Search

BACKGROUND & AIMS: Microscopic inflammation has significant prognostic value in ulcerative colitis (UC); however, its assessment is complex with high interobserver variability. We aimed to develop and validate an artificial intelligence (AI) computer-aided diagnosis system to evaluate UC biopsies and predict prognosis. METHODS: A total of 535 digitalized biopsies (273 patients) were graded according to the PICaSSO Histologic Remission Index (PHRI), Robarts, and Nancy Histological Index. A convolutional neural network classifier was trained to distinguish remission from activity on a subset of 118 biopsies, calibrated on 42 and tested on 375. The model was additionally tested to predict the corresponding endoscopic assessment and occurrence of flares at 12 months. The system output was compared with human assessment. Diagnostic performance was reported as sensitivity, specificity, prognostic prediction through Kaplan-Meier, and hazard ratios of flares between active and remission groups. We externally validated the model in 154 biopsies (58 patients) with similar characteristics but more histologically active patients. RESULTS: The system distinguished histological activity/remission with sensitivity and specificity of 89% and 85% (PHRI), 94% and 76% (Robarts Histological Index), and 89% and 79% (Nancy Histological Index). The model predicted the corresponding endoscopic remission/activity with 79% and 82% accuracy for UC endoscopic index of severity and Paddington International virtual ChromoendoScopy ScOre, respectively. The hazard ratio for disease flare-up between histological activity/remission groups according to pathologist-assessed PHRI was 3.56, and 4.64 for AI-assessed PHRI. Both histology and outcome prediction were confirmed in the external validation cohort. CONCLUSION: We developed and validated an AI model that distinguishes histologic remission/activity in biopsies of UC and predicts flare-ups. This can expedite, standardize, and enhance histologic assessment in practice and trials. ispartof: GASTROENTEROLOGY vol:164 issue:7 pages:1180-+ ispartof: location:United States status: published

Background Previous studies have indicated that the appendix may be a priming site of ulcerative colitis (UC). Appendectomy is inversely associated with the development of UC, and is suggested to have a beneficial effect on the disease course in patients with refractory disease. Objective The aim of the current study was to assess histological features of appendices from patients with UC and their clinical relevance. Methods Patients with UC in remission and active UC (therapy refractory) that underwent appendectomy between 2012 and 2019 were included. Histological features of UC appendices were compared to those of patients with acute appendicitis and colon carcinoma. The Robarts Histopathology Index (RHI) was used to assess appendiceal inflammation. In patients with active UC, histological and clinical characteristics were compared between patients with and without endoscopic response following appendectomy. Results In total, 140 appendix specimens were assessed (n = 35 UC remission, n = 35 active UC, n = 35 acute appendicitis, n = 35 colon carcinoma). Histological features of appendices from UC patients looked like UC rather than acute appendicitis. The presence of active appendiceal inflammation was comparable between patients in remission versus active disease (53.7% vs. 46.3%, p = 0.45) and limited versus extensive disease (58.5% vs. 41.5%, p = 0.50). Endoscopic response (Mayo 0-1) following appendectomy, assessed in 28 therapy refractory patients, was more frequently seen in patients with higher RHI scores (RHI > 6: 81.8% vs. RHI ≤ 6: 9.1%, p = 0.03) and limited disease (proctitis/left sided 63.6% vs. pancolitis 36.4%, p = 0.02). Conclusion The presence of active appendiceal inflammation is common in UC and does not correlate with colonic disease activity. More than 50% of UC patients in remission showed active histological disease in the appendix. Favorable response to appendectomy for refractory UC was seen in cases with ulcerative appendicitis. These findings might support the role of the appendix as a pivotal organ in UC.

Introduction. Histological healing has become a therapeutic goal in patients with ulcerative colitis. However, a consensus on its precise definition has not been reached yet. A large number of complex histological scoring systems for ulcerative colitis are available in literature making standardization a complicated issue. The objective of the study was to identify a histological scoring system that is adequate for routine practice and thus contributes to standardization of histological reporting of inflammation activity in ulcerative colitis. Materials and methods. We retrospectively reviewed and scored 64 H&E stained slides using Nancy index (NI), Geboes score (GS) and Robarts Histopathology Index (RHI). The level of inter-rater and intra-rater agreement, time needed for scoring per slide, and correlation between the histological scores and Mayo endoscopic score were further analysed statistically. Results. The inter-rater agreement was very good for NI (kappa=0.861) and GS (kappa=0.820), and moderate for RHI (kappa=0.592), p

Background Previous studies have indicated that the appendix may be a priming site of ulcerative colitis (UC). Appendectomy is inversely associated with the development of UC, and is suggested to have a beneficial effect on the disease course in patients with refractory disease. Objective The aim of the current study was to assess histological features of appendices from patients with UC and their clinical relevance. Methods Patients with UC in remission and active UC (therapy refractory) that underwent appendectomy between 2012 and 2019 were included. Histological features of UC appendices were compared to those of patients with acute appendicitis and colon carcinoma. The Robarts Histopathology Index (RHI) was used to assess appendiceal inflammation. In patients with active UC, histological and clinical characteristics were compared between patients with and without endoscopic response following appendectomy. Results In total, 140 appendix specimens were assessed (n = 35 UC remission, n = 35 active UC, n = 35 acute appendicitis, n = 35 colon carcinoma). Histological features of appendices from UC patients looked like UC rather than acute appendicitis. The presence of active appendiceal inflammation was comparable between patients in remission versus active disease (53.7% vs. 46.3%, p = 0.45) and limited versus extensive disease (58.5% vs. 41.5%, p = 0.50). Endoscopic response (Mayo 0–1) following appendectomy, assessed in 28 therapy refractory patients, was more frequently seen in patients with higher RHI scores (RHI > 6: 81.8% vs. RHI ≤ 6: 9.1%, p = 0.03) and limited disease (proctitis/left sided 63.6% vs. pancolitis 36.4%, p = 0.02). Conclusion The presence of active appendiceal inflammation is common in UC and does not correlate with colonic disease activity. More than 50% of UC patients in remission showed active histological disease in the appendix. Favorable response to appendectomy for refractory UC was seen in cases with ulcerative appendicitis. These findings might support the role of the appendix as a pivotal organ in UC.

Background & Aims Histopathology is an emerging treatment target in ulcerative colitis (UC) clinical trials. Our aim was to provide guidance on standardizing biopsy collection protocols, identifying optimal evaluative indices, and defining thresholds for histologic response and remission after treatment. Methods An international, interdisciplinary expert panel of 19 gastroenterologists and gastrointestinal pathologists was assembled. A modified RAND/University of California, Los Angeles appropriateness methodology was used to address relevant issues. A total of 138 statements were derived from a systematic review of the literature and expert opinion. Each statement was anonymously rated as appropriate, uncertain, or inappropriate using a 9-point scale. Survey results were reviewed and discussed before a second round of voting. Results Histologic measurements collected using a uniform biopsy strategy are important for assessing disease activity and determining therapeutic efficacy in UC clinical trials. Multiple biopsy strategies were deemed acceptable, including segmental biopsies collected according to the endoscopic appearance. Biopsies should be scored for architectural change, lamina propria chronic inflammation, basal plasmacytosis, lamina propria and epithelial neutrophils, epithelial damage, and erosions/ulcerations. The Geboes score, Robarts Histopathology Index, and Nancy Index were considered appropriate for assessing histologic activity; use of the modified Riley score and Harpaz Index were uncertain. Histologic activity at baseline should be required for enrollment, recognizing this carries operational implications. Achievement of histologic improvement or remission was considered an appropriate and realistic therapeutic target. Current histologic indices require validation for pediatric populations. Conclusions These recommendations provide a framework for standardized implementation of histopathology in UC trials. Additional work is required to address operational considerations and areas of uncertainty.

Background There are no accurate markers that can predict clinical outcome in ulcerative colitis at time of diagnosis. The aim of this study was to explore a comprehensive data set to identify and validate predictors of clinical outcome in the first year following diagnosis. Methods Treatment naive-patients with ulcerative colitis were included at time of initial diagnosis from 2004 to 2014, followed by a validation study from 2014 to 2018. Patients were treated according to clinical guidelines following a standard step-up regime. Patients were categorized according to the treatment level necessary to achieve clinical remission: mild, moderate and severe. The biopsies were assessed by Robarts histopathology index (RHI) and TNF gene transcripts. Results We included 66 patients in the calibration cohort and 89 patients in the validation. Mucosal TNF transcripts showed high test reliability for predicting severe outcome in UC. When combined with histological activity (RHI) scores the test improved its diagnostic reliability. Based on the cut-off values of mucosal TNF and RHI scores from the calibration cohort, the combined test had still high reliability in the validation cohort (specificity 0.99, sensitivity 0.44, PPV 0.89, NPV 0.87) and a diagnostic odds-ratio (DOR) of 54. Conclusions The combined test using TNF transcript and histological score at debut of UC can predict severe outcome and the need for anti-TNF therapy with a high level of precision. These validated data may be of great clinical utility and contribute to a personalized medical approach with the possibility of top-down treatment for selected patients.