DOP59 Development of a novel Ulcerative Colitis (UC) endoscopic activity prediction model using machine learning (ML)

ABSTRACTBackgroundThe international bowel ultrasound group‐segmental activity score (IBUS‐SAS) is a validated tool with high interobserver agreement for accurately detecting disease activity in Crohn's disease (CD). Here, we addressed whether the IBUS‐SAS is also suitable to assess disease activity in ulcerative colitis (UC).MethodsThe IBUS‐SAS and Limberg scores were determined in the sigmoid colon of patients with UC. The results were correlated to established scores of clinical, endoscopic and histologic disease activity (partial [pMS] and endoscopic [eMS] Mayo‐Score, ulcerative colitis endoscopic index of severity [UCEIS], histologic Nancy index) and/or biomarkers of inflammation (C‐reactive protein [CRP], fecal calprotectin). Sensitivity, specificity, positive (PPV) and negative predictive values (NPV) for IBUS‐SAS and the Limberg score to predict endoscopic and histologic disease activity were computed by receiver operating characteristics (ROC)‐analysis.ResultsFifty‐eight patients with UC were enrolled. The median IBUS‐SAS was 34.8. It was significantly correlated with pMS, eMS, UCEIS, Nancy index, CRP and fecal calprotectin. On ROC‐analysis, a cut‐off of 15.9 was reached with 100% sensitivity and 80.0% specificity for the prediction of endoscopic activity, resulting in a PPV of 94.7% and an NPV of 100%. The Limberg score performed only slightly worse (100.0%, 60.0%, 89.9%, 100%, respectively). Comparable results were found regarding the Nancy index for sensitivity (93.9% vs. 93.9%), specificity (57.1% vs. 42.9%), PPV (91.4% vs. 88.9%) and NPV (65.7% vs. 59.0%).ConclusionsThis study highlights the potential of IUS for the non‐invasive quantification of disease activity in UC and suggests that the IBUS‐SAS should be considered as a diagnostic tool in trials and real‐world management of UC.

BackgroundImpaired intestinal epithelial barrier is highly affected in inflammatory bowel disease. Transmembrane collagens connecting the epithelial cells to the extracellular matrix have an important role in epithelial cell homeostasis. Thus, we sought to determine whether the transmembrane type 23 collagen could serve as a surrogate marker for disease activity in patients with Crohn's disease and ulcerative colitis.MethodsWe developed an enzyme‐linked immunosorbent assay to detect the ectodomain of type 23 collagen (PRO‐C23) in serum, followed by evaluation of its levels in both acute and chronic dextran sulphate sodium colitis models in rats and human inflammatory bowel disease cohorts. Serum from 44 Crohn's disease and 29 ulcerative colitis patients with active and inactive disease was included.ResultsIn the acute and chronic dextran sulphate sodium‐induced rat colitis model, the PRO‐C23 serum levels were significantly increased after colitis and returned to normal levels after disease remission. Serum levels of PRO‐C23 were elevated in Crohn's disease (p < 0.05) and ulcerative colitis (p < 0.001) patients with active disease compared to healthy donors. PRO‐C23 differentiated healthy donors from ulcerative colitis (area under the curve [AUC]: 0.81, p = 0.0009) and Crohn's disease (AUC: 0.70, p = 0.0124). PRO‐C23 differentiated ulcerative colitis patients with active disease from those in remission (AUC: 0.75, p = 0.0219) and Crohn's disease patients with active disease from those in remission (AUC: 0.68, p = 0.05).ConclusionPRO‐C23 was elevated in rats with active colitis, and inflammatory bowel disease patients with active disease. Therefore, PRO‐C23 may be used as a surrogate marker for monitoring disease activity in ulcerative colitis and Crohn's disease.

Background Intestinal ultrasound (IUS) is becoming a standard evaluation tool for ulcerative colitis (UC). Since the limited diagnostic efficacy of individual ultrasound parameters, we aimed to develop and validate a predictive model for endoscopic disease activity in ulcerative colitis based on transabdominal intestinal ultrasound in combination with biochemical indices, to improve the non-invasive standard of UC synthetically Methods This study enrolled 101 consecutive adult UC patients in the First Affiliated Hospital of Zhengzhou University from June 2022 to August 2024. Classified by Mayo endoscopic score (MES) as remission (MES = 0), mild (MES = 1), moderate (MES = 2), and severe (MES = 3). The 101 patients were split into a training set (n = 81) and a test set (n = 20), with 10% of the training set as the validation set. The neural network model was built using an MLP multi-layer perceptron (Fig. 1), and the prediction performance of the model was evaluated using accuracy, precision, recall, and AUC. Results 1. The ultrasound indicators selected for correlation analysis with MES score including bowel wall thickness (BWT), Limberg blood flow signal, blood flow velocity, resistance index, and mesenteric hypertrophy were statistically significant (p&amp;lt;0.05). 2. The laboratory indicators selected for correlation analysis with the MES score including WBC, PLT count, hemoglobin, CRP, PCT, ESR, and ALB were statistically significant (p&amp;lt;0.05). 3. Seven biochemical indices and five IUS indices that had strong correlations were selected as inputs to construct an MLP network. In the test set, the combined US-bio model was used to predict the states of remission (MES = 1), mild (MES = 2), moderate (MES = 3), and severe (MES = 4), and the AUC values were 94.7%, 93.3%, 73.3%, and 94.9% respectively. When predicting the overall disease activity, the combined model predicted the disease activity of UC patients, with an AUC of 89.1%, an accuracy of 53.2%, and a recall of 52.2% (Table 1). Conclusion The indicators of IUS and laboratory biochemical are significantly related to the disease activity of UC patients. The neural network prediction model established based on IUS indicators combined with biochemical indicators can effectively predict the disease activity of UC patients.

We aimed to determine the optimal approach to assess disease activity (i.e., biological inflammation) in ulcerative colitis (UC) by comparing patients' and physicians' rating of the disease. This was a prospective, multicenter, double-cohort study. The first cohort was composed of 94 children with UC (parent proxy when required) and their physicians who provided independent clinical report and global assessment of disease, rated on a 100 mm visual analog scale. Constructs of disease activity (including mucosal inflammation, laboratory tests, Mayo score, and the Pediatric UC Activity Index), were scored by an independent blinded physician and used to compare validity of the assessment. Of the 94 children, 43 were seen at a follow-up visit and provided a global rating of change in disease activity. To ascertain whether age influences assessment accuracy, a second cohort of 86 adult UC patients were analyzed in a similar way. In both cohorts the physician global assessment had higher correlations with all constructs of disease activity than did the patient' global assessment (for colonoscopic score r = 0.76 vs. r = 0.29, P = 0.002). Even with abdominal pain, a subjective item, the physician's rating had higher correlation than the patient's rating. Similarly, the physician rating of change better reflected change in disease activity than that of the patient rating. For indirect measurement of biological activity on the basis of symptoms and signs, clinician assessments are superior to those of patients. Patient assessments, physician assessments, and direct measurement of disease activity provide complementary information in clinical research.

1050 Which Non-Invasive Disease Activity Index Should Be Used in Ulcerative Colitis? A Systematic Head-to-Head Psychometric Comparison

Neutrophil infiltration of the intestinal mucosa correlates closely with disease activity in ulcerative colitis (UC). This study aimed to investigate the contribution of reactive oxygen species (ROS) to disease severity in UC. Sixty-four subjects were enrolled, including 35 patients with active UC (18 males, 17 females; mean age: 38.1±13.6 years) and 29 healthy controls (15 males, 14 females; mean age: 42.7±11.3 years). Clinical disease activity was classified according to the Truelove and Witts' index. Mucosal biopsy samples were analyzed for oxidative stress markers: malondialdehyde (MDA), superoxide dismutase (SOD), glutathione peroxidase (GPO) and myeloperoxidase (MPO). Patients with UC had significantly higher mucosal levels of MPO, GPO, SOD, and MDA compared to controls (p=0.0001, 0.02, 0.001, and 0.03, respectively). When stratified by disease activity, mild, moderate, and severe UC groups exhibited progressively elevated MPO and antioxidant enzyme levels relative to controls. ROC analysis demonstrated that MDA and MPO levels had moderate discriminatory power for high disease activity (AUROC=0.74 and 0.79, respectively). All oxidative markers positively correlated with disease activity index (MDA: r=0.34, p=0.006; GPO: r=0.43, p=0.0001; MPO: r=0.59, p=0.0001; SOD: r=0.43, p=0.0001). Multivariate logistic regression identified MPO and SOD as independent predictors of disease activity. Elevated levels of ROS and associated antioxidant enzymes are significantly associated with clinical disease activity in UC. These findings support the potential therapeutic value of antioxidant-based strategies in UC management.

Tim-4 expressing monocytes as a novel indicator to assess disease activity and severity of ulcerative colitis

Endoscopic assessment of mucosal disease activity is routinely used to determine eligibility and response to therapy in clinical trials of ulcerative colitis. The operating properties of the existing endoscopic scoring indices are unclear. A systematic review was undertaken to evaluate the development and operating characteristics of endoscopic scoring indices for the evaluation of ulcerative colitis. We searched MEDLINE, Embase and CENTRAL from inception to 5 July 2016. We also searched references and conference proceedings (Digestive Disease Week, United European Gastroenterology Week, European Crohn's and Colitis Organization). Any study design (e.g. randomized controlled trials, cohort studies, case series) that evaluated endoscopic indices for evaluation of ulcerative colitis disease activity were considered for inclusion. Eligible participants were adult patients (> 16 years), diagnosed with ulcerative colitis using conventional clinical, radiologic and endoscopic criteria. Two authors independently reviewed the studies identified from the literature search. These authors also independently extracted and recorded data on the number of patients enrolled; number of patients per treatment arm; patient characteristics including age and gender distribution; endoscopic index; and outcomes such as reliability (intra-rater and inter-rater), validity (content, construct, criterion), responsiveness and feasibility. Any disagreements regarding study inclusion or data extraction were resolved by discussion and consensus with a third author. Risk of bias was assessed by determining whether assessors were blinded to clinical information and whether assessors scored the endoscopic index independently. We also assessed the methodological quality of the validation studies using the COSMIN checklist MAIN RESULTS: A total of 23 reports of 20 studies met the pre-defined inclusion criteria and were included in the review. Of the 20 included validation studies, 19 endoscopic scoring indices were assessed, including the Azzolini Classification, Baron Score, Blackstone Endoscopic Interpretation, Chinese Grading System of Ulcerative Colitis, Endoscopic Activty Index, Jeroen Score, Magnifying Colonoscopy Grade, Matts Score, Mayo Clinic Endoscopic Subscore, Modified Baron Score, Modified Mayo Clinic Endoscopic Subscore, Osada Score, Rachmilewtiz Endoscopic Score, St. Mark's Index, Ulcerative Colitis Colonoscopic Index of Serverity (UCCIS), endoscopic component of the Ulcerative Colitis Disease Activity Index (UCDAI), Ulcerative Colitis Endoscopic Index of Severity (UCEIS), Witts Sigmoidoscopic Score and Watson Grade. The individuals who performed the endoscopic scoring were blinded to clinical and/or histologic information in ten of the included studies, not blinded to clinical and/or histologic information in one of the included studies, and it was unclear whether blinding occurred in the remaining nine included studies. Independent observation was confirmed in four of the included studies, unclear in five of the included studies, and non-applicable (since inter-rater reliability was not assessed) in the remaining eleven included studies. The methodological quality (COSMIN checklist) of most of the included studies was rated as 'good' or 'excellent'. One study that assessed responsiveness was rated as 'fair'. The inter-rater reliability of nine endoscopic scoring indices including the Baron Score, Blackstone Endoscopic Interpretation, Endoscopic Activity Index, Matts Score, Mayo Clinic Endoscopic Subscore, Osada Score, UCCIS, UCEIS, Watson Grade was assessed in seven studies, with estimates of correlation, ƙ, ranging from 0.44 to 0.97. The iIntra-rater reliability of seven endoscopic scoring indices including the Baron Score, Blackstone Endoscopic Interpretation, Matts Score, Mayo Clinic Endoscopic Subscore, Osada Score, UCCIS and UCEIS was assessed in three studies, with estimates of correlation, ƙ, ranging from 0.41 to 0.86. No studies assessed content validity. Three studies evaluated the criterion validity of three endoscopic scoring indices including the Rachmilewitz Endoscopic Score, Magnifying Colonoscopy Grade and the UCCIS. These indices were correlated with objective markers of disease activity including albumin, blood leukocytes, C-reactive protein, fecal calprotectin, hemoglobin, mucosal interleukin-8 concentration and platelet count. Correlation estimates ranged from r = -0.19 to 0.83. Thirteen endoscopic scoring indices were tested for construct validity in 13 studies. Estimates of correlation between the endoscopic scoring indices and other measures of disease activity ranged from r = 0.27 to 0.93. Two studies explored the responsiveness of four endoscopic scoring indices including the Mayo Endoscopic Subscore, Modified Baron Score, Modified Mayo Endoscopic Subscore and UCEIS. One study concluded that the Modified Baron Score, Modified Mayo Endoscopic Subscore and UCEIS had similar responsiveness for detecting disease change in ulcerative colitis. The other included study concluded that the UCEIS may be the most accurate endoscopic scoring tool. None of the included studies formally assessed feasibility. While the UCEIS, UCCIS and Mayo Clinic Endoscopic Subscore have undergone extensive validation, none of these instruments have been fully validated and only two studies assessed responsiveness. Further research on the operating properties of these indices is needed given the lack of a fully-validated endoscopic scoring instrument for the evaluation of disease activity in ulcerative colitis.

In active ulcerative colitis, colonic nitric oxide (NO) generation is enhanced and probably has an important role in its pathogenesis. We tested the reliability of an NO electrode in monitoring colonic NO levels in ulcerative colitis patients and control subjects and its possible usage as a marker of disease activity. Colonic NO level was determined by the NO detection system model NO-501 (InterMedical, Nagoya, Japan). The working electrode was inserted into a 7-mm diameter polyvinyl tube and introduced at a distance 6 cm from the anus. In each subject sigmoidoscopy was performed and mucosal biopsies were obtained. NO synthase (NOS) activity was determined by monitoring the conversion of 3H-arginine to citrulline. Colonic NO level is significantly increased in patients with active ulcerative or Crohn's colitis--more than 2-fold higher than in control subjects. There was good correlation between colonic NO level and NOS activity and the clinical and endoscopic indices of disease activity. Direct determination of colonic NO level is convenient, and reliable, and may help to monitor disease activity in ulcerative colitis.

Background Histological remission in ulcerative colitis (UC) is considered a therapeutic target predictive of favorable clinical outcomes. Intestinal ultrasound (IUS) represents an imaging tool that is well correlated with endoscopy and can accurately define disease activity in UC. There is a major gap in the international literature examining the potential link between activity indices on IUS and histological findings in UC1. We aimed to evaluate the correlation of the Milan Ultrasound Criteria (MUC) with Nancy Histological index (NIH) in patients with UC. Methods We performed a cross-sectional study that included consecutive patients with established diagnosis of UC. All patients underwent colonoscopy with biopsy samples, as well as IUS within 3 days of one another. Endoscopic activity was defined as an endoscopic mayo score (EMS) &amp;gt; 0, while histological activity was defined as NHI &amp;gt; 12. Active disease on IUS was calculated on the most affected bowel segment by MUC [MUC = 1.4 × Bowel wall thickness (BWT) in mm) + 2 × Bowel Wall Flow (BWF); BWF = 1 if present, or BWF = 0 if absent] 3. Activity on IUS was defined as a MUC score &amp;gt; 6.2. For maximum accuracy, the most affected bowel segments on endoscopy and IUS were matched. On the day of endoscopy, partial mayo score (PMS) was calculated (PMS &amp;gt;1 corresponded to clinical activity), and C-reactive protein (CRP) was recorded. Results A total of 45 patients were included (table 1). We observed a strong correlation between MUC and endoscopic activity [ρ: 0.802 (p&amp;lt; 0.001)], as well as between MUC, PMS and CRP [ρ: 0.743 (p&amp;lt; 0.001) and ρ: 0.798 (p&amp;lt; 0.001)] respectively. We revealed a strong correlation between MUC and NHI [ρ: 0.811 (p&amp;lt; 0.001)]. A MUC &amp;gt; 6.2 possessed 74.3% sensitivity, 90% specificity, 96.3% PPV and 50%, NPV (p&amp;lt;0.001) in predicting histological activity (Nancy&amp;gt;1). At the optimal cut-off value of 5.67, MUC displayed a sensitivity of 97.1% and a specificity of 90% [(AUC: 0.973, 95% CI: 0.918-1.000, (p&amp;lt;0.0001) – fig 1] in predicting histological activity (NHI&amp;gt;1), in patients with UC. Conclusion Intestinal ultrasound represents a promising non-invasive tool that can accurately define histological activity in patients with UC. Further studies are needed to confirm the aforementioned results.

The aim of this study was to compare in vitro release of eosinophil cationic protein (ECP) from peripheral blood eosinophils during active phases of childhood Crohn disease (CD) and ulcerative colitis with phases of remission. Ten children with CD and nine children with ulcerative colitis were investigated during 55 and 56 clinical visits, respectively. Each patient was investigated during at least one phase of clinically active disease and one phase of remission. Disease activity was assessed by means of the Paediatric Crohn Disease Activity Index (PCDAI) in Crohn disease and according to the clinical activity index of Rachmilewitz in ulcerative colitis. On an intra-individual basis, in vitro ECP release was significantly higher (P < 0.001) during active phases of CD and ulcerative colitis than in phases of remission (CD:median: 24.5 microg/l, range 16.0-61.2 versus median: 5.7 microg/l, range 2.0-16.7; ulcerative colitis: 14.8 microg/l, 8.3-39.8 versus 4.9 microg/l, 2.0-9.9). On an inte-individual basis, in CD and ulcerative colitis a strong and highly significant correlation was observed between disease activity indices and in vitro release of ECP from peripheral eosinophils (r = 0.89, P < 0.0001 and r = 0.82, P < 0.0001, respectively). These results show that in vitro ECP release from peripheral eosinophils reflects disease activity in both CD and ulcerative colitis and therefore can be used as a new appropriate laboratory parameter for assessment of disease activity in chronic inflammatory bowel disease.

Mo1603 Feasibility of the Second-Generation Colon Capsule Endoscopy in Patients With Ulcerative Colitis With a Reduced Preparation Regimen

BACKGROUND Patients with inflammatory bowel disease (IBD) report more sleep disturbances than healthy controls. Self-reported sleep disturbances have been associated with active clinical disease. Few studies have examined the relationship between self-reported sleep and endoscopic disease activity, and IBD sleep studies have yet to consider the discrepancies that exist between clinical and endoscopic disease measures. The purpose of this pilot study was to examine self-reported sleep based on endoscopic and clinical disease activity among patients with IBD. METHODS Patients with IBD were recruited from a single medical center. Patients ages 18-55 with a scheduled endoscopy were included. Patients completed informed consent, wore a wrist actigraph for 10 days, and answered baseline demographic, clinical disease activity, and sleep questionnaires including Patient-Reported Outcomes Measurement Information System (PROMIS) sleep disturbance, PROMIS sleep-related impairment, and the Pittsburg Sleep Quality Index (PSQI). For both the PROMIS and PSQI, higher scores indicate greater sleep/wake disturbances. Endoscopic disease activity (Mayo or Simple Endoscopic Score) within three months was obtained from the medical record. RESULTS The study included 27 participants with a mean age of 33.3 (SD: 8.2) years and a disease duration of 11 (SD: 7.2) years. The sample predominantly had Crohn’s disease (75%) and 61% were female. Sixty-three percent of the total sample were classified as poor sleepers based on the PSQI. When comparing self-reported sleep based on clinical disease activity, patients with active clinical disease had higher self-reported sleep disturbance (57.3 vs. 49.7, D=1.28) and sleep-related impairment (58.1 vs. 52.8, D=0.51) compared to those with inactive clinical disease. However, self-reported sleep and endoscopic disease activity had the opposite interpretation. Only 40% of patients with active endoscopic disease were poor sleepers compared to 76.5% of patients with inactive endoscopic disease. Patients with active endoscopic disease had lower self-reported sleep disturbance (49.2 vs 52.6, D=-0.53) and sleep-related impairment (49.7 vs. 56.6, D=-0.71) compared to those with inactive endoscopic disease. CONCLUSION The relationship between self-reported sleep and disease activity differs based on the measure of disease activity. Our findings of self-reported sleep disturbances and active clinical disease are similar to previous studies. However, when examining the relationship based on endoscopic disease activity, patients with active endoscopic disease had less self-reported sleep disturbance than patients with inactive endoscopic disease. Further research is needed to better characterize the relationship between sleep and disease activity, and determine the underlying mechanisms related to poor sleep in the IBD population.

In a previous study, we reported that the high mobility group (HMG) non-histone chromosomal proteins HMG1 and HMG2 were novel target antigens of P-ANCA. In this study, we determined the immunodiagnostic value of anti-HMG1/HMG2 antibodies in patients with UC. Sixty sera from patients with UC were tested for reactivity with HMG1 and HMG2 by means of ELISA. Anti-HMG1 antibody was detected in 32% of patients (40% of P-ANCA+ patients). Anti-HMG2 antibody was detected in 33% (40% of P-ANCA+ patients). Thirty-five percent of sera were positive for antibody to either HMG1 or HMG2 (43% of P-ANCA+ patients). P-ANCA+ patients expressed anti-HMG1/HMG2 antibodies with significantly greater frequency compared with P-ANCA- patients. Furthermore, the anti-HMG1/HMG2 antibodies were significantly related to disease activity in UC. Sixteen of the 18 UC patients, who had high titres of anti-HMG1 or -HMG2 antibody during the active phase, showed lower titres in the inactive phase. Anti-HMG1/HMG2 antibodies appear to be useful as a marker for disease activity in UC.

Assessment of endoscopic disease activity, as measured by various endoscopic evaluative instruments, is an essential part of quantifying disease activity in clinical trials in patients with ulcerative colitis (UC). Evaluative instruments have specific definitions and operating properties that influence the interpretation of clinical trial results. Our objective was to systematically review all endoscopic evaluative instruments that measure endoscopic disease activity in UC and to describe their definitions and operating characteristics (reliability, responsiveness, and predictive validity). We performed a systematic review of evaluative instruments assessing endoscopic disease activity in UC. MEDLINE (Ovid), EMBASE (Ovid), PubMed, the Cochrane Library (CENTRAL), and Digestive Disease Week abstracts of clinical trials were searched from inception to January 2013. In total, 5885 studies were identified and screened for inclusion criteria. Four hundred twenty-two studies involving 31 evaluative instruments were identified. Two types of indices were found, numerical scoring systems and stepwise grading scales. Both the endoscopic evaluative instrument selected and the definition chosen for mucosal healing affect the validity of assessing endoscopic disease activity during a clinical trial for UC. Currently, the sigmoidoscopic component of the Mayo Score and the ulcerative colitis endoscopic index of severity show the most promise as reliable evaluative instruments of endoscopic disease activity. However, further validation is required.