Safety of artificial intelligence-assisted optical diagnosis for leaving colorectal polyps in situ during colonoscopy (PRACTICE): a non-inferiority, randomised controlled trial.

Background: Guidelines recommend leaving in situ rectosigmoid polyps diagnosed during colonoscopy that are 5 mm or smaller if the endoscopist optically predicts them to be non-neoplastic. However, no randomised controlled trial has been done to examine the efficacy and safety of this strategy.

Methods: This open-label, multicentre, non-inferiority, randomised controlled trial enrolled adults age 18 years or older undergoing colonoscopy for screening, surveillance, or clinical indications across four Italian centres.

Clinical implications of computer-aided real-time size estimation of colorectal polyps during colonoscopy.

BACKGROUND Accurate polyp size estimation during colonoscopy is crucial for clinical decision-making, follow-up, and cost-saving strategies. Objective sizing methods are lacking, and interobserver variability is high. This prospective, multicenter, study evaluated the accuracy of a novel artificial intelligence (AI) algorithm for polyp size estimation.

Prehabilitation With Exercise and Nutrition to Reduce Morbidity of Major Hepatectomy in Patients With Sarcopenia: The PREHEP Randomized Clinical Trial.

Importance: Sarcopenia is an emerging predictor of complications after liver surgery. Strategies to mitigate its impact are crucial to improving postoperative outcomes.

Objective: To determine whether a 6-week multimodal prehabilitation program combining physical exercise and nutritional support reduces postoperative morbidity in patients with sarcopenia who are undergoing major hepatectomy.

GastroGPT: Development and controlled testing of a proof-of-concept customized clinical language model.

Background And Study Aims: Current general-purpose artificial intelligence (AI) large language models (LLMs) demonstrate limited efficacy in clinical medicine, often constrained to question-answering, documentation, and literature summarization roles. We developed GastroGPT, a proof-of-concept specialty-specific, multi-task, clinical LLM, and evaluated its performance against leading general-purpose LLMs across key gastroenterology tasks and diverse case scenarios.

Methods: In this structured analysis, GastroGPT was compared with three state-of-the-art general-purpose LLMs (LLM-A: GPT-4, LLM-B: Bard, LLM-C: Claude).

SIED-GISCOR recommendations for colonoscopy in screening programs: Part 2 - Endoscopic treatment.

The endoscopic removal of colorectal polyps is a key skill for endoscopists and is considered an essential strategy for preventing colorectal cancer. This document focuses on the therapeutic phase of screening colonoscopy, providing indications on the appropriate treatment for all types of superficial colorectal lesions. Various polypectomy techniques are described and, moreover, recommendations about diagnosis and periprocedural management of antithrombotic therapy are given, in particular in the subgroup of small lesions.

Underwater versus standard endoscopic submucosal dissection for superficial colorectal neoplasms: a propensity score matched analysis.

Background And Study Aims: Underwater ESD (UESD) has recently emerged as a less complex technical alternative to standard endoscopic submucosal dissection (SESD), but only small retrospective data are currently available. Our aim was to evaluate the effectiveness and safety of UESD, as compared to the current standard of care.

Patients And Methods: We performed a 1-to-4 nearest-neighbor retrospective propensity-score-matched-analysis between all UESD cases and all SESD cases performed and collected prospectively in a Western and an Eastern interventional endoscopy referral center, respectively.

Artificial intelligence and colorectal neoplasia detection performances in patients with positive fecal immunochemical test: Meta-analysis and systematic review.

Objectives: The combination of fecal immunochemical test (FIT) followed by colonoscopy has established itself as one of the preferred population-based screening strategies. Despite extensive exploration of various techniques and technologies, their impact on adenoma detection rate has shown inconsistency across studies in this specific setting "FIT+ population." We aimed to assess the impact of the computer-aided detection (CADe) system in all randomized trials focused on this subpopulation.

Patient Satisfaction with IBD Undergoing Colonoscopy: A Multicenter Cross-Sectional Study.

Colonoscopy is crucial for diagnosing and monitoring inflammatory bowel disease (IBD), assessing disease activity, and detecting dysplasia. However, patient adherence to surveillance remains suboptimal due to discomfort, anxiety, and concerns about bowel preparation. This multicenter cross-sectional study assessed patient satisfaction with colonoscopy in IBD patients across three Italian centers.

Building Machine Learning Models in Gastrointestinal Endoscopy.

The current landscape of machine learning models in GI endoscopy is fraught with considerable variability in methodologies and quality, posing challenges for validation and generalization. To ensure the effective integration of AI in clinical practice, it is crucial to develop and validate models rigorously across diverse and representative datasets. This involves standardizing reference standards, ensuring thorough external validation, using representative patient populations, and incorporating a range of image qualities.

Position statement of the World Endoscopy Organization: Role of endoscopy in screening, diagnosis, and treatment of esophageal superficial squamous neoplasiaia.

Esophageal squamous cell carcinoma (ESCC) remains a significant global health challenge, being the sixth leading cause of cancer mortality with pronounced geographic variability. The incidence rates range from 125 per 100,000 in northern China to 1-1.5 per 100,000 in the United States, driven by environmental and lifestyle factors such as tobacco and alcohol use, dietary habits, and pollution.

A Predictive Model Based on Quantitative Fecal Immunochemical Test Can Stratify the Risk of Colorectal Cancer in an Organized Screening Program.

Background & Aims: A significant number of post fecal immunochemical test (FIT) colonoscopies in European-organized colorectal cancer (CRC) screening programs are performed beyond the recommended 31-day threshold due to overburdened colonoscopy services. We aimed to develop a simple predictive model to stratify CRC risk of FIT+ patients.

Methods: In a cohort of screenees undergoing colonoscopy following a positive (≥20 μg hemoglobin/g feces) OC-sensor FIT result between 2004 and 2019, we derived and validated logistic regression-based models including variables independently associated with CRC and advanced neoplasms.

Clinical consequences of computer-aided colorectal polyp detection.

Background And Aim: Randomised trials show improved polyp detection with computer-aided detection (CADe), mostly of small lesions. However, operator and selection bias may affect CADe's true benefit. Clinical outcomes of increased detection have not yet been fully elucidated.

Retinal Dystrophies Associated With Peripherin-2: Genetic Spectrum and Novel Clinical Observations in 241 Patients.

Purpose: To describe the clinical, electrophysiological and genetic spectrum of inherited retinal diseases associated with variants in the PRPH2 gene.

Methods: A total of 241 patients from 168 families across 15 sites in 9 countries with pathogenic or likely pathogenic variants in PRPH2 were included. Records were reviewed for age at symptom onset, visual acuity, full-field ERG, fundus colour photography, fundus autofluorescence (FAF), and SD-OCT.

Combined gastric and colorectal cancer endoscopic screening may be cost-effective in Europe with the implementation of artificial intelligence: an economic evaluation.

Background/aims: Endoscopic screening for gastric cancer (GC) is not recommended in low-intermediate incidence countries. Artificial intelligence (AI) has high accuracy in GC detection and might increase the cost-effectiveness of screening strategies. We aimed to assess the cost-effectiveness of AI for GC detection in settings with different GC incidence and different accuracies of AI systems.

SIED-GISCOR recommendations for colonoscopy in screening programs: Part I - Diagnostic.

The implementation of FIT programs reduces incidence and mortality from CRC in the screened subjects. The ultimate efficacy for CRC morbidity and mortality prevention in a FIT program depends on the colonoscopy in FIT+ subjects that has the task of detecting and removing these advanced lesions. Recently, there has been growing evidence on factors that influence the quality of colonoscopy specifically withing organized FIT programs, prompting to dedicated interventions in order to maximize the benefit/harm ratio of post-FIT colonoscopy.