and AUC of 0.777 for GIST. Evaluating GIST vs GIL, the experts achieved a sensitivity of 73% (95%CI: 0.65-0.80; P < 0.01) and an AUC of 0.819. CONCLUSION: AI-assisted EUS has high diagnostic accuracy for fourth-layer SELs, especially for GIST, demonstrating superiority compared to experienced endoscopists' and improving their diagnostic performance in the absence of invasive procedures.

Prognostic factors for ESD of early gastric cancers: a systematic review and meta-analysis.

Background and study aims Gastric neoplasms are one of the leading types of cancer in the world and early detection is essential to improve prognosis. Endoscopy is the gold-standard diagnostic procedure and allows adequate treatment in selected cases. Endoscopic submucosal dissection (ESD) has been reported to safely address most early gastric cancers (EGCs), with high curability rates. However, data on prognostic factors related to ESDs of EGCs are conflicting. Therefore, we aimed to systematically review the available literature and to perform a meta-analysis to identify the relevant prognostic factors in this context. Methods We performed this study according to PRISMA guidelines. Comparative studies assessing the relationship between curative resection or long-term curability rates and relevant prognostic factors were selected. Prognostic factors were demographic data, lesion features (location, morphology of the lesion, size, and depth of invasion), histological findings, Helycobacter pylori (HP) infection, presence of gastric a atrophy and body mass index (BMI). Finally, we also evaluated risk factors related to metachronous gastric neoplasm. Results The initial search retrieved 2829 records among which 46 studies were included for systematic review and meta-analysis. The total sample comprised 28366 patients and 29282 lesions. Regarding curative resection, pooled data showed no significant influence of sex [odds ratio (OR): 1.15 (0,97, 1.36) P  = 0.10 I 2  = 47 %] , age [OR: 1.00 (0.61, 1.64) P  = 1.00 I 2  = 58 %], posterior vs non-posterior location [OR: 1.35 (0.81, 2.27) P  = 0.25 I 2  = 84 %], depressed vs von-depressed macroscopic type[OR: 1.21 (0.99, 1.49) P  = 0.07 I 2  = 0 %], non-upper vs upper location [OR: 1.41 (0.93, 2.14) P  = 0.10 I 2  = 77 %] and BMI [OR: 0.84 (0.57; 1.26) P  = 0.41 I 2  = 0 %]. Differentiated neoplasms presented greater chance of cure compare to undifferentiated [OR: 0.10 (0.07, 0.15) P  < 0.00001 I 2  = 0 %]. Ulcerated lesions had lower curative rates compared to non-ulcerated [OR: 3.92 (2.81, 5.47) P  < 0.00001 I 2  = 44 %]. Lesions smaller than 20 mm had greater chance of curative resection [OR: 3.94 (3.25, 4.78) P  < 0.00001 I 2  = 38 %]. Bleeding during procedure had lower curative rates compared to non-bleeding [OR: 2.13 (1.56, 2.93) P  < 0.0001 I 2  = 0 %]. Concerning long-term cure, female gender [OR 1.62 (1.33, 1.97) P  < 0.00001 I 2  = 0 %] and the mucosal over SM1 cancers were protective factors [OR: 0.08 (0.02, 0.39) P  = 0.002 I 2  = 86 %]. Gastric atrophy [OR: 0.60 (0.45, 0.81) P  = 0.0006 I 2  = 42 %] and the pepsinogen I/pepsinogen II ratio [OR 2.29 (1.47, 3.57) P  = 0.0002 I 2  = 0 %] were risk factors to metachronous gastric neoplasm. Conclusions Ulcerated lesions, histology, bleeding and size > 20 mm are prognostic factors concerning curative resection. Regarding long-term cure, female gender and mucosal over SM1 cancer are predictive factors. Gastric atrophy and the pepsinogen ratio are risk factors for metachronous gastric neoplasm.

Is Endoscopic Balloon Dilation Still Associated With Higher Rates of Pancreatitis?: A Systematic Review and Meta-Analysis.

The objective of this study was to compare the efficacy and safety of endoscopic papillary balloon dilation (EPBD), endoscopic sphincterotomy (ES), and the combination of large balloon dilation and ES (ES + EPLBD) in the treatment of common bile duct stones, with a special focus on postendoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP). Individualized search strategies were developed in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We included randomized controlled trials (RCTs) which evaluated at least one of the following outcomes: PEP, complete stone removal in the first ERCP, need for mechanical lithotripsy, recurrence of common bile duct stones, bleeding, and cholangitis. Twenty-five RCTs were selected for analysis. Pancreatitis rates were higher for EPBD than for ES (P = 0.003), as were severe pancreatitis rates (P = 0.04). However, in the 10-mm or greater balloon subgroup analysis, this difference was not shown (P = 0.82). Rates of PEP were higher in the subgroup of non-Asian subjects (P = 0.02), and the results were not robust when RCTs that used endoscopic nasobiliary drainage were omitted. The incidence of pancreatitis was comparable between EPLBD and ES + EPLBD. All 3 approaches were equally efficacious. Nevertheless, the results should be interpreted with caution, because pancreatitis is a multifactorial pathology, and RCTs can have limited generalizability.

Expression of CK-19, galectin-3 and HBME-1 in the differentiation of thyroid lesions: systematic review and diagnostic meta-analysis.

BACKGROUND: To distinguish between malignant and benign lesions of the thyroid gland histological demonstration is often required since the fine-needle aspiration biopsy method applied pre-operatively has some limitations. In an attempt to improve diagnostic accuracy, markers using immunocytochemistry and immunohistochemistry techniques have been studied, mainly cytokeratin-19 (CK-19), galectin-3 (Gal-3) and Hector Battifora mesothelial-1 (HBME-1). However, current results remain controversial. The aim of the present article was to establish the diagnostic accuracy of CK-19, Gal-3 and HBME-1 markers, as well as their associations, in the differentiation of malignant and benign thyroid lesions. METHODS: A systematic review of published articles on MEDLINE and The Cochrane Library was performed. After establishing inclusion and exclusion criteria, 66 articles were selected. The technique of meta-analysis of diagnostic accuracy was employed and global values of sensitivity, specificity, area under the summary ROC curve, and diagnostic odds ratio (dOR) were calculated. RESULTS: For the immunohistochemistry technique, the positivity of CK-19 for the diagnosis of malignant thyroid lesions demonstrated global sensitivity of 81% and specificity of 73%; for Gal-3, sensitivity of 82% and specificity of 81%; and for HBME-1, sensitivity of 77% and specificity of 83%. The association of the three markers determined sensitivity of 85%, specificity of 97%, and diagnostic odds ratio of 95.1. Similar results were also found for the immunocytochemistry assay. CONCLUSION: This meta-analysis demonstrated that the three immunomarkers studied are accurate in pre- and postoperative diagnosis of benign and malignant thyroid lesions. Nevertheless, the search for other molecular markers must continue in order to enhance this diagnostic accuracy since the results found still show a persistency of false-negative and false-positive tests. VIRTUAL SLIDES: Http://www.diagnosticpathology.diagnomx.eu/vs/3436263067345159.