Endoscopic Activity In Ulcerative Colitis Research Articles

A New Risk Prediction Model for Detecting Endoscopic Activity of Ulcerative Colitis.

: Ulcerative colitis (UC) is an incurable, relapsing-remitting inflammatory disease that increases steadily. Mucosal healing has become the primary therapeutic objective for UC. Nevertheless, endoscopic assessments are invasive, expensive, time-consuming, and inconvenient. Therefore, it is crucial to develop a noninvasive predictive model to monitor endoscopic activity in patients with UC. : Clinical data of 198 adult patients with UC were collected from January 2016 to August 2022 at Huadong Hospital, China. : Patients with UC were randomly divided into the training cohort (70%, n=138) and the validation cohort (30%, n=60). The receiver operating characteristic curve value for the training group was 0.858 (95% confidence interval [CI], 0.781 to 0.936), whereas it was 0.845 (95% CI, 0.731 to 0.960) for the validation group. The calibration curve employed the Hosmer-Lemeshow test (p>0.05) to demonstrate the consistency between the predicted and the actual probabilities in the nomogram of these two groups. The decision curve analysis validated that the nomogram had clinical usefulness. : The nomogram, which incorporated activated partial thromboplastin time, fecal occult blood test, β2-globulin level, and fibrinogen degradation products, served as a prospective tool for evaluating UC activity in clinical practices.

Serum fibroblast growth factor 19 level correlates inversely with clinical and endoscopic activity of inflammatory bowel disease.

Inflammatory bowel disease (IBD), including ulcerative colitis (UC) and Crohn's disease (CD), is a chronic condition with relapsing-remitting course. Diarrhea and abdominal pain are the most common IBD symptoms. Fibroblast growth factor 19 (FGF19) is an endocrine factor that inhibits hepatic bile acid production and may be used as a diagnostic marker for bile acid malabsorption. To assess serum FGF19 levels in active and inactive phases of IBD and find a potential correlation between FGF19 and disease activity. Fasting serum FGF19 levels were measured in 105 IBD patients (47 UC patients, 41 CD patients without previous ileocecal resection (NR-CD), 17 CD patients after ileocecal resection (IR-CD), and 17 control subjects). The disease activity was assessed using clinical, laboratory and endoscopic criteria. Inverse correlations were found between FGF19 level and intensity of diarrhea (in UC), abdominal pain intensity (in UC and IR-CD) and inflammatory markers (in UC and IR-CD). Moreover, FGF19 concentration was inversely correlated with clinical and endoscopic activity indices in UC and CD. Fluctuations in FGF19 level related to clinical and endoscopic activity of UC and CD revealed a clear pattern of higher values in remission than in active disease phases. Fibroblast growth factor 19 may serve as a potential diagnostic biomarker and constitute a new therapeutic target in IBD.

Molecular Activity of Inflammation and Epithelial-Mesenchymal Transition in the Microenvironment of Ulcerative Colitis.

: The genetic expression in the active inflammatory regions is increased in ulcerative colitis (UC) with endoscopic activity. The aim of this study was to investigate the molecular activity of inflammation and tissue remodeling markers in endoscopically inflamed and uninflamed regions of UC. : Patients with UC (n=47) and controls (n=20) were prospectively enrolled at the Seoul National University Bundang Hospital. Inflamed tissue was obtained at the most active lesion, and uninflamed tissue was collected from approximately 15 cm above the upper end of the active lesion via colonoscopic biopsies. The messenger RNA expression levels of transforming growth factor β (TGF-β), interleukin (IL)-1β, IL-6, IL-17A, E-cadherin, olfactomedin-4 (OLFM4), leucine-rich repeat-containing G protein-coupled receptor 5 (LGR5), vimentin, fibroblast-specific protein-1 (FSP1), and α-smooth muscle actin (SMA) were evaluated. Mucosal healing (MH) was defined according to a Mayo endoscopic score of 0, 1 or non-MH (Mayo endoscopic score of 2 or 3). : The messenger RNA expressions of TGF-β, IL-1β, OLFM4, FSP1, vimentin, and α-SMA were significantly higher, and that of E-cadherin was significantly lower in inflamed and uninflamed regions of patients with UC than those in controls. In the inflamed regions, patients in the non-MH group had significantly increased genetic expression of TGF-β, FSP1, vimentin, and α-SMA compared to patients in the MH group. Similarly, the non-MH group had significantly higher genetic expression of TGF-β, IL-1β, IL-6, vimentin, and α-SMA than the MH group in the uninflamed regions. : Endoscopic activity in UC suggests inflammation and tissue remodeling of uninflamed regions similar to inflamed regions (ClinicalTrials.gov, NCT05653011).

Enhancing Calprotectin's Predictive Power as a Biomarker of Endoscopic Activity in Ulcerative Colitis: A Machine Learning Use Case.

Ulcerative colitis (UC) is a chronic inflammatory bowel disease characterized by periods of exacerbation and remission, making disease monitoring and management challenging. Endoscopy, the gold standard for assessing disease activity and severity, involves invasive procedures and is associated with patient discomfort and risks. Using machine learning (ML) to combine fecal calprotectin with other clinical or biological tests can significantly enhance the non-invasive prediction of endoscopic disease activity (EDA) in UC. Aim: To prove that by fusing fecal calprotectin with other clinical data into an ML model, the performance of the non-invasive prediction of EDA can be significantly improved. Methods: We conducted a prospective, observational, single-center study encompassing 103 patients diagnosed with UC. We employed multilayer perceptron models as the core ML algorithm for predicting EDA. For the constructed models, we utilized the varImp function from the caret library in R to assess the significance of each variable in predicting the outcome. Results: Calprotectin as a sole predictor obtained an accuracy of 70% and an area under the curve (AUC) of 0.68. Combining calprotectin with the list of selected predictors that were fed to the MLP models improved accuracy and the AUC. The accuracy of the algorithm on the test set was 85%. Similarly, the AUC increased to 0.93. This is the first study to propose the use of calprotectin as a predictor in an ML model to estimate UC endoscopic disease activity. Conclusion: The deployment of this ML model can furnish doctors and patients with valuable evaluation of endoscopic disease activity which can be highly beneficial for individuals with UC who need long-term treatment.

P235 Correlation of mental and psychological status to disease activity in patients with Inflammatory Bowel Disease using The Symptom Checklist -90- Revised Questionnaire (SCL90R)

Abstract Background Inflammatory Bowel Disease can affect mental health. There is no evidence that stress is a direct cause of the disease. Most Inflammatory Bowel Disease patients describe an emotional impact, mainly feelings of depression and anxiety. Many questionnaires used to assess anxiety in those patients including Symptom Checklist -90-Revised Questionnaire. This research aimed to investigate Correlation of mental and psychological status to disease activity in patients with Inflammatory Bowel Disease using Symptom Checklist -90-Revised Questionnaire. Methods The study included one hundred patients (50 Crohn's Disease patients – 50 Ulcerative Colitis patients). Detailed history taking, systemic physical examination, laboratory investigations, Colonoscopy, Symptom Checklist -90-Revised Questionnaire. A self-report psychometric instrument (questionnaire) for every patient. Results The mean age of Crohn’s Disease patients was 24,2 years +/- SD 3,6 years. In Ulcerative Colitis patients the mean age was 28,5 years +/- SD 7,3 years. No age or gender relation could be detected with Symptom Checklist -90-Revised Questionnaire score in both groups, The study showed a direct correlation of Crohn's Disease Activity Index (CDAI) and endoscopic activity (Simple Endoscopic Score) (SES) to Symptom Checklist -90-Revised Questionnaire. There was direct correlation of Ulcerative Colitis disease activity (Simple Clinical Colitis Activity Index) (SCCAI) and Endoscopic activity (Ulcerative Colitis Endoscopic Index of Severity) (UCEIS) to Symptom Checklist -90-Revised Questionnaire. Conclusion There is a direct correlation of disease activity and Endoscopic activity in Ulcerative Colitis and Crohn's Diseases to Symptom Checklist -90-Revised Questionnaire.

Serum Activin A Is a Novel Biomarker of Endoscopic Activity in Ulcerative Colitis.

Endoscopic healing (EH) is the long-term therapeutic goal for ulcerative colitis (UC). Since repeated colonoscopies are inconvenient and invasive, a surrogate biomarker for endoscopic activity is needed. Activin A is one of the transforming growth factor-β superfamily of proteins and has been shown to be associated with intestinal inflammation. This single-center observational study included 27 Japanese patients with UC in clinical remission who underwent colonoscopy and blood sampling. We investigated the correlations between laboratory parameters, including serum activin A levels, and endoscopic activity, classified by the Mayo endoscopic subscore (MES) in these patients. This study included 15 males and 12 females. The median age was 44.0 years. In terms of endoscopic activity, five patients were diagnosed with MES 0, 14 patients with MES 1, seven patients with MES 2, and one patient with MES 3. The median serum activin level was 134.8 pg/mL (interquartile range (IQR), 105.3 - 188.1). Serum activin A levels were significantly correlated with the MES (Spearman's rank correlation coefficient r = 0.591, P = 0.001), which was better than that of C-reactive protein (CRP) (r = 0.487, P = 0.010). In the comparison between the EH group (MES 0) and non-EH group (MES 1-3), patients without EH had significantly higher serum activin A levels (Mann-Whitney U test, P = 0.047). A cutoff value of 133.6 pg/mL indicated non-EH with a sensitivity and specificity of 0.682 and 1.000, respectively. The area under the curve (AUC) of serum activin A for detecting non-EH was 0.791 (95% confidence interval (CI), 0.618 - 0.964), while that of CRP was 0.723 (95% CI, 0.504 - 0.941). The serum activin A level is a potential novel biomarker of endoscopic activity in UC.

Laboratory Data and IBDQ-Effective Predictors for the Non-Invasive Machine-Learning-Based Prediction of Endoscopic Activity in Ulcerative Colitis.

A suitable, non-invasive biomarker for assessing endoscopic disease activity (EDA) in ulcerative colitis (UC) has yet to be identified. Our study aimed to develop a cost-effective and non-invasive machine learning (ML) method that utilizes the cost-free Inflammatory Bowel Disease Questionnaire (IBDQ) score and low-cost biological predictors to estimate EDA. Four random forest (RF) and four multilayer perceptron (MLP) classifiers were proposed. The results show that the inclusion of IBDQ in the list of predictors that were fed to the models improved accuracy and the AUC for both the RF and the MLP algorithms. Moreover, the RF technique performed noticeably better than the MLP method on unseen data (the independent patient cohort). This is the first study to propose the use of IBDQ as a predictor in an ML model to estimate UC EDA. The deployment of this ML model can furnish doctors and patients with valuable insights into EDA, a highly beneficial resource for individuals with UC who need long-term treatment.

Early Intestinal Ultrasound Predicts Long-Term Endoscopic Response to Biologics in Ulcerative Colitis.

The Milan ultrasound criteria [MUC] is a validated score to assess endoscopic activity in ulcerative colitis [UC]. MUC > 6.2 detects Mayo endoscopic score [MES] > 1. In this study we evaluated the predictive value of MUC for biologic treatment response, using colonoscopy [CS] as a reference standard. Consecutive UC patients starting biologic therapy were included, and underwent CS, IUS, clinical assessment and faecal calprotectin [FC] measurement at baseline and within 1 year. In addition, IUS, clinical and FC assessments were performed at week 12. The primary objective was to evaluate whether ultrasound improvement [MUC ≤ 6.2] at week 12 predicted endoscopic improvement at reassessment [MES ≤ 1]. Endoscopic remission was defined as MES = 0. Forty-nine patients were included [59% under infliximab, 29% under vedolizumab, 8% under adalimumab, 4% under ustekinumab]. MUC ≤ 6.2 at week 12 was the only independent predictor for MES ≤ 1 and MES = 0 at reassessment (odds ratio [OR] 5.80, p = 0.010; OR 10.41, p = 0.041; respectively). MUC ≤ 6.2 at week 12 showed a negative predictive value of 96% for detecting MES = 0. A ≥2 reduction of the MUC predicted MES = 0 (area under the curve [AUC] 0.816). MUC ≤ 4.3 was the most accurate cut-off value for MES = 0 [AUC 0.876]. Guyatt's responsiveness ratio for the MUC was 1.73 [>0.8]. MUC ≤ 6.2 at week 12 predicts long-term endoscopic response. MUC is accurate in monitoring treatment response and may be used in both clinical trials and routine practice.

Risk prediction model based on blood biomarkers for predicting moderate to severe endoscopic activity in patients with ulcerative colitis.

We explored developing an internal validation model to predict the moderate to severe endoscopic activity of ulcerative colitis (UC) patients based on non-invasive or minimally-invasive parameters. Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Mayo endoscopic subscore were performed for UC patients who met the criteria from January 2017 to August 2021 through the electronic database of our center. Logistic regression and a least absolute shrinkage and selection operator (Lasso) regression model were performed to screen the risk factors of moderate to severe UC activity. The nomogram was established subsequently. Discrimination of the model was evaluated using the concordance index (c-index), and the calibration plot and 1,000 Bootstrap were used to evaluate the model's performance and conduct internal validation. Sixty-five UC patients were included in this study. According to UCEIS criteria,45 patients were moderate to severe endoscopic activity. 26 potential predictors of UC were analyzed by logistic and Lasso regression showed that vitamin D (Vit D), albumin (ALB), prealbumin (PAB), and fibrinogen (Fbg) were the best predictors of moderate to severe endoscopic activity of UC. We used these 4 variables to develop a dynamic nomogram prediction model. The c-index was 0.860, which means good discrimination. The calibration plot and Bootstrap analysis showed that the prediction model accurately distinguished the moderate to severe endoscopic activity in UC patients. The prediction model was verified using a cohort of UC patients with moderate to severe activity defined by the Mayo endoscopic subscore, and it was found that the model still had good discrimination and calibration (c-index = 0.891). The model containing Vit D, ALB, PAB, and Fbg was a good tool for evaluating UC activity. The model is simple, accessible, and user-friendly, which has broad application prospects in clinical practice.

Hocus Pocus: the Role of Hand-held Ultrasonography in Predicting Disease Extension and Endoscopic Activity in Ulcerative Colitis.

Ulcerative colitis [UC] assessment still requires ileocolonoscopy [IC]. Intestinal ultrasound [IUS] has emerged as a non-invasive assessment tool, and the Milan Ultrasound Criteria [MUC] score has been validated to estimate and grade UC disease activity. Recently, hand-held IUS [HHIUS] has been used in several clinical settings, but data about its use in UC are limited. We aimed to evaluate the diagnostic accuracy of HHIUS compared with conventional IUS in detecting UC extension and activity. From November 2021 to September 2022, we prospectively enrolled UC patients afferent to our third-level IBD Unit for IC evaluation. Patients underwent IC, HHIUS, and IUS. Ultrasound activity was defined by MUC >6.2, and endoscopic activity was defined by a Mayo endoscopic score [MES] >1. Cohen's k test was applied to test the concordance between IUS-MUC and HHIUS-MUC after MUC dichotomisation [MUC >6.2, yes/no]. In all, 86 patients with UC were enrolled. No significant difference was recorded between IUS and HHIUS at the per-segment extension [p = N.S.], and both procedures were comparable in terms of results of bowel wall thickness [BWT] and bowel wall stratification [BWS] assessment [p = N.S.]. IUS and HHIUS displayed excellent agreement when the MUC score system was applied [k = 0.86, p <0.01]. Hand-held intestinal ultrasound and IUS are comparable in UC extension definition and MUC evaluation. HHIUS could be reliable for detecting disease activity and estimating its extension, providing close monitoring. It also represents a non-invasive, easily practicable investigation, allowing immediate medical decisions with significant time and cost advantages.

P304 Leucine-rich alpha 2 glycoprotein reduces the necessity for endoscopic examination for activity evaluation

Abstract Background Leucine-rich alpha 2 glycoprotein (LRG) reflects mucosal healing in ulcerative colitis (UC) and is useful for assessing mucosal healing. In this study, we hypothesized that endoscopy for activity evaluation may be unnecessary depending on LRG levels, and investigated the relationship between LRG and endoscopic findings. Methods Patients who underwent endoscopy for UC from April 2021 to August 2022, when LRG measurement became available, and whose LRG was measured within a month, were included in the study. The relationship between Mayo endoscopic subscore (MES) and LRG was evaluated and symptoms were also reviewed to examine these relationships. Endoscopic remission was defined as MES 1 or less. Results The mean (range) LRG values per MES and the percentage of patients with a cutoff value of less than 16 μg/mL were MES 0 (n=86): 11.3±2.8 (6.0-24.2) μg/mL, 96.5%; MES 1 (n=56): 13.3±6.0 (7.7-43.8) μg/mL, 79.2%; MES 2(n=53): 21.7±11.5(8.1~65.1) μg/mL, 34.0%, MES 3(n=19): 26.4±9.3(12.3~42.9) μg/mL, 25.0%, and AUC 0.856 in ROC analysis, higher than other markers (CRP, Alb, WBC) LRG Even below the cutoff value, 15.0% (22/147) were in endoscopic non-remission. Even when patients have neither diarrhea 3 or more times a day nor bloody stool, 7.4% (9/122) were still in endoscopic non-remission. However, there were no cases in endoscopic non-remission when the LRG was below the cutoff value and there were no such symptoms. In multivariate analysis using binomial logistic regression analysis, LRG (p=0.028) was an independent predictor of endoscopic remission, in addition to diarrhea (p=0.003) and bloody stool (p&amp;lt;0.001). Conclusion LRG was a useful tool for predicting endoscopic activity in ulcerative colitis, but LRG alone could not exclude non-remitting cases. However, LRG was considered to be an independent predictor of endoscopic remission, and all patients who had less than the LRG cutoff value and no diarrhea or bloody stool more than 3 times a day showed endoscopic remission, suggesting that endoscopy for activity evaluation may be unnecessary in such cases.

P129 Intestinal ultrasound at week 12 predicts long-term endoscopic response to biologics in ulcerative colitis

Abstract Background Intestinal ultrasound (IUS) is accurate to assess endoscopic activity in ulcerative colitis (UC). The Milan ultrasound criteria (MUC) is a validated scoring system to assess and grade endoscopic activity in UC. The most accurate cutoff value for MUC was &amp;gt; 6.2 for endoscopic activity (defined as a Mayo endoscopic score, MES ≥ 2). The aim of this study was to assess the predictive value of IUS and MUC for treatment response in a longitudinal cohort, using colonoscopy (CS) as reference standard. Methods Consecutive active UC patients starting biologic therapy were included. All patients underwent CS, IUS, clinical and faecal calprotectin (FC) evaluations prior commencing a biological therapy, and within one year (mean 9.4 months). In addition, patients were evaluated by IUS, clinical and FC assessments at week 12. The primary objective was to evaluate whether ultrasound improvement (defined as MUC ≤ 6.2) at week 12 predicted endoscopic improvement at reassessment (defined as MES ≤ 1). Endoscopic remission was defined as MES = 0. Results Forty-nine patients were included (59% under infliximab, 29% under vedolizumab, 8% under adalimumab, 4% under ustekinumab). MUC and MES correlated at reassessment (r= 0.767, p &amp;lt; 0.001). Ultrasound improvement at week 12 was the only independent predictor for MES ≤ 1 and MES = 0 at reassessment (OR 5.80, p = 0.010; OR 10.41, p = 0.041; respectively). Ultrasound improvement at week 12 showed NPV of 96% for detecting MES = 0. A ≥ 2 reduction of the MUC score predicted MES=0 (area under the curve, AUC 0.816). MUC ≤ 4.3 was the most accurate cut-off value for MES = 0 (AUC 0.876). The responsiveness ratio of Guyatt for the MUC was 1.73 and the standardized effect size ratio was 1.6. Both these values &amp;gt; 0.8 indicate a large effect of responsiveness for the MUC. Conclusion MUC is highly accurate to monitor treatment response. Ultrasound improvement after the induction period may predict long-term endoscopic response. The MUC may be used both in clinical trials and routine practice.

P228 Machine learning models utilizing simple laboratory tests may assess endoscopic activity in ulcerative colitis

Abstract Background Together with the implementation of innovative therapies for inflammatory bowel disease, mucosal healing (MH) became the novel therapeutic goal. Currently, a golden standard for evaluation of the colonic mucosa is an invasive and expensive colonoscopy. We propose here a machine learning (ML) based model as a noninvasive tool trained on biochemical patient data. Employed random forest technique used aggregation and randomization of predictors constituted of biochemical tests to accomplish a high degree of predictive accuracy reaching 95%. SHapley Additive exPlanations (SHAP) known from cooperative game theory were used to boost the interpretability of ML model based on additive feature importance across all possible predictors in the feature space. Methods The study group consisted of 252 ulcerative colitis patients hospitalized in theDepartment of Gastroenterology and Hepatology, Wroclaw Medical University. Routine laboratory test results and colonoscopy reports with the Mayo scores were collected. The data were processed with different ML classifiers. The most performant model was the random forest classifier. Then the SHAP model for the importance of consecutive clinical data was calculated. Results We found a set of particular biochemical predictors. Total protein, C-reactive protein, creatinine, and fecal calprotectin had the most significant impact on the prediction of endoscopic Mayo score, as shown in Figure 1. Conclusion Novel numerical models may predict the endoscopic activity of ulcerative colitis based on simple biochemical tests.

Common laboratory blood test immune panel markers are useful for grading ulcerative colitis endoscopic severity

BackgroundAt present, many indicators reflect the clinical disease activity of ulcerative colitis (UC). However, commonly used inflammatory markers do not show good utility for indicating endoscopic disease activity. The purpose of this study was to evaluate high sensitivity C-reactive protein (hs-CRP), C-reactive protein to albumin ratio (CAR), inflammatory markers, and complete blood count (CBC) related parameters in patients with UC as simple, non-invasive, and independent markers of endoscopic activity (EA).MethodsWe retrospectively collected extensive data from the hospital medical records of 386 patients who presented with UC to the First Affiliated Hospital of Xinjiang Medical University (Urumqi, China) from 2018 to 2022 January. The Mayo endoscopic score (MES) was used to evaluate endoscopic disease activity. All included patients were defined as the MES-All group; those with extensive colitis (E3) were defined as the MES-E3 group. Demographics, laboratory parameters, endoscopic results, the extent of disease, and drug history were recorded and analyzed.ResultsFor patients in the MES-All or MES-E3 group, hs-CRP, CAR, neutrophil to lymphocyte ratio (NLR), and platelet to lymphocyte ratio (PLR) were significantly higher in EA UC patients than in those with mucosal healing. The mean platelet volume (MPV) and lymphocyte to monocyte ratio were significantly lower in active disease than in the patient’s remission (p < 0.001). ROC analysis showed that in the MES-All and MES-E3 groups, the cutoff values of hs-CRP activity under endoscopy were 5.32 mg/L (AUC 0.850, sensitivity 77.6%, specificity 81.9%) and 5.16 mg/L (AUC 0.902, sensitivity 86.9%, specificity 85.4%) respectively, and the cutoff values of CAR were 0.14 (AUC 0.853, sensitivity 76.8%, specificity 84.8%) and 0.18 (AUC 0.904, sensitivity 81.8%, specificity 89.6%) respectively. Multivariate logistic regression analysis showed that hs-CRP, CAR, NLR, and PLR identified UC EA, while decreased MPV reflected inflammatory activity in the UC mucosa.ConclusionEspecially in patients with extensive colitis, hs-CRP and CAR are closely related to EA and show a higher diagnostic value compared to the related CBC parameters. The aforementioned indicators are simple and non-invasive independent markers that reflect the EA in UC.

Improving the Computer-Aided Estimation of Ulcerative Colitis Severity According to Mayo Endoscopic Score by Using Regression-Based Deep Learning.

Assessment of endoscopic activity in ulcerative colitis (UC) is important for treatment decisions and monitoring disease progress. However, substantial inter- and intraobserver variability in grading impairs the assessment. Our aim was to develop a computer-aided diagnosis system using deep learning to reduce subjectivity and improve the reliability of the assessment. The cohort comprises 11 276 images from 564 patients who underwent colonoscopy for UC. We propose a regression-based deep learning approach for the endoscopic evaluation of UC according to the Mayo endoscopic score (MES). Five state-of-the-art convolutional neural network (CNN) architectures were used for the performance measurements and comparisons. Ten-fold cross-validation was used to train the models and objectively benchmark them. Model performances were assessed using quadratic weighted kappa and macro F1 scores for full Mayo score classification and kappa statistics and F1 score for remission classification. Five classification-based CNNs used in the study were in excellent agreement with the expert annotations for all Mayo subscores and remission classification according to the kappa statistics. When the proposed regression-based approach was used, (1) the performance of most of the models statistically significantly increased and (2) the same model trained on different cross-validation folds produced more robust results on the test set in terms of deviation between different folds. Comprehensive experimental evaluations show that commonly used classification-based CNN architectures have successful performance in evaluating endoscopic disease activity of UC. Integration of domain knowledge into these architectures further increases performance and robustness, accelerating their translation into clinical use.

Time to Endorse A Sensitive Method for Scoring Endoscopic Activity of Ulcerative Colitis in Clinical Research.

The endoscopic scoring of ulcerative colitis is routinely used for both individual patient management and as an endpoint in clinical trials. The most commonly used scoring system is the Mayo endoscopic subscore, which scores endoscopic disease activity on a scale between 0 and 3. With only four possible scores and consideration of only the most involved area of the colon, the Mayo endoscopic subscore lacks sensitivity to change in measuring the totality of the endoscopic inflammatory involvement in patients with ulcerative colitis. Here, we present one case study from clinical practice and one from clinical trials in which using the Mayo endoscopic score leads to potentially incorrect conclusions. Further, in a post-hoc analysis, we re-examined endoscopic videos from a clinical trial and demonstrate that assessing involved ulcerated and affected areas on a segmental level of the colon or summing Mayo scores of colonic segments can identify improvements in endoscopic disease activity in almost twice as many subjects as identified by the Mayo endoscopic subscore alone. Although the alternative scoring systems we have used in this report will need further validation, our findings demonstrate the need for a more sensitive endoscopic scoring system in ulcerative colitis.

Gelsolin as a Potential Biomarker for Endoscopic Activity and Mucosal Healing in Ulcerative Colitis.

The therapeutic goal in ulcerative colitis is mucosal healing, which requires improved non-invasive biomarkers to evaluate disease activity. Gelsolin is associated with several autoimmune diseases, and here, we aimed to analyze its usefulness as a serological biomarker for clinical and endoscopic activities in ulcerative colitis. Patients with ulcerative colitis (n = 138) who had undergone blood tests and colonoscopy were included. Serum gelsolin was measured using enzyme-linked immunosorbent assay, and correlation between the gelsolin level and clinical and endoscopic activities was examined. The serum gelsolin level in patients with ulcerative colitis was significantly lower than that in healthy subjects, and it decreased in proportion to increasing Mayo score and Mayo endoscopic subscore. The area under the curve for correlation between clinical and endoscopic remission and serum gelsolin level was higher than that for C-reactive protein. Furthermore, in C-reactive protein-negative patients, the serum gelsolin level was lower in the active phase than in remission. Our findings indicate that the serum gelsolin level correlates with clinical and endoscopic activities in ulcerative colitis, has a higher sensitivity and specificity than C-reactive protein, and can detect mucosal healing, suggesting that gelsolin can be used as a biomarker for ulcerative colitis.

Predictive value of Milan ultrasound criteria in ulcerative colitis: A prospective observational cohort study.

BackgroundEndoscopic healing is an established treatment target for ulcerative colitis (UC). We have recently validated the Milan ultrasound criteria (MUC) to assess endoscopic activity in UC; a MUC score > 6.2 is a valid cut‐off to discriminate endoscopic activity (Mayo endoscopic subscore > 1).ObjectiveThe aim of this study was to assess the predictive value of MUC on disease course in a prospective cohort of UC patients.MethodsUC patients regardless of disease activity and current therapy, underwent colonoscopy and bowel ultrasound (US) at baseline in a blinded fashion. Correlations between baseline MUC and Mayo endoscopic subscore were assessed using Spearman's rank correlation. UC‐related negative course (defined as the need for corticosteroids, or treatment escalation, or hospitalization, or need for colectomy: a composite outcome) over a median 20 months follow‐up, was investigated using the Kaplan‐Meier method and Cox regression analysis.Results98 UC patients were followed up for a median time of 1.6 years (IQR 0.9¬2.7). Milan ultrasound criteria and Mayo endoscopic subscore significantly correlated at baseline (ρ = 0.653; p < 0.001). 70 patients (71%) had negative disease course during the follow‐up period. Milan ultrasound criteria > 6.2 at baseline was statistically significantly associated with negative disease course (HR: 3.87, 95% CI: 2.25–6.64, p < 0.001). Kaplan–Meier analyses drawed a statistically significantly lower cumulative probability of treatment escalation, need of corticosteroids, hospitalization and colectomy, among patients who had MUC ≤ 6.2 at baseline as compared to patients with MUC > 6.2 (p < 0.05 for all outcomes).Conclusionwe have demonstrated for the first time the value of bowel US and an US score in predicting disease course in UC. Milan ultrasound criteria, a validated US‐based score, predicts disease course in UC. Milan ultrasound criteria ≤ 6.2 may be the new treatment target to achieve to reduce the risk of worse outcomes.

Effect of disease duration on the association between C-reactive protein-albumin ratio and endoscopic activity in ulcerative colitis

BackgroundA simple serum biomarker for clinical outcome in patients with ulcerative colitis (UC) remains an unmet need. Some studies have shown an association between C-reactive protein (CRP)-albumin ratio (CAR) and prognosis in patients with inflammatory bowel disease (IBD), but evidence regarding the association between CAR and UC remains limited. We evaluated the association between CAR and clinical outcome in Japanese patients with UC.MethodsSubjects were 273 Japanese patients with UC. Clinical remission was defined as absence of both abnormally high stool frequency (< 3 per day) and rectal bleeding. Mucosal healing (MH) was defined as Mayo endoscopic subscore (MES) 0. Moderate to severe endoscopic activity was defined as MES 2–3. Subjects were divided according to CAR into tertiles (low, moderate, and high).ResultsThe proportions of patients with clinical remission, MH, and moderate to severe endoscopic activity were 57.9%, 26.0%, and 37.0%, respectively. High CAR was significantly positively associated with moderate to severe endoscopic activity but not MH or clinical remission after adjustment (adjusted odds ratio [OR] 2.18 [95% confidence interval (CI) (1.11–4.35)], p for trend 0.023), but only in patients with long disease duration (> 7 years) (adjusted OR 2.95 [95% CI (1.06–8.79)], p for trend 0.023). CAR was not associated with clinical remission or MH.ConclusionsCAR may be significantly positively associated with moderate to severe endoscopic activity but not clinical remission or MH in Japanese patients with UC. In patients with long UC duration, CAR might be a useful serum marker for disease activity.

Lymphocyte-to-Monocyte Ratio as a Marker for Endoscopic Activity in Ulcerative Colitis

Leukocyte subtypes can be used to evaluate the severity of ulcerative colitis (UC). In this study, we examined the relationship between the lymphocyte-to-monocyte ratio (LMR) and the Mayo endoscopic score (MES) in assessing endoscopic activity in UC. Eighty-nine samples of leukocyte subtypes and biomarkers, including fecal calprotectin (FC), the fecal immunochemical occult blood test (FIT), and C-reactive protein (CRP), from 71 patients with UC were retrospectively investigated, along with the MES. The MES was significantly correlated with the LMR, FC, the FIT, and CRP. There were significant differences in the LMR, FC, the FIT, and CRP between groups with an MES &lt; 1 and &gt;2 (p = 0.001, p = 0.003, p &lt; 0.001, and p &lt; 0.001, respectively). In the receiver operating characteristic (ROC) analysis for predicting mucosal healing (MES 0 or 1), the areas under the curve (AUCs) for the LMR, FC, the FIT, and CRP, were 0.712, 0.860, 0.908, and 0.796, respectively. In the analysis of patients without immunomodulators, the correlation of the MES with the LMR and CRP was significant. The LMR can be used to assess endoscopic activity in UC, particularly in patients without immunomodulators.