KODA score: an updated and validated bowel preparation scale for patients undergoing small bowel capsule endoscopy

AI-KODA score application for cleanliness assessment in video capsule endoscopy frames

BACKGROUND

Currently, there is no automated method for assessing cleanliness in video capsule endoscopy (VCE). Our objectives were to automate the process of evaluating and collecting medical scores of VCE frames according to the existing KOrea-CanaDA (KODA) scoring system by developing an easy-to-use mobile application called artificial intelligence-KODA (AI-KODA) score, as well as to determine the inter-rater and intra-rater reliability of the KODA score among three readers for prospective AI applications, and check the efficacy of the application.

METHOD

From the 28 patient capsule videos considered, 1539 sequential frames were selected at five-minute intervals, and 634 random frames were selected at random intervals during small bowel transit. The frames were processed and shifted to AI-KODA. Three readers (gastroenterology fellows), who had been trained in reading VCE, rated 2173 frames in duplicate four weeks apart after completing the training module on AI-KODA. The scores were saved automatically in real time. Reliability was assessed for each video using estimate of intra-class correlation coefficients (ICCs). Then, the AI dataset was developed using the frames and their respective scores, and it was subjected to automatic classification of the scores via the random forest and the k-nearest neighbors classifiers.

RESULTS

For sequential frames, ICCs for inter-rater variability were 'excellent' to 'good' among the three readers, while ICCs for intra-rater variability were 'good' to 'moderate'. For random frames, ICCs for inter-rater and intra-rater variability were 'excellent' among the three readers. The overall accuracy achieved was up to 61% for the random forest classifier and 62.38% for the k-nearest neighbors classifier.

CONCLUSIONS

AI-KODA automates the process of scoring VCE frames based on the existing KODA score. It saves time in cleanliness assessment and is user-friendly for research and clinical use. Comprehensive benchmarking of the AI dataset is in process.

A multi-label dataset and its evaluation for automated scoring system for cleanliness assessment in video capsule endoscopy

An automated scoring system for cleanliness assessment during video capsule endoscopy (VCE) is presently lacking. The present study focused on developing an approach to automatically assess the cleanliness in VCE frames as per the latest scoring i.e., Korea-Canada (KODA). Initially, an easy-to-use mobile application called artificial intelligence-KODA (AI-KODA) score was developed to collect a multi-label image dataset of twenty-eight patient capsule videos. Three readers (gastroenterology fellows), who had been trained in reading VCE, rated this dataset in a duplicate manner. The labels were saved automatically in real-time. Inter-rater and intra-rater reliability were checked. The developed dataset was then randomly split into train:validate:test ratio of 70:20:10 and 60:20:20. It was followed by a comprehensive benchmarking and evaluation of three multi-label classification tasks using ten machine learning and two deep learning algorithms. Reliability estimation was found to be overall good among the three readers. Overall, random forest classifier achieved the best evaluation metrics, followed by Adaboost, KNeighbours, and Gaussian naive bayes in the machine learning-based classification tasks. Deep learning algorithms outperformed the machine learning-based classification tasks for only VM labels. Thorough analysis indicates that the proposed approach has the potential to save time in cleanliness assessment and is user-friendly for research and clinical use. Further research is required for the improvement of intra-rater reliability of KODA, and the development of automated multi-task classification in this field.

The Role of Endoscopy in the Diagnosis and Management of Small Bowel Pathology in Children

Small bowel evaluation has been transformed by capsule endoscopy and advances in small bowel imaging, which provide reliable and noninvasive means for assessing the mucosal surface. Device-assisted enteroscopy has been critical for histopathological confirmation and endoscopic therapy for a wide range of small bowel pathology that conventional endoscopy cannot reach. The purpose of this review is to provide a comprehensive overview of the indications, techniques, and clinical applications of capsule endoscopy; device-assisted enteroscopy; and imaging studies for small bowel evaluation in children.

Inter/Intra-Observer Agreement in Video-Capsule Endoscopy: Are We Getting It All Wrong? A Systematic Review and Meta-Analysis

Video-capsule endoscopy (VCE) reading is a time- and energy-consuming task. Agreement on findings between readers (either different or the same) is a crucial point for increasing performance and providing valid reports. The aim of this systematic review with meta-analysis is to provide an evaluation of inter/intra-observer agreement in VCE reading. A systematic literature search in PubMed, Embase and Web of Science was performed throughout September 2022. The degree of observer agreement, expressed with different test statistics, was extracted. As different statistics are not directly comparable, our analyses were stratified by type of test statistics, dividing them in groups of "None/Poor/Minimal", "Moderate/Weak/Fair", "Good/Excellent/Strong" and "Perfect/Almost perfect" to report the proportions of each. In total, 60 studies were included in the analysis, with a total of 579 comparisons. The quality of included studies, assessed with the MINORS score, was sufficient in 52/60 studies. The most common test statistics were the Kappa statistics for categorical outcomes (424 comparisons) and the intra-class correlation coefficient (ICC) for continuous outcomes (73 comparisons). In the overall comparison of inter-observer agreement, only 23% were evaluated as "good" or "perfect"; for intra-observer agreement, this was the case in 36%. Sources of heterogeneity (high, I2 81.8-98.1%) were investigated with meta-regressions, showing a possible role of country, capsule type and year of publication in Kappa inter-observer agreement. VCE reading suffers from substantial heterogeneity and sub-optimal agreement in both inter- and intra-observer evaluation. Artificial-intelligence-based tools and the adoption of a unified terminology may progressively enhance levels of agreement in VCE reading.

Capsule Endoscopy in Children

Since its clearance for use throughout the world, capsule endoscopy (CE) has become an important diagnostic tool, helping us to understand and document both normal and abnormal findings in the small intestine, especially in children, since CE usually can be employed without sedation or radiation. The indications in children and adults are similar, though their relative frequencies are different, with evaluation of potential and known inflammatory bowel disease the most common in the pediatric population, with CE also yielding increased diagnostic certainty compared to radiographic studies and surrogate biomarkers. Newer capsules now create opportunities to expand that understanding and our practices so that we can learn when and how to employ CE and pan-enteric CE to better monitor and guide therapy. It will take further studies to determine the best uses for CE and how to select the appropriate candidates, especially with ongoing concern about capsule ingestion vs. placement, the potential for capsule retention (particularly in known Crohn's disease), still elusive optimal methods for bowel cleansing, and the most meaningful scoring for research and clinical use.

A randomized controlled trial of high volume simethicone to improve visualization during capsule endoscopy

Background

The optimal dose of simethicone before capsule endoscopy is unknown. Prior studies have reported inconsistent cleansing, with some showing improved visualization only in the proximal small intestine. We hypothesized a higher volume of simethicone may improve cleansing and diagnostic yield, especially in the distal small bowel.

Methods

A phase III randomized controlled trial was conducted comparing high volume (1125 mg simethicone in 750 ml water) versus standard volume (300 mg simethicone in 200 ml water) solutions, both at 1.5 mg/ml. The primary outcome was adequate bowel preparation, defined as a KOrea-CanaDA (KODA) score >2.25, overall and stratified by the proximal and distal half of the small bowel. Secondary outcomes included mean KODA score, diagnostic yield, completion rate, and adverse events. All analyses were intention-to-treat.

Results

A total of 167 patients were randomized (mean (SD) age 58.7 (15.7), 54% female) and the most common indication was obscure gastrointestinal bleeding (71.7%). Adequate cleansing was achieved in 39 (50%) patients in the high volume group and in 39 (48%) patients in the standard volume group (RR 1.04, 95% CI 0.76–1.43, p = 0.82), with no differences observed in the proximal half (71% vs 64%, p = 0.40) or the distal half -of the small bowel (36% vs. 37%, p = 0.88). There was no differences in the mean (SD) KODA score (2.20 (0.41) vs. 2.18 (0.44), p = 0.73), diagnostic yields (53% vs. 56%, p = 0.71), or completion rates (both 95%). One adverse event, nausea, occurred in the control group.

Conclusion

High volume simethicone does not improve visualization during capsule endoscopy.

Clinical trial registration

Clinical trial:NCT02334631.