Disagreement Among Gastroenterologists Using the Mayo and Rutgeerts Endoscopic Scores

Endoscopic scoring system utilization for inflammatory bowel disease activity assessment: A multicenter real-world study from Argentina

BACKGROUND

The frequency and patterns of use of scores for the assessment of endoscopic activity in inflammatory bowel disease patients are not known.

AIM

To describe the prevalence of adequate use of endoscopic scores in IBD patients who underwent colonoscopy in a real-life setting.

MATERIALS AND METHODS

A multicenter observational study comprising six community hospitals in Argentina was undertaken. Patients with a diagnosis of Crohn's disease or ulcerative colitis who underwent colonoscopy for endoscopic activity assessment between 2018 and 2022 were included. Colonoscopy reports of included subjects were manually reviewed to determine the proportion of colonoscopies that included an endoscopic score report. We determined the proportion of colonoscopy reports that included all of the IBD colonoscopy report quality elements proposed by BRIDGe group. Endoscopist's specialty, years of experience as well as expertise in IBD were assessed.

RESULTS

A total of 1556 patients were included for analysis (31.94% patients with Crohn's disease). Mean age was 45.94±15.46. Endoscopic score reporting was found in 58.41% of colonoscopies. Most frequently used scores were Mayo endoscopic score (90.56%) and SES-CD (56.03%) for ulcerative colitis and Crohn's disease, respectively. In addition, 79.11% of endoscopic reports failed to comply with all recommendations on endoscopic reporting for inflammatory bowel disease.

CONCLUSIONS

A significant proportion of endoscopic reports of inflammatory bowel disease patients do not include the description of an endoscopic score to assess mucosal inflammatory activity in a real-world setting. This is also associated with a lack of compliance in recommended criteria for proper endoscopic reporting.

The Role of Artificial Intelligence in Monitoring Inflammatory Bowel Disease-The Future Is Now

Crohn's disease and ulcerative colitis remain debilitating disorders, characterized by progressive bowel damage and possible lethal complications. The growing number of applications for artificial intelligence in gastrointestinal endoscopy has already shown great potential, especially in the field of neoplastic and pre-neoplastic lesion detection and characterization, and is currently under evaluation in the field of inflammatory bowel disease management. The application of artificial intelligence in inflammatory bowel diseases can range from genomic dataset analysis and risk prediction model construction to the disease grading severity and assessment of the response to treatment using machine learning. We aimed to assess the current and future role of artificial intelligence in assessing the key outcomes in inflammatory bowel disease patients: endoscopic activity, mucosal healing, response to treatment, and neoplasia surveillance.

A virtual chromoendoscopy artificial intelligence system to detect endoscopic and histologic activity/remission and predict clinical outcomes in ulcerative colitis

BACKGROUND

Endoscopic and histological remission (ER, HR) are therapeutic targets in ulcerative colitis (UC). Virtual chromoendoscopy (VCE) improves endoscopic assessment and the prediction of histology; however, interobserver variability limits standardized endoscopic assessment. We aimed to develop an artificial intelligence (AI) tool to distinguish ER/activity, and predict histology and risk of flare from white-light endoscopy (WLE) and VCE videos.

METHODS

1090 endoscopic videos (67 280 frames) from 283 patients were used to develop a convolutional neural network (CNN). UC endoscopic activity was graded by experts using the Ulcerative Colitis Endoscopic Index of Severity (UCEIS) and Paddington International virtual ChromoendoScopy ScOre (PICaSSO). The CNN was trained to distinguish ER/activity on endoscopy videos, and retrained to predict HR/activity, defined according to multiple indices, and predict outcome; CNN and human agreement was measured.

RESULTS

The AI system detected ER (UCEIS ≤ 1) in WLE videos with 72 % sensitivity, 87 % specificity, and an area under the receiver operating characteristic curve (AUROC) of 0.85; for detection of ER in VCE videos (PICaSSO ≤ 3), the sensitivity was 79 %, specificity 95 %, and the AUROC 0.94. The prediction of HR was similar between WLE and VCE videos (accuracies ranging from 80 % to 85 %). The model's stratification of risk of flare was similar to that of physician-assessed endoscopy scores.

CONCLUSIONS

Our system accurately distinguished ER/activity and predicted HR and clinical outcome from colonoscopy videos. This is the first computer model developed to detect inflammation/healing on VCE using the PICaSSO and the first computer tool to provide endoscopic, histologic, and clinical assessment.

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

INTRODUCTION

The evaluation of endoscopic disease severity is a crucial component in managing patients with ulcerative colitis (UC). However, endoscopic assessment suffers from substantial intraobserver and interobserver variations, limiting the reliability of individual assessments. Therefore, we aimed to develop a deep learning model capable of distinguishing active from healed mucosa and differentiating between different endoscopic disease severity degrees.

METHODS

One thousand four hundred eighty-four unique endoscopic images from 467 patients were extracted for classification. Two experts classified all images independently of one another according to the Mayo endoscopic subscore (MES). In cases of disagreement, a third expert classified the images. Different convolutional neural networks were considered for automatically classifying UC severity. Five-fold cross-validation was used to develop and select the final model. Afterward, unseen test data sets were used for model evaluation.

RESULTS

In the most challenging task-distinguishing between all categories of MES-our final model achieved a test accuracy of 0.84. When evaluating this model on the binary tasks of distinguishing MES 0 vs 1-3 and 0-1 vs 2-3, it achieved accuracies of 0.94 and 0.93 and areas under the receiver operating characteristic curves of 0.997 and 0.998, respectively.

DISCUSSION

We have developed a highly accurate, new, automated way of evaluating endoscopic images from patients with UC. We have demonstrated how our deep learning model is capable of distinguishing between all 4 MES levels of activity. This new automated approach may optimize and standardize the evaluation of disease severity measured by the MES across centers no matter the level of medical expertise.

Machine Learning Predictive Outcomes Modeling in Inflammatory Bowel Diseases

There is a rising interest in use of big data approaches to personalize treatment of inflammatory bowel diseases (IBDs) and to predict and prevent outcomes such as disease flares and therapeutic nonresponse. Machine learning (ML) provides an avenue to identify and quantify features across vast quantities of data to produce novel insights in disease management. In this review, we cover current approaches in ML-driven predictive outcomes modeling for IBD and relate how advances in other fields of medicine may be applied to improve future IBD predictive models. Numerous studies have incorporated clinical, laboratory, or omics data to predict significant outcomes in IBD, including hospitalizations, outpatient corticosteroid use, biologic response, and refractory disease after colectomy, among others, with considerable health care dollars saved as a result. Encouraging results in other fields of medicine support efforts to use ML image analysis-including analysis of histopathology, endoscopy, and radiology-to further advance outcome predictions in IBD. Though obstacles to clinical implementation include technical barriers, bias within data sets, and incongruence between limited data sets preventing model validation in larger cohorts, ML-predictive analytics have the potential to transform the clinical management of IBD. Future directions include the development of models that synthesize all aforementioned approaches to produce more robust predictive metrics.

[Position paper on endoscopic reporting in IBD]

The complete and reliable documentation of endoscopic findings make up the crucial foundation for the treatment of patients with inflammatory bowel diseases such as Crohn´s disease and ulcerative colitis. These findings are, on the one hand, a prerequisite for therapeutic decisions and, on the other hand, important as a tool for assessing the response to ongoing treatments. Endoscopic reports should, therefore, be recorded according to standardized criteria to ensure that the findings of different endoscopists can be adequately compared and that changes in the course of the disease can be traced back. In consideration of these necessities, fifteen members of the Imaging Working Group of the German Kompetenznetz Darmerkrankungen have created a position paper proposing a structure and specifications for the documentation of endoscopic exams. In addition to the formal report structure, the recommendations address a large number of attributes of acute and chronic inflammatory alterations as well as endoscopically detectable complications, which are explained in detail and illustrated using exemplary images. In addition, more frequently used endoscopic activity indices are presented and their use in everyday clinical practice is discussed.

Artificial Intelligence Enhances Studies on Inflammatory Bowel Disease

Inflammatory bowel disease (IBD), which includes ulcerative colitis (UC) and Crohn’s disease (CD), is an idiopathic condition related to a dysregulated immune response to commensal intestinal microflora in a genetically susceptible host. As a global disease, the morbidity of IBD reached a rate of 84.3 per 100,000 persons and reflected a continued gradual upward trajectory. The medical cost of IBD is also notably extremely high. For example, in Europe, it has €3,500 in CD and €2,000 in UC per patient per year, respectively. In addition, taking into account the work productivity loss and the reduced quality of life, the indirect costs are incalculable. In modern times, the diagnosis of IBD is still a subjective judgment based on laboratory tests and medical images. Its early diagnosis and intervention is therefore a challenging goal and also the key to control its progression. Artificial intelligence (AI)-assisted diagnosis and prognosis prediction has proven effective in many fields including gastroenterology. In this study, support vector machines were utilized to distinguish the significant features in IBD. As a result, the reliability of IBD diagnosis due to its impressive performance in classifying and addressing region problems was improved. Convolutional neural networks are advanced image processing algorithms that are currently in existence. Digestive endoscopic images can therefore be better understood by automatically detecting and classifying lesions. This study aims to summarize AI application in the area of IBD, objectively evaluate the performance of these methods, and ultimately understand the algorithm–dataset combination in the studies.

Comparison of the Mayo Endoscopy Score and the Ulcerative Colitis Endoscopy Index of Severity and the Ulcerative Colitis Colonoscopy Index of Severity

Background and study aims: Endoscopy plays an essential role in managing patients with ulcerative colitis (UC), as it allows us to visualize and assess the severity of the disease. As such assessments are not always objective, different scores have been devised to standardize the findings. The main aim of this study was to assess the interobserver variability between the Mayo Endoscopy Score (MES), Ulcerative Colitis Endoscopy Index of Severity (UCEIS) and Ulcerative Colitis Colonoscopy Index of Severity (UCCIS) analyzing the severity of the endoscopic lesions in patients with ulcerative colitis. Patients and methods: This was a single-cohort observational study in which a colonoscopy was carried out on patients with UC, as normal clinical practice, and a video was recorded. The results from the video were classified according to the MES, UCEIS and UCCIS by three endoscopic specialists independently, and they were compared to each other. The Mayo Endoscopy Score (MES) was used to assess the clinical situation of the patient. The therapeutic impact was analyzed after colonoscopy was carried out. Results: Sixty-seven patients were included in the study. The average age was 51 (SD ± 16.7) and the average MES was 3.07 (SD ± 2.54). The weighted Kappa index between endoscopists A and B for the MES was 0.8; between A and C 0.52; and between B and C 0.49. The intraclass correlation coefficient for UCEIS was 0.92 among the three endoscopists (CI 95 %: 0.83-0.96) and 0.96 for UCCIS among the three endoscopists (CI 95 % 0.94-0.97). A change in treatment for 34.3 % of the patients was implemented on seeing the results of the colonoscopy. Conclusions: There was an adequate, but not perfect, correlation between the different endoscopists for MES, UCEIS, UCCIS. This was higher with the last two scores. Thus, there is still some subjectivity to be minimized through special training, on assessing the seriousness of the endoscopic lesions in patients with UC.

Endoscopy and central reading in inflammatory bowel disease clinical trials: achievements, challenges and future developments

Central reading, that is, independent, off-site, blinded review or reading of imaging endpoints, has been identified as a crucial component in the conduct and analysis of inflammatory bowel disease clinical trials. Central reading is the final step in a workflow that has many parts, all of which can be improved. Furthermore, the best reading algorithm and the most intensive central reader training cannot make up for deficiencies in the acquisition stage (clinical trial endoscopy) or improve on the limitations of the underlying score (outcome instrument). In this review, academic and industry experts review scoring systems, and propose a theoretical framework for central reading that predicts when improvements in statistical power, affecting trial size and chances of success, can be expected: Multireader models can be conceptualised as statistical or non-statistical (social). Important organisational and operational factors, such as training and retraining of readers, optimal bowel preparation for colonoscopy, video quality, optimal or at least acceptable read duration times and other quality control matters, are addressed as well. The theory and practice of central reading and the conduct of endoscopy in clinical trials are interdisciplinary topics that should be of interest to many, regulators, clinical trial experts, gastroenterology societies and those in the academic community who endeavour to develop new scoring systems using traditional and machine learning approaches.

Towards an Interpretable Classifier for Characterization of Endoscopic Mayo Scores in Ulcerative Colitis Using Raman Spectroscopy

Ulcerative colitis (UC) is one of the main types of chronic inflammatory diseases that affect the bowel, but its pathogenesis is yet to be completely defined. Assessing the disease activity of UC is vital for developing a personalized treatment. Conventionally, the assessment of UC is performed by colonoscopy and histopathology. However, conventional methods fail to retain biomolecular information associated to the severity of UC and are solely based on morphological characteristics of the inflamed colon. Furthermore, assessing endoscopic disease severity is limited by the requirement for experienced human reviewers. Therefore, this work presents a nondestructive biospectroscopic technique, for example, Raman spectroscopy, for assessing endoscopic disease severity according to the four-level Mayo subscore. This contribution utilizes multidimensional Raman spectroscopic data to generate a predictive model for identifying colonic inflammation. The predictive modeling of the Raman spectroscopic data is performed using a one-dimensional deep convolutional neural network (1D-CNN). The classification results of 1D-CNN achieved a mean sensitivity of 78% and a mean specificity of 93% for the four Mayo endoscopic scores. Furthermore, the results of the 1D-CNN are interpreted by a first-order Taylor expansion, which extracts the Raman bands important for classification. Additionally, a regression model of the 1D-CNN model is constructed to study the extent of misclassification and border-line patients. The overall results of Raman spectroscopy with 1D-CNN as a classification and regression model show a good performance, and such a method can serve as a complementary method for UC analysis.

Do You See What I See? An Assessment of Endoscopic Lesions Recognition and Description by Gastroenterology Trainees and Staff Physicians

Background

Gastroenterologists should accurately describe endoscopic findings and integrate them into management plans. We aimed to determine if trainees and staff are describing inflammatory bowel disease (IBD) lesions in a similar manner.

Methods

Using 20 ileocolonoscopy images, participants described IBD inflammatory burden based on physician severity rating, and Mayo endoscopic score (MES) (ulcerative colitis [UC]) or simple endoscopic score (SES-CD) (Crohn’s disease [CD]). Images were selected based on agreement by three IBD experts. Findings of varying severity were presented; 10 images included a question about management. We examined inter-observer agreement among trainees and staff, compared trainees to staff, and determined accuracy of response comparing both groups to IBD experts.

Results

One hundred and twenty-nine staff and 47 trainees participated from across Canada. There was moderate inter-rater agreement using physician severity rating (κ = 0.53 UC and 0.52 CD for staff, κ = 0.51 UC and 0.43 CD for trainees). There was moderate inter-rater agreement for MES for staff and trainees (κ = 0.49 and 0.48, respectively), but fair agreement for SES-CD (κ = 0.37 and 0.32, respectively). For accuracy of response, the mean score was 68.7% for staff and 63.7% for trainees (P = 0.028). Both groups identified healed bowel or severe disease better than mild/moderate (P < 0.05). There was high accuracy for management, but staff scored higher than trainees for UC (P < 0.01).

Conclusion

Inter-rater agreement on description of IBD lesions was moderate at best. Staff and trainees more accurately describe healed and severe disease, and better describe lesions in UC than CD.

Significance of Linked Color Imaging for Predicting the Risk of Clinical Relapse in Ulcerative Colitis

Ulcerative colitis (UC) is a chronic inflammatory bowel disease with unknown etiology. Recently, mucosal healing has emerged as an important therapeutic endpoint in UC. Linked color imaging (LCI) is a novel endoscopic system that enhances the color differences of the gastrointestinal mucosa. Our previous study emphasized the redness and yellowness of the lesion using LCI observation, which was useful for the evaluation of histological mucosal activity in UC. In this study, we aimed to evaluate the correlation between LCI observation and clinical relapse rate in UC patients. We retrospectively analyzed UC patients who underwent total colonoscopy between August 2016 and October 2018 at our facility with Mayo endoscopic scores of 0 or 1. We assessed the correlation between orange-like color lesion (defined as LCI-scarlet color lesions) and clinical relapse rate (requiring additional treatment for UC) during the 1-year follow-up period. Fifty-eight patients (22 female, 36 male; median age at diagnosis, 47.2 (18–80) years) who underwent colonoscopy were analyzed. During the 1-year follow-up period, clinical relapse was observed in 12 patients (20.1%) among which ten patients (83.3%) had an LCI-scarlet color lesions recognized by LCI. By contrast, 29 patients (63%) had no LCI-scarlet color lesions in the clinical remission group (n = 46). There was a significant difference in LCI-scarlet color between the clinical relapse and remission groups, remaining significantly associated with clinical relapse. LCI findings, including an orange-like color lesion, have diagnostic implications for predicting the risk of clinical relapse in UC during the 1-year follow-up period.

Treat to target in inflammatory bowel disease: a survey of treatment strategies amongst Portuguese doctors

BACKGROUND

treatment goals in inflammatory bowel disease have changed over the last few years and have shifted from a mainly symptom-based management to objective endpoints, such as mucosal healing and deep remission. A treat-to-target strategy to achieve these goals has been proposed by several experts, although the real-life clinical data is still lacking. This study aimed to investigate the current practices among Portuguese gastroenterologists who treat inflammatory bowel disease patients.

METHODS

Portuguese gastroenterologists were asked to participate in an anonymous online survey. The questions focused on opinions and current practice with regard to treatment targets in inflammatory bowel disease.

RESULTS

sixty-two physicians agreed to participate in the survey, 40 were gastroenterology specialists and 22 (35.5%) were fellows. Deep remission was considered as the main treatment goal for Crohn's disease and ulcerative colitis by 82% and 83.9% of the participants, respectively. Mucosal healing as a treatment target was used by 95% and 80% of participants in ulcerative colitis and Crohn's disease, respectively; 71% intensified the treatment to achieve mucosal healing after clinical remission. The most common definition of mucosal healing in Crohn's disease and ulcerative colitis was the absence of mucosal ulceration (32.3%) and a Mayo endoscopic sub-score of 0 (41.9%). Only 3.2% escalated treatment with the aim to achieve histologic remission in ulcerative colitis.

CONCLUSION

a treat-to-target strategy to achieve mucosal healing and deep remission is currently accepted by a substantial number of Portuguese gastroenterologists.

Recent advances and emerging therapies in the non-surgical management of ulcerative colitis

The so-called “biologicals” (monoclonal antibodies to various inflammatory targets like tumor necrosis factor or integrins) have revolutionized the treatment of inflammatory bowel diseases. In ulcerative colitis, they have an established role in inducing remission in steroid-refractory disease and, thereafter, maintaining remission with or without azathioprine. Nevertheless, their limitations are also obvious: lack of primary response or loss of response during maintenance as well as various, in part severe, side effects. The latter are less frequent in anti-integrin treatment, but efficacy, especially during induction, is delayed. New antibodies as well as small molecules have also demonstrated clinical efficacy and are soon to be licensed for ulcerative colitis. None of these novel drugs seems to be much more effective overall than the competition, but they provide new options in otherwise refractory patients. This increasing complexity requires new algorithms, but it is still premature to outline each drug’s role in future treatment paradigms.