Endoscopic Severity In Ulcerative Colitis Research Articles

P288 Fecal leukocyte esterase level can predict endoscopic activity for Inflammatory Bowel Disease patients

Abstract Background The urine leukocyte esterase (LE) strip is widely employed to detect leukocyte presence in human body fluids due to its simplicity, speed, and cost-effectiveness. Our previous study demonstrated that fecal LE (FLE) correlated with fecal calprotectin (FC) which serves as a surrogate marker reflecting disease activity in inflammatory bowel disease (IBD) patients. This study aims to assess the correlation between FLE and endoscopy severity. Methods This prospective study included IBD patients at National Taiwan University Hospital from December 2021 to November 2023. FLE and FC in the same stool sample, which was collected within one month of endoscopy, were analyzed. The correlation between FLC, FC, and endoscopic severity scores was assessed using the Pearson method. Active disease in ulcerative colitis (UC) and Crohn's disease (CD) patients was defined as Mayo endoscopic score (MES) ≥ 2 and simple Endoscopic Score for Crohn's Disease (SESCD) ≥ 8, respectively. Sensitivity, specificity, positive and negative predictive values (PPV and NPV, respectively), and the Area Under the Receiver Operating Characteristic curve (AUROC) were analyzed by using SPSS. Results A total of 177 IBD patients (93 with UC, 84 with CD) were included. The correlation between FLE and FC levels was moderately positive (r=0.305, p<0.001). The correlation between FLE and endoscopic severity in UC and CD patients was 0.442 (p<0.001) and 0.293 (p=0.007), respectively. Among UC patients, the area under the receiver operating characteristic curve (AUROC) for predicting MES ≥ 2 by FLE and FC was 0.717 and 0.787 (p=0.241), with an optimal cutoff of 2+ for FLE and 42.5 mg/kg for FC, respectively. At this cutoff point, FLE demonstrated a sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for predicting MES ≥ 2 as 52.3%, 81.6%, 71.8%, and 65.6%, respectively. For CD patients, the AUROC for predicting SESCD ≥ 8 by FLE and FC was 0.761 and 0.869 (p=0.203), with an optimal cutoff of 2+ for FLE and 225 mg/kg for FC, respectively. FLE exhibited a sensitivity, specificity, PPV, and NPV of 81.8%, 64.4%, 74.3%, and 95.9% for predicting SESCD ≥8 respectively, at this cutoff. Conclusion Our results demonstrated that FLE can predict endoscopic activity, which is a cheaper and widely available monitoring tool, might be an alternative choice to FC for IBD monitoring.

Artificial intelligence quantifying endoscopic severity of ulcerative colitis in gradation scale.

Existing endoscopic scores for ulcerative colitis (UC) objectively categorize disease severity based on the presence or absence of endoscopic findings; therefore, it may not reflect the range of clinical severity within each category. However, inflammatory bowel disease (IBD) expert endoscopists categorize the severity and diagnose the overall impression of the degree of inflammation. This study aimed to develop an artificial intelligence (AI) system that can accurately represent the assessment of the endoscopic severity of UC by IBD expert endoscopists. A ranking-convolutional neural network (ranking-CNN) was trained using comparative information on the UC severity of 13,826 pairs of endoscopic images created by IBD expert endoscopists. Using the trained ranking-CNN, the UC Endoscopic Gradation Scale (UCEGS) was used to express severity. Correlation coefficients were calculated to ensure that there were no inconsistencies in assessments of severity made using UCEGS diagnosed by the AI and the Mayo Endoscopic Subscore, and the correlation coefficients of the mean for test images assessed using UCEGS by four IBD expert endoscopists and the AI. Spearman's correlation coefficient between the UCEGS diagnosed by AI and Mayo Endoscopic Subscore was approximately 0.89. The correlation coefficients between IBD expert endoscopists and the AI of the evaluation results were all higher than 0.95 (P < 0.01). The AI developed here can diagnose UC severity endoscopically similar to IBD expert endoscopists.

DOP74 Artificial Intelligence Quantifying Endoscopic Severity of Ulcerative Colitis in Gradation Scale

Abstract Background The existing endoscopic scores for Ulcerative Colitis (UC) such as the Mayo Endoscopic Subscore (MES) and the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) are objectively categorize the severity of the disease based on presence or absence of endoscopic findings. Therefore, they may not reflect the range of clinical severity within each category. But, Inflammatory bowel disease expert endoscopists do not only categorize the severity, but rather diagnose the overall impression of degree of inflammation. Therefore, the purpose of this study was to develop an AI that can accurately represent the complexed assessment of endoscopic severity of UC by expert endoscopists, similarly to Visual Analogue Scale (VAS). Methods To enable the AI to perform continuous evaluations of inflammation in line with the strategy used by IBD expert endoscopists, we did not utilize scores determined from images using MES or UCEIS for physician data. Rather, we incorporated data for the relationships identified by IBD expert endoscopists who compared the severity of paired images. This study was conducted using a method that incorporates data on relationships identified by comparing the severity of paired images created from 59595 endoscopic images by an IBD expert endoscopist into a Ranking- Convolutional Neural Network, and then the severity was then expressed on a scale called UC Endoscopic Gradation Scale (UCEGS) rather than a score. Using 4,000 images for which the MES had been assessed beforehand by an IBD expert endoscopist, correlation coefficients were calculated to ensure that there were no inconsistencies in assessments of severity made using results of this novel AI diagnosed UCEGS and the current MES score. The correlation coefficients of the means of the UCEGS results for the 50 test images evaluated by the five IBD expert endoscopists and the novel AI were also calculated. Results Spearman's correlation coefficient between MES and AI-diagnosed UCEGS was approximately 0.89, indicating a strong positive correlation for the order of severity between the AI-diagnosed UCEGS and MES. Correlation coefficient between IBD expert endoscopists and the AI of the evaluation results were all higher than 0.95 (P&amp;lt;0.01). Conclusion In this study, we developed a novel AI that does not rely on conventional scoring methods but instead aims to leverage the intelligence of IBD expert endoscopists when evaluating the disease status of UC. This AI quantifies inflammation as a gradient, allowing for an automated visualization of the expert endoscopist's assessment of mucosal inflammation.

S945 Diagnostic Accuracy of Convolutional Neural Network-Based Machine Learning Algorithms in Endoscopic Severity Prediction of Ulcerative Colitis: A Systematic Review and Meta-Analysis

Introduction: Endoscopic severity of ulcerative colitis (UC) predicts clinical outcomes and is essential to guide treatment and evaluate therapeutic response. The Mayo endoscopic score (MES) is commonly used to objectively classify mucosal damage. It ranges from 0 to 3, with a higher score reflecting increased severity. With advances in machine learning, artificial intelligence is being employed for automating image analysis. Convolutional neural network (CNN) is a powerful deep learning method for image recognition, and in this study, we aim to look at diagnostic accuracy parameters of CNN based machine learning algorithms to predict UC severity. Methods: Multiple databases, including Medline, Scopus, and Embase, were searched from inception to May 2022 using specific terms for studies evaluating the diagnostic accuracy parameters of machine learning algorithms in assessing UC severity. Inclusion was restricted to studies that employed CNN based algorithms. Outcomes of interest were the pooled accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Multiple 4X4 contingency Tables assessing the diagnostic accuracy of the algorithms were considered independent of each other as the goal was to study the overall direction of pooled rates and not calculate precise point estimates. Standard meta-analysis methods were employed using the random-effects model, and heterogeneity was assessed using the I2 statistics. Results: 12 studies were included that exclusively used CNN algorithm. Studies that used support vector machines or a combination were excluded. The CNN algorithm was trained and tested to predict Mayo score severity 0, 1, 2 & 3, individually in majority of the studies. In few studies the CNN algorithm was used to differentiate between Mayo 0 vs 1, and Mayo 0-1 vs 2-3. Although, 'ground-truth' differed, individual 4X4 Tables were considered as independent of each other for the purpose of this study. The pooled rate were as follows: Accuracy 91.2% (95% CI; 87.4-93.9, I2=84%), sensitivity 83.9% (79.2-87.7, 89%), specificity 82.3% (89.5-94.4, 84%), PPV 86.5% (980.7-90.8, 89%) and NPV 89.4% (85.8-92.2, 78%) (Figure). Conclusion: Based on our meta-analysis of 12 studies, CNN-based machine learning algorithms demonstrated excellent pooled diagnostic accuracy parameters. Further work seems to be needed to get the NPV >90. Future well-controlled studies are warranted to establish its clinical use in comparison to endoscopists’ assessment of colonoscopic UC severity (Table).Figure 1.: Forest Plot for sensitivities of selected studies Table 1. - Pooled rates of outcomes of interest Outcome Pooled rates (95% confidence interval, I2 % heterogeneity) Accuracy 91.2% (87.4-93.9, 84%)20 datasets Sensitivity 83.9% (79.2-87.7, 89%)30 datasets Specificity 92.3% (89.5-94.4, 84%)30 datasets PPV 86.5% (80.7-90.8, 89%)18 datasets NPV 89.4% (85.8-92.2, 78%)18 datasets

High Accuracy in Classifying Endoscopic Severity in Ulcerative Colitis Using Convolutional Neural Network.

The evaluation of endoscopic disease severity is a crucial component in managing patients with ulcerative colitis (UC). However, endoscopic assessment suffers from substantial intraobserver and interobserver variations, limiting the reliability of individual assessments. Therefore, we aimed to develop a deep learning model capable of distinguishing active from healed mucosa and differentiating between different endoscopic disease severity degrees. One thousand four hundred eighty-four unique endoscopic images from 467 patients were extracted for classification. Two experts classified all images independently of one another according to the Mayo endoscopic subscore (MES). In cases of disagreement, a third expert classified the images. Different convolutional neural networks were considered for automatically classifying UC severity. Five-fold cross-validation was used to develop and select the final model. Afterward, unseen test data sets were used for model evaluation. In the most challenging task-distinguishing between all categories of MES-our final model achieved a test accuracy of 0.84. When evaluating this model on the binary tasks of distinguishing MES 0 vs 1-3 and 0-1 vs 2-3, it achieved accuracies of 0.94 and 0.93 and areas under the receiver operating characteristic curves of 0.997 and 0.998, respectively. We have developed a highly accurate, new, automated way of evaluating endoscopic images from patients with UC. We have demonstrated how our deep learning model is capable of distinguishing between all 4 MES levels of activity. This new automated approach may optimize and standardize the evaluation of disease severity measured by the MES across centers no matter the level of medical expertise.

Automated evaluation of colon capsule endoscopic severity of ulcerative colitis using ResNet50.

Capsule endoscopy has been widely used as a non-invasive diagnostic tool for small or large intestinal lesions. In recent years, automated lesion detection systems using machine learning have been devised. This study aimed to develop an automated system for capsule endoscopic severity in patients with ulcerative colitis along the entire length of the colon using ResNet50. Capsule endoscopy videos from patients with ulcerative colitis were collected prospectively. Each single examination video file was partitioned into four segments: the cecum and ascending colon, transverse colon, descending and sigmoid colon, and rectum. Fifty still pictures (576 × 576 pixels) were extracted from each partitioned video. A patch (128 × 128 pixels) was trimmed from the still picture at every 32-pixel-strides. A total of 739,021 patch images were manually classified into six categories: 0) Mayo endoscopic subscore (MES) 0, 1) MES1, 2) MES2, 3) MES3, 4) inadequate quality for evaluation, and 5) ileal mucosa. ResNet50, a deep learning framework, was trained using 483,644 datasets and validated using 255,377 independent datasets. In total, 31 capsule endoscopy videos from 22 patients were collected. The accuracy rates of the training and validation datasets were 0.992 and 0.973, respectively. An automated evaluation system for the capsule endoscopic severity of ulcerative colitis was developed. This could be a useful tool for assessing topographic disease activity, thus decreasing the burden of image interpretation on endoscopists.

P561 Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Mayo Endoscopic Score (MES) in predicting the therapeutic effect of mesalazine in UC patients

Abstract Background The Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and the Mayo Endoscopic Score (MES) were developed as an objective method of the endoscopic severity in ulcerative colitis (UC); however, it was still unclear whether UCEIS and MES could guide the mesalazine treatment in UC. Methods Consecutive UC patients who had undergone colonoscopy within 1 month before starting mesalazine between October 2011 and July 2016 were retrospectively evaluated. Demographic data, previous therapy, clinical observations, laboratory parameters, medical therapy and endoscopic assessments were documented. The primary outcome was the need for ‘step up’ treatment (containing the use of corticosteroids, immunomodulatory or surgery.) during admission and follow-up. Results Sixty-five patients were enrolled, 12(18.5%) needed ‘step up’ treatment’ due to primary or secondary nonresponse to mesalazine. UCEIS score is a predictor of primary or secondary nonresponse to mesalazine in multivariate analysis (OR, 25.65; 95% CI, 3.048–45.985; P =0.003). Receiver-operator characteristic (ROC) area of UCEIS is 0.95, with a sensitivity of 100% and specificity of 84.6%, using cut-off value of 6, which outperforms MES with the ROC area of 0.70; When UCEIS score ≥6, 60% of patients eventually need ‘step up’ treatment. Conclusion UCEIS score is a useful instrument for evaluating endoscopic improvement in UC patients treated with mesalazine. The high probability of mesalazine treatment failure and benefits of other therapy should be discussed in patients with baseline UCEIS ≥ 6.

P076 USING DEEP LEARNING FOR AUTOMATED GRADING OF ENDOSCOPIC DISEASE SEVERITY IN ULCERATIVE COLITIS

Objectives: Endoscopic severity of ulcerative colitis predicts clinical outcomes, making it critical for assessing efficacy of new therapies. However, its use in routine practice is limited by availability of experienced and trained human reviewers. We investigated the feasibility of using deep learning algorithms to independently and accurately grade severity of ulcerative colitis from still images and full motion video colonoscopies. Setting: Patients with ulcerative colitis undergoing colonoscopy at a single tertiary care referral center in the United States between 2007-2017. Design: Retrospective grading of ulcerative colitis severity was performed on colonoscopic images using the standardized Mayo score by at least 2 human reviewers as the gold standard for diagnosis. A 159-layer convolutional neural network was employed as a deep learning algorithm for feature extraction and used to train and categorize images into two clinically-relevant groups: remission (defined as Mayo 0-1) and moderate-to-severe disease (defined as Mayo 2-3). Seventy-percent of the cohort was used to train the algorithm and 30% of the cohort was used to test it. An independent set of graded full motion video colonoscopies (N=30) unseen by the algorithm was then used for external validation. Main Outcome Measure: Performance of the deep learning automated grading system was assessed using Area Under the Receive Operating Curve (AuROC), positive (PPV) and negative predictive values (NPV),and kappa statistics for agreement relative to the gold standard of human reviewers. 14,830 endoscopic still images over 3,038 unique individuals with ulcerative colitis underwent grading. The accuracy of the convolutional neural network approach for distinguishing endoscopic remission from moderate-severe disease was excellent at 93.7% (95% CI 96.4 to 97.9) with an AuROC of 0.979, yielding a PPV of 88.41% and NPV of 93.75%. Misclassification of exact Mayo endoscopic severity score was more common for intermediate endoscopic severities (Mayo grade 1 and 2), with an overall weighted Kappa agreement of k=0.855 (95% CI 0.847 to 0.863) between deep learning prediction and human reference score. Applying score prediction methods to unseen, full-motion colonoscopy videos demonstrated similar accuracy at identifying endoscopic remission (AuROC 0.981) and agreement of scores with human reference scores (k=0.821, 95% CI 0.803 to 0.839, Table 1). A deep learning algorithm accurately grades severity of ulcerative colitis as compared with experienced human reviewers. Automated analysis of colonoscopy videos could substantially improve access to standardized assessments of ulcerative colitis in routine practice and research.

Fecal Amino Acid Analysis Can Discriminate De Novo Treatment-Naïve Pediatric Inflammatory Bowel Disease From Controls.

Endoscopy remains mandatory in the diagnostic work-up of inflammatory bowel disease (IBD), but is a costly and invasive procedure. Identification of novel, noninvasive, diagnostic biomarkers remains a priority. The aim of the present study was to explore the potential of fecal amino acid composition as diagnostic biomarker for pediatric IBD. In this case-control study, treatment-naïve, de novo pediatric patients with IBD from two tertiary centers were included. Endoscopic severity of ulcerative colitis (UC) and Crohn's disease (CD) was based on physician global assessment scores, substantiated by levels of fecal calprotectin and C-reactive protein at study inclusion. Patients were instructed to collect a fecal sample prior to bowel cleansing. Healthy controls (HCs) were recruited from primary schools in the same region. Dedicated amino acid analysis was performed on all samples. Significant differences between 30 IBD patients (15 UC, 15 CD) and 15 age and sex-matched HCs were found in six amino acids (histidine, tryptophan, phenylalanine, leucine, tyrosine, and valine; all area under the curve >0.75 and P < 0.005), displaying higher levels in IBD. When distributing the patients according to type of IBD, a similar spectrum of amino acids differed between UC and HC (histidine, tryptophan, phenylalanine, leucine, valine, and serine), whereas three amino acids were different between CD and HC (histidine, tryptophan, and phenylalanine). Significantly increased levels of six different fecal amino acids were found in patients with IBD compared to controls. Whether these differences reflect decreased absorption or increased loss by inflamed intestines needs to be elucidated.

Ulcerative Colitis Endoscopic Index of Severity (UCEIS) versus Mayo Endoscopic Score (MES) in guiding the need for colectomy in patients with acute severe colitis.

BackgroundThe Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and the Mayo Endoscopic Score (MES) were developed as an objective method of the endoscopic severity in ulcerative colitis (UC); however, it was still unclear whether UCEIS vs MES could guide the need for colectomy in acute severe colitis (ASC).MethodsConsecutive ASC patients between January 2012 and May 2016 were retrospectively evaluated. Demographic data, previous therapy, clinical observations, laboratory parameters, medical therapy and endoscopic assessments were documented. The primary outcome was the need for colectomy during admission and follow-up.ResultsNinety-two patients were enrolled. 37 (40.2%) needed colectomy. UCEIS score is a predictor of requirement for colectomy in multivariate analysis (OR, 3.25; 95% CI, 1.77–5.97; P < 0.001). Receiver-operator characteristic (ROC) area of UCEIS is 0.85, with a sensitivity of 60.3% and specificity of 85.5% using cut-off value of 7, which outperforms MES with the ROC area of 0.65; When UCEIS score ≥7, 80% of patients eventually need colectomy.ConclusionUCEIS outperformed MES as a predictor for need for colectomy in ASC patients. The high probability of medical treatment failure and benefits of early colectomy should be discussed in patients with baseline UCEIS ≥ 7.Acute severe colitis; colectomy; Ulcerative Colitis Endoscopic Index of Severity; Mayo Endoscopic Score

Developing an instrument to assess the endoscopic severity of ulcerative colitis: the Ulcerative Colitis Endoscopic Index of Severity (UCEIS)

BackgroundVariability in endoscopic assessment necessitates rigorous investigation of descriptors for scoring severity of ulcerative colitis (UC).ObjectiveTo evaluate variation in the overall endoscopic assessment of severity, the intra- and interindividual variation...

Human herpesvirus 6 and cytomegalovirus in ileocolonic mucosa in inflammatory bowel disease

Objectives. Reactivation of a latent cytomegalovirus (CMV) may occur in inflammatory bowel disease (IBD). Data of human herpesvirus 6 (HHV-6)—a close relative to CMV—in active IBD are scarce. The aim of this study was to detect HHV-6 and CMV antigens in the mucosa of active and inactive IBD. Material and Methods. 79 IBD patients (47 ulcerative colitis (UC) and 32 Crohn's disease (CD)) were recruited and endoscopic and histological disease activity was scored. Control group consisted of 15 non-IBD patients with normal colonoscopy. Immunohistochemical stainings for HHV-6B and CMV antigens were performed on biopsy specimens from the ileum and colorectum. The intensity of HHV-6B and CMV expression was graded as negative, mild, moderate, or intense. Results. HHV-6B antigen was positive in 35 (44%) and CMV in 64 (81%). Of controls, 6 (40%) were mildly positive for HHV-6 and 6 (40%) for CMV. In IBD, both CMV and HHV-6B intensity correlated with endoscopic disease severity (CMV p = 0.010 and HHV-6 p = 0.048). Simultaneous HHV-6B and CMV antigen expression occurred in 29 (37%) and associated with endoscopic activity (p = 0.006) and to a number of immunosuppressives (p = 0.033). A significant difference in HHV-6B positivity was found between endoscopically active and inactive UC (p = 0.040). Both CMV and HHV-6B intensity correlated with histological severity in the rectal biopsy specimens (for CMV p = 0.040 and for HHV-6B p = 0.027). Conclusions. Both viruses occurred ubiquitously in the IBD mucosa. Coexistence of viruses was common and associated with disease activity and use of immunosuppressives. HHV-6B intensity correlated with endoscopic severity in UC.

ENDOSCOPIC QUANTIFICATION OF MUCOSAL SURFACE ROUGHNESS FOR GRADING SEVERITY OF ULCERATIVE COLITIS

Background: Mucosal surface roughness is the element of Matts grading system for endoscopic severity of ulcerative colitis. The aims of the present study were to develop an image-processing method for quantifying mucosal surface roughness and to evaluate performance of this method by comparison with visually assessed surface roughness. Methods: A total of 139 digitized colonoscopic pictures from 69 randomly selected patients with ulcerative colitis were used. The red frame of the endoscopic picture was processed for the mean spatial gradient reflecting the surface roughness. Three endoscopists (E1, E2, E3), unaware of the study design were asked to assess the surface roughness by using a visual analog scale (VAS) from 0 to 1. A total of three sessions for surface roughness were performed by each endoscopist on different days. Results: The overall mean gradient was 28.9 ± 10.9. The mean VAS did not significantly differ among endoscopists (0.42 ± 0.23 for E1, 0.45 ± 0.19 for E2 and 0.43 ± 0.28, P > 0.05). The correlation coefficient of VAS between E1 and E2, between E2 and E3, and between E3 and E1 was 0.957 (P < 0.0001), 0.914 (P < 0.0001) and 0.950 (P < 0.0001), respectively. The mean gradient correlated with the averaged VAS for each endoscopist (r = 0.711 for E1, P < 0.0001; 0.672 for E2, P < 0.0001; 0.826 for E3, P < 0.0001). Conclusion: This method may provide a means for mucosal surface roughness as a pictorial parameter, regardless of the organ studied.

Bowel Ultrasound and Mucosal Healing in Ulcerative Colitis

Background and Aim: Mucosal healing (MH) after short-term medical treatment is being considered as an important step in the therapeutic work-up of inflammatory bowel disorder (IBD) patients due to the potential prognostic role of MH in predicting disease outcome. However, IBD patients are reluctant to be re-endoscoped during follow-up; therefore, there is a need for non-invasive alternative index of MH which can replace endoscopy in clinical practice. We evaluated bowel ultrasound (US) as a surrogate of colonoscopy in a series of consecutive patients with active ulcerative colitis (UC). Patients and Methods: 83 patients with moderate to severe UC requiring high-dose steroids were initially recruited; endoscopic severity of UC was graded 0–3 according to Baron score, and US severity was also graded 0–3 according to the colonic wall thickening and the presence of vascular signal at power Doppler. 74 patients responsive to steroids and then maintained on 5-ASA compounds were followed up with repeated colonoscopy and bowel US at 3, 9 and 15 months from entry. Concordance between clinical, endoscopic and US scores at various visits was determined by kappa statistics. Multiple unconditional logistic regression models were used to assess the predictivity of Truelove, Baron and US scores measured at 3 and 9 months on the development of a UC relapse (Baron score 2–3) at 15 months. Results: An inconsistent concordance was found over time between 0 and I Baron scores and Truelove score (weighted κ between 0.38 and 0.94), with high and consistent concordance between 0 and I Baron scores and US scores (weighted κ between 0.76 and 0.90). On logistic regression analysis, a moderate/severe Baron score, regardless of their Truelove score, at 3 months was associated with a high risk of endoscopic activity at 15 months (OR 5.2; 95% CI: 1.6–17.6); similarly, patients with severe US scores (2–3) at 3 months had a high risk of severe endoscopic activity at 15 months (OR 9.1; 95% CI: 2.5–33.5). Discussion: In expert hands bowel US may be used as a surrogate of colonoscopy in evaluating the response to high-dose steroids in severe forms of UC. US score after 3 months of steroid therapy accurately predicts clinical outcome of disease at 15 months.

W1158 Inter-Observer Agreement and Predictors of Assessment of Overall Endoscopic Severity in Ulcerative Colitis (UC)

W1158 Inter-Observer Agreement and Predictors of Assessment of Overall Endoscopic Severity in Ulcerative Colitis (UC)

ENDOSCOPIC QUANTIFICATION OF MUCOSAL SURFACE ROUGHNESS FOR GRADING SEVERITY OF ULCERATIVE COLITIS

Background: Mucosal surface roughness is the element of Matts grading system for endoscopic severity of ulcerative colitis. The aims of the present study were to develop an image‐processing method for quantifying mucosal surface roughness and to evaluate performance of this method by comparison with visually assessed surface roughness.Methods: A total of 139 digitized colonoscopic pictures from 69 randomly selected patients with ulcerative colitis were used. The red frame of the endoscopic picture was processed for the mean spatial gradient reflecting the surface roughness. Three endoscopists (E1, E2, E3), unaware of the study design were asked to assess the surface roughness by using a visual analog scale (VAS) from 0 to 1. A total of three sessions for surface roughness were performed by each endoscopist on different days.Results: The overall mean gradient was 28.9 ± 10.9. The mean VAS did not significantly differ among endoscopists (0.42 ± 0.23 for E1, 0.45 ± 0.19 for E2 and 0.43 ± 0.28, P &gt; 0.05). The correlation coefficient of VAS between E1 and E2, between E2 and E3, and between E3 and E1 was 0.957 (P &lt; 0.0001), 0.914 (P &lt; 0.0001) and 0.950 (P &lt; 0.0001), respectively. The mean gradient correlated with the averaged VAS for each endoscopist (r = 0.711 for E1, P &lt; 0.0001; 0.672 for E2, P &lt; 0.0001; 0.826 for E3, P &lt; 0.0001).Conclusion: This method may provide a means for mucosal surface roughness as a pictorial parameter, regardless of the organ studied.

An Inverse Correlation of Human Peripheral Blood Regulatory T Cell Frequency with the Disease Activity of Ulcerative Colitis

Evidence suggests that CD4+CD25+ regulatory T cells play a crucial role in the suppression of intestinal inflammation. However, their role in the suppression of inflammatory bowel disease has not yet been addressed. We examined the proportion of regulatory T cells in inflammatory bowel disease. First, we isolated CD4+CD45RO+CD25+ T cells from the peripheral blood of healthy persons and showed that these cells suppressed T cell proliferation profoundly and expressed FoxP3 abundantly, revealing that they are regulatory cells. Then the proportion of CD45RO+CD25+ in peripheral blood CD4+ T cells was analyzed in patients and healthy controls by flow cytometry. CD4+CD45RO+CD25+ T cell frequency was significantly lower in active ulcerative colitis than in the control and inactive ulcerative colitis. CD4+CD45RO+CD25+ T cell frequency was inversely correlated with the clinical and endoscopic severity of ulcerative colitis. These results suggest that a deficiency of regulatory T cells is associated with the progression of ulcerative colitis.

Proposal of a New Clinical Index Predictive of Endoscopic Severity in Ulcerative Colitis

Assessment of disease activity by clinical parameters in ulcerative colitis is still controversial. Different clinical indexes have been proposed. Colonoscopy provides detailed information on mucosal damage. The aim of this study was to identify, among 21 clinical and laboratory parameters, which were predictive of endoscopic activity. We included 137 consecutive patients with ulcerative colitis who underwent colonoscopy, clinical examination, and blood tests within 4 weeks. Endoscopic severity was recorded using a simple score (range, 0-30). The multiple stepwise regression coefficient of each significant variable predictive of mucosal damage was used to develop a new activity index predictive of endoscopic appearance (Endoscopic-Clinical Correlation Index; ECCI). We tested the ability of our score to discriminate patients with severe endoscopic disease, calculating the area under the receiver operator characteristic curve, and we compared it to activity indexes proposed by other authors. Endoscopic severity was significantly influenced by four parameters: bloody stool, nocturnal bowel movements, body temperature >37.5 degrees C, and serum albumin. The new scoring system was calculated as ECCI = {[serum albumin x (-26)] + (bloody stool x 17) + (nocturnal bowel movements x 16) + [fever (0 or 1) x 39]} + 107. The ECCI accurately identified patients with severe endoscopic disease in our sample (sensitivity = 81%, specificity = 95%). In conclusion, the ECCI should be useful in clinical practice because it is simple and strongly related to endoscopic activity.

Computer‐aided grading system for endoscopic severity in patients with ulcerative colitis

The degree of mucosal redness can be quantified as an index of hemoglobin (IHB) that changes with photographic conditions. The first aim of the present study was to stress the exclusion of γ correction as a critical procedure for reliable measurements of IHB. The second aim was to characterize Matts grade by pictorial parameters in the gray scale picture of IHB and to establish a computer‐aided grading system of endoscopic severity in ulcerative colitis. A total of 130 digital endoscopic pictures of 55 patients with ulcerative colitis (30 Matts 1, 70 Matts 2, 20 Matts 3 and 10 Matts 4) were used. The pictures without γ correction were processed for the mean IHB, SD of IHB, kurtosis of IHB and contrast feature. A computer‐aided grading system was constructed on the basis of Bayes decision theory. Significant increase in the mean IHB was seen when comparing Matts 1 to Matts 2. The SD of IHB or contrast feature significantly increased from Matts 2 to Matts 3 or from Matts 3 to Matts 4. Kurtosis of IHB was significantly larger in Matts 3 than in Matts 1 or Matts 4. Sensitivity and specificity when discriminating Matts 1 from Matts 2, Matts 2 from Matts 3 and Matts 3 from Matts 4 by the grading system were found to be 84 and 96%, 94 and 70%, and 100 and 85%, respectively. The computer‐aided grading system may permit quantitative evaluation of effects of treatments in ulcerative colitis with minimal interobserver variation.

Proposal of a new clinical index predictive of endoscopic severity in ulcerative colitis

Proposal of a new clinical index predictive of endoscopic severity in ulcerative colitis