Iacucci, Marietta

Abstract Background & Aims Central reading of endoscopy and histopathology is the current standard for disease activity assessment in inflammatory bowel disease (IBD) clinical trials but is limited by interreader and intrareader variability, operational delays, and cost. Artificial intelligence (AI) and machine learning (ML) offer the potential to improve accuracy, efficiency, and reproducibility. The International Organization for the Study of IBD (IOIBD) developed consensus statements on AI/ML use for endoscopic and histologic endpoint assessment in IBD trials. Methods As part of the IOIBD endpoints cluster initiative, a narrative, evidence-informed review with literature searches of Medline and Embase (January 2018-February 2025) identified studies applying AI/ML to endoscopy or histology in IBD. Relevant evidence informed 36 survey statements formulated by a steering committee. Seventy-two IOIBD members were invited to vote online; consensus required ≥80% agreement (score: 7-10 on a 10-point scale). Results Forty-five members completed the survey. Consensus was reached for 28 statements related to endoscopy, pathology, and trial design. Experts agreed that AI-based central reading could improve diagnostic accuracy, expedite processes, reduce costs, and enhance reproducibility. Combining human and AI assessments was favored over AI replacement. The key limitations identified included insufficient validation, generalizability concerns, and dependence on human-annotated training datasets. Conclusions This IOIBD consensus supports the integration of AI/ML into central reading for IBD clinical trials to improve objectivity, efficiency, and consistency, while maintaining human oversight. Further research should address validation, regulatory frameworks, and multimodal integration to enable broader adoption in both trials and clinical practice.

Abstract Background and Aims Lack of clinical validation and inter-observer variability are two limitations of endoscopic assessment and scoring of disease severity in patients with ulcerative colitis [UC]. We developed a deep learning [DL] model to improve, accelerate and automate UC detection, and predict the Mayo Endoscopic Subscore [MES] and the Ulcerative Colitis Endoscopic Index of Severity [UCEIS]. Methods A total of 134 prospective videos [1550 030 frames] were collected and those with poor quality were excluded. The frames were labelled by experts based on MES and UCEIS scores. The scored frames were used to create a preprocessing pipeline and train multiple convolutional neural networks [CNNs] with proprietary algorithms in order to filter, detect and assess all frames. These frames served as the input for the DL model, with the output being continuous scores for MES and UCEIS [and its components]. A graphical user interface was developed to support both labelling video sections and displaying the predicted disease severity assessment by the artificial intelligence from endoscopic recordings. Results Mean absolute error [MAE] and mean bias were used to evaluate the distance of the continuous model’s predictions from ground truth, and its possible tendency to over/under-predict were excellent for MES and UCEIS. The quadratic weighted kappa used to compare the inter-rater agreement between experts’ labels and the model’s predictions showed strong agreement [0.87, 0.88 at frame-level, 0.88, 0.90 at section-level and 0.90, 0.78 at video-level, for MES and UCEIS, respectively]. Conclusions We present the first fully automated tool that improves the accuracy of the MES and UCEIS, reduces the time between video collection and review, and improves subsequent quality assurance and scoring.

AbstractThe European Society of Gastrointestinal Endoscopy (ESGE) presents a short list of performance measures for colonoscopy in inflammatory bowel disease (IBD) patients. Current performance measures for colonoscopy mainly focus on detecting (pre)malignant lesions. However, these performance measures are not relevant for all colonoscopy indications in IBD patients. Therefore, our aim was to provide endoscopy services across Europe and other interested countries with a tool for quality monitoring and improvement in IBD colonoscopy. Eight key performance measures and one minor performance measure were recommended for measurement and evaluation in daily endoscopy practice.

Abstract Background The European Society of Gastrointestinal Endoscopy (ESGE) has developed a core curriculum for high quality optical diagnosis training for practice across Europe. The development of easy-to-measure competence standards for optical diagnosis can optimize clinical decision-making in endoscopy. This manuscript represents an official Position Statement of the ESGE aiming to define simple, safe, and easy-to-measure competence standards for endoscopists and artificial intelligence systems performing optical diagnosis of diminutive colorectal polyps (1 – 5 mm). Methods A panel of European experts in optical diagnosis participated in a modified Delphi process to reach consensus on Simple Optical Diagnosis Accuracy (SODA) competence standards for implementation of the optical diagnosis strategy for diminutive colorectal polyps. In order to assess the clinical benefits and harms of implementing optical diagnosis with different competence standards, a systematic literature search was performed. This was complemented with the results from a recently performed simulation study that provides guidance for setting alternative competence standards for optical diagnosis. Proposed competence standards were based on literature search and simulation study results. Competence standards were accepted if at least 80 % agreement was reached after a maximum of three voting rounds. Recommendation 1 In order to implement the leave-in-situ strategy for diminutive colorectal lesions (1–5 mm), it is clinically acceptable if, during real-time colonoscopy, at least 90 % sensitivity and 80 % specificity is achieved for high confidence endoscopic characterization of colorectal neoplasia of 1–5 mm in the rectosigmoid. Histopathology is used as the gold standard. Level of agreement 95 %. Recommendation 2 In order to implement the resect-and-discard strategy for diminutive colorectal lesions (1–5 mm), it is clinically acceptable if, during real-time colonoscopy, at least 80 % sensitivity and 80 % specificity is achieved for high confidence endoscopic characterization of colorectal neoplasia of 1–5 mm. Histopathology is used as the gold standard. Level of agreement 100 %. Conclusion The developed SODA competence standards define diagnostic performance thresholds in relation to clinical consequences, for training and for use when auditing the optical diagnosis of diminutive colorectal polyps.