Ulcerative Colitis Endoscopic Index Research Articles

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

Endoscopic assessment of ulcerative colitis (UC) can be performed by Mayo Endoscopic Score (MES), or the Ulcerative Colitis Endoscopic Index of Severity (UCEIS). In this meta-analysis, we assessed the pooled diagnostic accuracy parameters of deep machine learning, by means of convolutional neural network (CNN) algorithms, in predicting UC severity on endoscopic images. Databases including Medline, Scopus, and Embase, were searched in June 2022. Outcomes of interest were the pooled accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Standard meta-analysis methods were employed using the random-effects model, and heterogeneity was assessed using the I2statistics. Twelve studies were included in the final analysis. The pooled diagnostic parameters of CNN-based machine learning algorithms in endoscopic severity assessment of UC were: Accuracy 91.5% (95% confidence interval (CI) [88.3-93.8],I2=84%), sensitivity 82.8% ([78.3-86.5],I2=89%), specificity 92.4% ([89.4-94.6],I2=84%), PPV 86.6% ([82.3-90],I2=89%) and NPV 88.6% ([85.7-91],I2=78%). Subgroup analysis revealed significantly better sensitivity and PPV with UCEIS scoring system as compared to MES (93.6% [87.5-96.8],I2=77% vs 82% [75.6-87],I2=89%, p=0.003; and 93.6% [88.7-96.4],I2=68% vs 83.6% [76.8-88.8],I2=77%; p=0.007, respectively). CNN-based machine learning algorithms demonstrated excellent pooled diagnostic accuracy parameters in the endoscopic severity assessment of UC. Utilizing UCEIS scores in CNN training might offer better results than MES. Further studies are warranted to establish these findings in real-life.

Peripheral Blood DNA Methylation Signatures and Response to Tofacitinib in Moderate-to-severe Ulcerative Colitis.

Predictive biomarkers for treatment efficacy of ulcerative colitis [UC] treatments are lacking. Here, we performed a longitudinal study investigating the association and potential predictive power of genome-wide peripheral blood [PB] DNA methylation signatures and response to tofacitinib treatment in UC. We recruited moderate-to-severe UC patients starting tofacitinib treatment, and measured PB DNA methylation profiles at baseline [T1], after 8 weeks [T2], and in a subset [n = 8] after a median of 20 weeks [T3] using the Illumina Infinium HumanMethylation EPIC BeadChip. After 8 weeks, we distinguished responders [R] from non-responders [NR] based on a centrally read endoscopic response [decrease in endoscopic Mayo score ≥1 or Ulcerative Colitis Endoscopic Index of Severity ≥2] combined with corticosteroid-free clinical and/or biochemical response. T1 PB samples were used for biomarker identification, and T2 and publicly available intraclass correlation [ICC] data were used for stability analyses. RNA-sequencing was performed to understand the downstream effects of the predictor CpG loci. In total, 16 R and 15 NR patients, with a median disease duration of 7 [4-12] years and overall comparable patient characteristics at baseline, were analysed. We identified a panel of 53 differentially methylated positions [DMPs] associated with response to tofacitinib [AUROC 0.74]. Most DMPs [77%] demonstrated both short- and long-term hyperstability [ICC ≥0.90], irrespective of inflammatory status. Gene expression analysis showed lower FGFR2 [pBH = 0.011] and LRPAP1 [pBH = 0.020], and higher OR2L13 [pBH = 0.016] expression at T1 in R compared with NR. Our observations demonstrate the utility of genome-wide PB DNA methylation signatures to predict response to tofacitinib.

Value of Improved Mayo Endoscopic Score for evaluating treatment efficacy for active ulcerative colitis

To assess the value of Improved Mayo Endoscopic Score (IMES) for evaluation of treatment efficacy for active ulcerative colitis (UC). We retrospectively analyzed the clinical and endoscopic data of 103 patients diagnosed with active UC in Beijing Tsinghua Changgung Hospital from January, 2015 to December, 2020. The severity of endoscopic lesions was determined by Mayo Endoscopic Score and the Ulcerative Colitis Endoscopic Index of Severity (UCEIS), and the area of the endoscopic lesions was evaluated based on the Montreal classification system. The IMES was established by combining the MES with the Montreal classification. Univariate analysis suggested that young patients (<40 years old), patients with extensive disease type (E3), patients with high endoscopic scores (MES=3, UCEIS>4, and IMES>4), and patients receiving advanced drug therapy (with systemic hormones, immunosuppressants, immunomodulators, and biological agents, etc.) had lower clinical and endoscopic remission rates. COX survival analysis showed that IMES≤4 was an independent risk factor for clinical and endoscopic remission. ROC curve indicated that the predictive value of IMSE≤4 for clinical and endoscopic remission (AUC=0.7793 and 0.7095, respectively; P<0.01) was better than that of Montreal (AUC=0.7357 and 0.6847, respectively; P<0.01), MES=2 (AUC=0.6671 and 0.5929, respectively; P<0.01), and UCEIS≤4 (AUC=0.6823 and 0.6459, respectively; P<0.01); IMES=5 had a better predictive value for patients with active UC undergoing colectomy tham E3 and MES=3. IMES has good value in evaluating treatment efficacy for active UC.

Clinical significance of the noninvasive mucosal inflammation index for assessing the endoscopic activity of Crohn’s disease in children

Introduction. The use of non-invasive methods for examining patients with endoscopic remission can be useful in identifying the need for endoscopic interventions and assessing disease activity over time.&#x0D; Materials and methods. We analyzed two hundred thirty two medical histories of children with Crohn’s disease (CD) who were examined and treated at the National Medical Research Center for Children’s Health. The relationship between the CD simple endoscopic score (SES-CD) and the newly developed mucosal inflammation noninvasive index (MINI) was determined. Similarly, data from 80 children with ulcerative colitis were examined to identify correlations between the ulcerative colitis endoscopic index of severity (UCEIS) and MINI.&#x0D; Results. Among all forms of Crohn’s disease, a direct strong correlation was found between MINI and SES-CD (R = 0.81, &#x0D; p &lt; 0.001). A MINI value &gt; 5 indicated the absence of mucosal healing (SES-CD &gt; 2 points) with a sensitivity of 73% and a specificity of 84%, and a MINI value ≥13 predicted high activity of Crohn’s disease (SES-CD ≥ 16 points) with sensitivity and specificity of 79% and 88%, respectively. The correlation between MINI and UCEIS in patients with ulcerative colitis revealed an average relationship, which requires further modification of the index in accordance with the characteristics of the course of the disease.&#x0D; Conclusion. The newly developed MINI is a simple and intuitive tool for assessing mucosal inflammation in CD children.

Correlations Between Gastrointestinal Symptoms and Endoscopic-Histologic Disease Activity in Adults with Ulcerative Colitis.

Discordance between gastrointestinal (GI) symptoms and endoscopic inflammation in patients with ulcerative colitis (UC) is known. However, the correlations between symptoms and endoscopic and histologic (endo-histologic) mucosal healing and remains unknown. We performed a secondary analysis of prospectively collected clinical, endoscopic, and histologic data on 254 colonoscopies from 179 unique adults at a tertiary referral center from 2014 to 2021. Spearman's rank was used to assess the correlation between patient reported outcomes and objective assessments of disease activity, as measured by validated instruments: Two-item patient-reported outcome measure (PRO-2) for stool frequency and rectal bleeding, the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) for endoscopic inflammation, and the Geboes score for histologic inflammation. The predictive value of objective assessments of inflammation and clinical symptoms was described using sensitivity, specificity, and positive/negative predictive value. One-quarter (28%, 72/254) of cases were in endo-histologic remission; of these, 25% (18/72) report GI symptoms (22% diarrhea; 6% rectal bleeding). Endo-histologically active disease had higher sensitivity (95% rectal bleeding; 87% diarrhea) and negative predictive value (94% rectal bleeding, 78% diarrhea) for clinically active disease compared to active disease on endoscopic (77%) or histologic assessment only (80%). The specificity of endo/histologic inflammation for GI symptoms was < 65%. PRO-2 was positively correlated with endoscopic disease activity (Spearman's rank 0.57, 95% CI 0.54-0.60, p < 0.0001) and histologic disease activity (Spearman's rank 0.49, 0.45-0.53, p < 0.0001). One-quarter of patients with ulcerative colitis in endo-histologic (deep) remission have gastrointestinal symptoms, more commonly with diarrhea than rectal bleeding. Endo-histologic inflammation has high sensitivity (≥ 87%) for diarrhea/rectal bleeding.

Bedside Intestinal Ultrasound Predicts Disease Severity and the Disease Distribution of Pediatric Patients With Inflammatory Bowel Disease: A Pilot Cross-sectional Study.

Intestinal ultrasound (IUS) is a noninvasive tool to assess bowel inflammation. There is a paucity of data on its accuracy in pediatric patients. The aim of this study is to evaluate the diagnostic performance of bowel wall thickness (BWT) measured using IUS compared with endoscopic disease activity in children suspected of having inflammatory bowel disease (IBD). We conducted a single-center cross-sectional pilot study of pediatric patients suspected to have previously undiagnosed IBD. Endoscopic inflammation was graded using segmental scores of the Simple Endoscopic Score for Crohn's Disease (SES-CD) and the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and classified as having healthy, mild, or moderate/severe disease activity. Association between BWT and endoscopic severity was assessed using the Kruskal-Wallis test. The diagnostic performance of BWT to detect active disease at endoscopy was evaluated using the area under the receiver operating characteristic curve; sensitivity and specificity were calculated. In all, 174 bowel segments in 33 children were assessed by IUS and ileocolonoscopy. An elevated median BWT was associated with increased bowel segment disease severity, classified by the SES-CD (P < .001) and the UCEIS (P < .01). Using a cutoff value of 1.9 mm, we found that the BWT had an area under the receiver operating characteristic curve of 0.743 (95% CI, 0.67-0.82), a sensitivity of 64% (95% CI, 53%-73%), and a specificity of 76% (95% CI, 65%-85%) to detect inflamed bowel. Increasing BWT is associated with increasing endoscopic activity in pediatric IBD. Our study suggests that the optimal BWT cutoff value for detecting active disease may be less than that seen in adults. Additional pediatric studies are needed.

Composite Assessment Using Intestinal Ultrasound and Calprotectin Is Accurate in Predicting Histological Activity in Ulcerative Colitis: A Cohort Study.

Beyond endoscopic remission, histological remission in ulcerative colitis (UC) is predictive of clinical outcomes. Intestinal ultrasound (IUS) may offer a noninvasive surrogate marker for histological activity; however, there are limited data correlating validated ultrasound and histological indices. Our aim was to determine the correlation of IUS activity in UC with a validated histological activity index. Twenty-nine prospective, paired, same-day IUS/endoscopy/histology/fecal calprotectin (FC) cases were included. Intestinal ultrasound activity was determined using the Milan Ultrasound Criteria, histological activity using the Nancy Histological Index, endoscopic activity using Mayo endoscopic subscore and Ulcerative Colitis Endoscopic Index of Severity, and clinical activity using the Simple Clinical Colitis Activity Score. Histological activity demonstrated a significant linear association with overall IUS activity (coefficient 0.14; 95% CI, 0.03-0.25; P = .011). Intestinal ultrasound activity was also significantly associated with endoscopic activity (0.32; 95% CI, 0.14-0.49; P < 0.001), total Mayo score (0.31; 95% CI, 0.02-0.60; P = .036) but not FC (0.10; 95% CI, -0.01 to 0.21; P = .064) or clinical disease activity (0.04; 95% CI, -0.21 to 0.28; P = .768). A composite of IUS and FC showed the greatest association (1.31; 95% CI, 0.43-2.18; P = .003) and accurately predicted histological activity in 88% of cases (P = .007), with sensitivity of 88%, specificity 80%, positive predictive value 95%, and negative predictive value 57%. Intestinal ultrasound is an accurate noninvasive marker of histological disease activity in UC, the accuracy of which is further enhanced when used in composite with FC. This can reduce the need for colonoscopy in routine care by supporting accurate point-of-care decision-making in patients with UC.

Artificial Intelligence Enabled Histological Prediction of Remission or Activity and Clinical Outcomes in Ulcerative Colitis

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

Comparison of The Toronto IBD Global Endoscopic Reporting (TIGER) score, Mayo endoscopic score (MES), and ulcerative colitis endoscopic index of severity (UCEIS) in predicting the need for ileal pouch–anal anastomosis in patients with ulcerative colitis

Total proctocolectomy (TPC) with ileal pouch-anal anastomosis (IPAA) has been accepted as a radical surgery for refractory ulcerative colitis (UC). We aimed to assess the predictive value of several novel and widely used endoscopic core systems, The Toronto IBD Global Endoscopic Reporting (TIGER) score, Mayo endoscopic score (MES), and ulcerative colitis endoscopic index of severity (UCEIS) in guiding the need for IPAA. Data on patients with UC from June 1986 and June 2022 at our institute were collected. The endoscopic evaluation was recorded according to the first colonoscopy after hospitalization. Primary outcome was the need for IPAA during admission and follow-up. A total of 313 patients with a median follow-up time and a median TIGER score of 12.0years (interquartile range (IQR): 6.0-17.0) and 212.0 (IQR: 7.0-327.0) were enrolled. IPAA was conducted in 110 (35.1%) patients, which significantly improved the long-term quality of life. TIGER score had the biggest area under the receiver-operating characteristic curve of 0.810 with a sensitivity of 75.0% and specificity of 87.1% at the cut-off value of 315 (p < 0.001). TIGER score ≥ 315 was an independent risk factor with the highest odds ratio for the need for IPAA and associated with the shortest IPAA-free survival time compared with UCEIS and MES. TIGER score was superior to UCEIS and MES in predicting the need for IPAA. For colorectal surgeons, three or more segments with moderate-to-severe endoscopic activity should be considered as a threshold value for decision-making for IPAA.

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.

P368 The presence of extra-intestinal manifestations is associated with poor prognosis in acute severe ulcerative colitis: A KASID multicenter study

Abstract Background Many patients with inflammatory bowel disease experience extra-intestinal manifestations (EIM)s. The presence of EIMs is related to disease activity. Acute severe ulcerative colitis (ASUC) is associated with a high inflammatory burden. However, there are insufficient studies on the relation between the presence of EIMs and the prognosis of exacerbation of ulcerative colitis. This study was conducted to elucidate the correlation between EIMs and ASUC. Methods We retrospectively included patients who were hospitalized at four tertiary medical centers for ASUC management between January 2015 to December 2020, and data on the underlying disease, disease activity, EIMs, colectomy, treatment method, and readmission due to ulcerative colitis aggravation were checked. Results A total of 145 patients (mean age 44.4 years, 68 women) were investigated. The initial partial Mayo score, the Mayo endoscopy sub-score, and the ulcerative colitis endoscopic severity index were 7.6±0.8%, 2.7±0.5, and 6.0±1.4%, respectively. EIMs were expressed in a total of 10.3% (15/145) of patients. The most common type of EIMs was the peripheral articular type (46.7%) followed by skin lesions (20%) and axial articular disease (13.3%). The group with EIMs was younger and had a higher proportion of women than the group without EIMs (39.4 versus 45 years, p=0.03), and had a longer duration of disease (5.8 versus 3.5 years, p=0.02). The Mayo endoscopic sub-score (2.9 vs. 2.7, p&amp;lt;0.01) and partial endoscopic score (7.9 vs. 7.6, p&amp;lt;0.01) were also higher in the EIMs group. The length of hospital stay was also longer in the EIMs group (25.5 days vs. 13.8 days, p&amp;lt;0.01). The response rate to initial treatment was lower in the EIMs group (71.4% vs. 95.5%, p&amp;lt;0.01), and more rescue therapy (28.6% vs. 4.5%, p&amp;lt;0.01) was performed. The rate of colectomy on admission was also higher in the group with EIMs (13.3% vs. 0.8%, p&amp;lt;0.01). Patients with EIMs showed a high tendency to visit the hospital for re-exacerbation of ulcerative colitis after discharge (p=0.07, HR 2.10 CI: 0.93 – 4.76). Conclusion EIMs were expressed in a total of 10.3% of patients with ASUC. The presence of EIMs suggested a poor prognosis in ASUC.

P290 Development of an artificial intelligence model using stool pictures for predicting endoscopic mucosal inflammation in patients with Ulcerative Colitis; KASID multicenter study

Abstract Background Disease monitoring through objective measures including fecal calprotectin and endoscopy is crucial for the management of ulcerative colitis (UC). The role of stool pictures taken by smart phones in the disease monitoring of UC is not known. We aimed to develop artificial intelligence (AI) model using stool pictures for predicting endoscopic mucosal inflammation in patients with UC. Methods This was a prospective multicenter study conducted in 6 tertiary referral hospitals. Patients scheduled to undergo endoscopy for monitoring of mucosal inflammation were included in the study. They were asked to send their stool photos taken at the toilet using smartphones within ± 5 days from the day of endoscopy. Endoscopic activity was assessed with Ulcerative Colitis Endoscopic Index of Severity (UCEIS). 80% and 20% of total data were randomly selected as training and validation set, respectively and this process repeated 4 times on different iterations for cross-validation. Accuracy of AI model for predicting endoscopic healing was compared with that of fecal calprotectin (Fcal). Results A total of 2463 stool pictures from 293 patients with UC were collected (mean age, year, 44±15.2; female, 108 (36.9%)). Endoscopic healing was found in 165 patients (56.3%). In validation set, the mean area under the receiver operating characteristic (AUROC) for predicting endoscopic activity using AI model was 0.78±0.02 (p=0.001) which was not statistically different from the AUROC of Fcal (0.81±0.08, p=0.01; AI model vs. Fcal p&amp;gt;0.05). When we excluded rectal sparing cases (20, 6.8%), the mean AUROC of AI model increased to 0.85±0.05 (p=0.0007). Accuracy, sensitivity and specificity of AI model for predicting endoscopic activity in all patients and without rectal sparing cases were 0.739, 0.643, and 0.826, and 0.798, 0.711, and 0.872, respectively. Conclusion Stool photos of UC patients with deep learning technology demonstrated similar accuracy to Fcal in speculating endoscopic activity with better accuracy in patients without rectal sparing. The potential of simple stool pictures as a possible monitoring tool for UC activity is hopefully presented in this study.

P908 Faecal Microbiota Transplantation refurbishes the crypt-associated microbiota in Ulcerative colitis

Abstract Background Intestinal crypts form a pristine gut biogeographical niche, homing the intestinal stem cells and being the closest neighbors to underlying lamina propria. Initially believed to be sterile, the crypt lumen was recently shown to inhabit a conserved microbial population. However, the identity of the crypt-associated microbiota (CAM) remains elusive. The present study is among the first to illustrate the CAM composition in health and its deviation during ulcerative colitis (UC), and the effect of faecal microbiota transplantation along with an anti-inflammatory diet (FMT-AID) on the structure of this community. Methods Recto-sigmoidal biopsies from controls, and from patients with mild-moderate UC before and after FMT-AID (n=26), were subjected to methacarn-fixation, followed by paraffin-embedding, sectioning and laser-capture microdissection-assisted crypt isolation. DNA isolated from micro-dissected samples was subjected to 16S rRNA gene sequencing. The bacterial presence in colonic crypts was confirmed using fluorescence in-situ hybridization(FISH). Microbiome data analysis was carried out by using QIIME2 and R packages. Results FISH performed using pan-bacterial probes revealed the presence of sparse microbial clusters in colonic crypts, distinct from the overlying layer of Mucosa-associated microbiota (MAM), in both controls as well as in UC(Fig.1a and 1b). While MAM is dominated by members of phyla Firmicutes (45%) and Bacteroidetes (26%),CAM is comprised predominantly of aerobic members of Actinobacteria(54%) and Proteobacteria(38%), followed by minor proportions of Firmicutes(4%), Acidobacteria and Cyanobacteria (2% each). The significant members of CAM included aerobic genera -Cutibacterium(35%),Sphingobium(13%), Paracoccus(11%), Micrococcus(3%), Lawsonella(3%), Rothia(2%), Prauserella(2%), Kocuria, Corynebacterium, Acinetobacter and Brevundimonas (1% each)(Fig.1c and 1d). Analysis of CAM diversity in controls, and in patients with UC before and after FMT-AID, showed no significant alterations in the α- and β diversity matrices(Fig.1e and 1f).CAM demonstrated UC-associated dysbiosis of specific taxa which was restored after FMT-AID(Fig.2a and 2b). These FMT-restored CAM taxa correlated negatively with disease-associated parameters - Fecal calprotectin (FCP), Simple Clinical Colitis Activity Index (SCCAI) and Ulcerative Colitis Endoscopic Index of Severity (UCEIS)(Fig.2c and 2d). The positive effects of FMT-AID further refurbished the CAM-MAM interaction networks, which were obliterated in UC.(Fig.2e) Conclusion A gut bacterial community, enriched in aerobic bacteria, resides in the colonic crypts, and undergoes taxa-level alterations during UC and in response to FMT.

P618 Long-term real-world data of Ustekinumab in Ulcerative Colitis – the Stockholm Ustekinumab study – STOCUSTE

Abstract Background Background: Ustekinumab (UST) is an anti-interleukin-12/23 antibody in the treatment of inflammatory bowel disease (IBD), mainly used in patients failing anti-TNF-agents. The STOCUSTE study includes patients treated at four hospitals in Stockholm to provide long-term real-world data. Methods Methods: This was a retrospective study including patients diagnosed with ulcerative colitis and treated with UST between years 2016 and 2021. The patients were followed from start of UST until withdrawal of treatment for any reason, or until end of study follow-up, July 31, 2021.We assessed disease activity; Physician Global Assessment (PGA); Ulcerative Colitis Endoscopic Index of Severity (UCEIS) score, laboratory parameters and drug persistence. The primary outcome was remission (PGA = 0) and response (decrease PGA ≥ 1 from baseline) at 3 and 12 months, respectively. Results Results: 96 patients, 44 women and 52 men were included. The patients had either extensive colitis (68%), left-sided colitis (29%) or proctitis (3%). All but two patients were anti-TNF-experienced; 94 (98%) had failed ≥1, 59 (61%) ≥2 and 34 (35%) ≥3 anti-TNF-drugs. At inclusion 92 patients (96%) had active disease and 4 patients were in remission, 48 (50%) were on oral or topical corticosteroids, 13 (14%) had thiopurines. At 12 months only 9% were on oral or topical corticosteroids. Among patients who were treated with UST, 9/71 (6%) were in remission at 3 months, and 26/33 (78%) patients were in remission at 12 months. Withdrawal from treatment during the first 12 months was 36 (38 %), mainly due to persisting disease activity (20%); 8% were withdrawn due to adverse events, 2% needed bowel surgery, and 2% were lost to follow up. Conclusion Conclusions: In this group of difficult-to-treat patients with ulcerative colitis, Ust was shown to be effective in the majority, with high drug persistence at 12 months in combination with a favorable safety profile.

P321 Increased modified DUBLIN scores are associated with serious ulcerative colitis and treatment failure

Abstract Background Grading of endoscopic lesions is important for determining the severity of ulcerative colitis and developing treatment strategies, but the commonly used methods are not sufficient.This study aimed to investigate whether new endoscopic scoring systems incorporating lesions and disease extent are associated with clinical disease severity and maintainable remission. Methods This was a retrospective study. One hundred and ten patients with ulcerative colitis were included and eighty seven completed 12 months follow-up.Colonoscopy was performed within 1week before blood samples were taken. DUBLIN (Degree of ulcerative colitis burden of luminal inflammation) scores were calculated as the product of MES (Mayo endoscopic score) by disease extent and UCEIS (ulcerative colitis endoscopic index of severity) was used to replace MES when calculating modified DUBLIN scores. Results DUBLIN and modified DUBLIN scores were increased in the moderate and severe groups significantly (p&amp;lt;0.05). Both of increased scores contributed to the detection of serious diseases, and the clinical cut-off values of DUBLIN and modified DUBLIN were 3(AUC=0.809, p=0.001) and 7(AUC=0.815, p=0.001). They were with high sensitivity, but the specificity of DUBLIN was lower. Both scores were correlated to partial Mayo scores, CPR and ESR positively, and they were correlated to the albumin negatively (p&amp;lt;0.05). Higher modified DUBLIN scores (&amp;gt;7) were associated with an increase risk of treatment failure (HR=4.96, 95% CI 1.17-21.00, p=0.03), but there were no association between DUBLIN scores and long term remission (p&amp;gt;0.05). Conclusion Increased DUBLIN and modified DUBLIN scores were conducive to screening serious disease, but only modified DUBLIN scores had the potential to assist in making an upgraded therapeutic schedule.

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.

P247 Oncostatin M and its receptor are markers of endoscopic and histological disease activity in Inflammatory Bowel Disease

Abstract Background Oncostatin M (OSM) and its receptor (OSMR) have been associated with active disease in patients with inflammatory bowel disease (IBD). This study compared the expression of OSM and OSMR in intestinal tissue according to clinical, endoscopic, and histological disease activity. Methods A multi-centre IBD database containing RNA-sequencing datasets, was used to analyse OSM and OSMR expression in ileal and/or colonic tissue, expressed as transcripts per million (TPM). Clinical scoring systems included the Harvey Bradshaw Index for Crohn’s disease (CD) and partial Mayo score for ulcerative colitis (UC). Endoscopic scoring systems included the simple endoscopic score for CD (SES-CD) and UC endoscopic index of severity (UCEIS). Histological scoring included the modified Naini and Cortina, and Riley scores. Graphs were presented in log transformed TPM+1 values. Results 155 patients (108 CD, 47 UC) and 38 controls were included. For IBD patients, 49% were men, median age was 35 years and intestinal tissue was collected at endoscopy (73%) and surgery (27%). Compared to controls, patients with CD and UC had significantly elevated median expression of OSM (0.08, 0.29 and 0.34 TPM respectively) and OSMR (1.21, 1.69 and 3.53 TPM respectively). OSMR expression was higher in UC patients than CD (p&amp;lt;0.001). There was no difference in OSM or OSMR between Harvey Bradshaw Index categories (0-4 vs 5-7 vs 8-16) or partial Mayo scores (0 vs 1-3 vs 4-7). Endoscopically, OSM was higher for SES-CD scores of 16-51 (1.11 TPM), compared to SES-CD scores of 0-3 (0.14 TPM, p=0.003) and controls (0.08 TPM, p&amp;lt;0.0001). Median OSMR increased non-significantly with increasing SES-CD scores (score 0-3: 1.59 TPM; score 4-15: 1.90 TPM; score 16-51: 2.04 TPM). There was no difference in OSM and OSMR expression between UCEIS scores, but the most severe disease (UCEIS score 5-8) had higher expression than controls for both OSM (3.92 vs 0.08 TPM, p&amp;lt;0.001) and OSMR (6.10 vs 1.21 TPM, p&amp;lt;0.0001). Increasing expression of OSM and OSMR was found with increasing histological scores, see Figure. Using the modified Naini and Cortina score for CD, OSM and OSMR were most expressed in the highest scores compared to the lowest scores (OSM: 1.48 vs 0.09 TPM, p&amp;lt;0.001; OSMR: 5.50 vs 1.27 TPM, p=0.003). For the modified Riley score for UC, both OSM and OSMR were also able to differentiate between the highest and lowest score groups (OSM: 3.14 vs 0.12 TPM, p=0.0001; OSMR: 6.61 vs 1.58 TPM, p&amp;lt;0.0001). Conclusion This study showed that OSM and OSMR expression in intestinal tissue is associated with inflammation both histologically and endoscopically. Further investigations are needed to confirm our observations and explore the OSM pathway’s relevance in intestinal inflammation.

DOP73 Predicting endoscopic improvement in Ulcerative Colitis using the Ulcerative Colitis Severity Index (UCSI)

Abstract Background Scoring indices used in clinical trials for moderate-severe ulcerative colitis (UC) may lack specificity as a prognostic tool. We developed and internally validated a prognostic scoring index for UC patients on therapy that considers baseline patient-reported outcomes, biomarkers, endoscopy, and histology for achieving one-year endoscopic improvement (EI). Methods This post-hoc analysis of the UNIFI clinical trial (ClinicalTrials.gov identifier: NCT02407236) included 644 patients treated with ustekinumab induction therapy. Data were randomly split into 70% training and 30% testing cohorts. Baseline variables were assessed in multivariate analyses and variables with p &amp;lt;0.05 were assigned weights according to their relative prognostic value for predicting one-year EI (Mayo endoscopic score (MES) ≤1). A cut-off was obtained by calculating the maximum Youden index and validated in the testing cohort. Results Prior biologic failure, albumin &amp;lt; 40 g/L, CRP &amp;gt; 5mg/L, Mayo stool frequency (SF) subscore, endoscopic erosions/ulcerations based on the UC Endoscopic Index of Severity, and histologic structural/architectural changes demonstrated significant associations with one-year EI and included in the final model. The Ulcerative Colitis Severity Index (UCSI) was generated (Table 1) and the median UCSI score among all participants was 10.4 (IQR 7-14.4, range: 2.2-20), which had acceptable discriminative ability for one-year EI in the training [AUC: 0.78 (95% CI: 0.70-0.86)] and testing cohort [AUC: 0.76 (95% CI: 0.68-0.85)] (Table 2). Compared to the UCSI, the Mayo score demonstrated poor accuracy [AUC: 0.49 (95% CI: 0.40-0.58)] for predicting one-year EI (p=0.0006). The UCSI also predicted one-year endoscopic healing (MES of 0), clinical remission (total Mayo score ≤2 and no subscore &amp;gt;1), partial Mayo score (PMS) remission (PMS &amp;lt; 2), and PRO-2 remission (SF and rectal bleeding subscore of 0) with significantly greater accuracy compared to the Mayo score. Similar findings were observed when the UCSI was compared with the adapted Mayo score. The maximum Youden index corresponded to a cut-off of 10. Participants with a UCSI ≥10 had a lower probability of one-year EI [27/104 (26%) vs. 40/76 (52.6%)]. Performance characteristics are detailed in Tables 3 and 4. Conclusion The UCSI is an internally validated prognostic scoring tool that accurately predicts one-year EI at baseline among patients with moderate-to-severe UC on active therapy. The UCSI demonstrated greater accuracy for one-year EI, EH, and clinical remission compared to the total and adapted Mayo score. The UCSI could improve disease management in UC by stratifying patients based on their predicted likelihood of long-term outcomes.

MULTIPLE ENVIRONMENTAL AND SOCIAL DETERMINANTS OF HEALTH FACTORS WERE NOT ASSOCIATED WITH THE GASTROINTESTINAL SYMPTOMATIC BURDEN OF ULCERATIVE COLITIS WITH MUCOSAL HEALING

Abstract INTRODUCTION In a biopsychosocial interdisciplinary model, complex interactions between the hosts (individuals/patients), disease (e.g., ulcerative colitis [UC]), and environment (e.g., social determinants of health [SDOH]) may all contribute to the disease burden. Whether SDOH contributes to the symptomatic burden of UC in deep remission is unclear. METHODS We performed a secondary analysis on prospectively collected data from adults with UC enrolled in the biobank at a tertiary referral center in southern California from 2014-2021. Standardized clinical (unweighted two-item patient-reported outcome [PRO-2] for stool frequency [SF] and rectal bleeding [RB]; remission=SF0/RB0), endoscopic (Ulcerative Colitis Endoscopic Index of Severity [UCEIS]; remission UCEIS=0), and histologic (Geboes score; remission &amp;lt;2B.0) disease activity assessments were performed within 30 days of a colonoscopy (case) with segmental colonic biopsies. SDOH were assessed using the California Healthy Places Index (SDOH Index), a publicly available zip code-based system that ranks SDOH domain and subdomain scores from the least to most healthy (0-100 percentile) using weighted z-scores. Patients without SDOH scores (e.g., reside outside of California; n=88 cases) were excluded. We used χ2-square and Wilcoxon-Mann Whitney tests to investigate for associations between SDOH factors (non-parametric, independent variables dichotomized as below vs above the median) and cardinal GI symptoms (continuous unweighted PRO-2 symptomatic severity and dichotomized clinical remission/active disease), patient-, and disease-related factors. In adults with UC in endoscopic or endo-histologic remission, we used univariate logistic regression to assess the risk of health disadvantage (SDOH score below median) and the presence of GI symptoms. RESULTS Of the 166 UC cases, 46% (76/166), 38% (63/166), and 30% (49/166) were in clinical, endoscopic, and endo-histologic remission, respectively. Approximately one-fifth of cases (21%, 35/166) had SDOH scores below the state median. However, health disadvantage (below SDOH index median) was not associated with clinical, endoscopic, or endo-histologic disease activity; and neither were IBD duration; gender or race/ethnicity (all p&amp;gt;0.05) (Tab 1). Approximately one-third of cases had active GI symptoms despite endoscopic (32%, 20/63) and endo-histologic remission (29%, 14/49). However, none of the eight investigated SDOH domains were associated with increased risks for GI symptoms when UC had objective mucosal healing on colonoscopy (Tab 2) CONCLUSION Although one-third of adults with mucosal healing of UC report GI symptoms (diarrhea/rectal bleeding), there was no association with multiple social determinants of health factors (e.g., education, neighborhood, economic, social, and environmental) in this secondary analysis of a prospective cohort.

Clinical Background Factors as Predictors of the Efficacy of 5-Aminosalicylic Acid Suppositories in Patients with Ulcerative Colitis

Introduction: Although the efficacy of 5-aminosalicylic acid (ASA) suppositories for ulcerative colitis (UC) has been reported in many studies, many studies have also described poor adherence to 5-ASA suppository regimens. We aimed to identify the clinical background factors that influence adherence to 5-ASA suppositories to improve adherence and efficacy of the treatment. Methods: We conducted a retrospective cohort study of 61 patients with active UC who were using 5-ASA suppositories. All patients underwent endoscopy and rectal biopsy for histological diagnosis prior to 5-ASA suppository treatment. The efficacy of 5-ASA suppository treatment was compared in relation to clinical background factors (sex, age, disease duration, disease type, clinical activity, Ulcerative Colitis Endoscopic Index of Severity, histological activity, serum C-reactive protein level, concomitant use of immunomodulators, history of steroid use, and dose of oral 5-ASA). Results: The efficacy of 5-ASA suppositories was significantly related to low Lichtiger Colitis Activity Index (LCAI) scores and proctitis type prior to its use. In terms of sex, females tended to show higher efficacy. Multivariate logistic regression analysis using these three factors showed high predictive value for the efficacy of 5-ASA suppositories (AUC, 0.788; sensitivity, 87.2%; and specificity, 63.7%). Conclusion: This study is the first to extract clinical background factors for predicting the efficacy of 5-ASA suppositories. The use of 5-ASA suppositories in patients who are expected to show efficacy will be effective in improving patient co-operation.