Validation of a new optical diagnosis training module to improve dysplasia characterization in inflammatory bowel disease: a multicenter international study

Post written by Marietta Iacucci, MD, PhD, FASGE, AGAF, from APC Microbiome Ireland, College of Medicine and Health, University College of Cork, Cork, Ireland.

Iacucci_photo

Patients with long-standing inflammatory bowel disease (IBD) have an increased risk of dysplastic lesions. Therefore, consensus and guidelines recommend performing regular surveillance colonoscopy using dye or virtual chromoendoscopy to enhance lesion identification and characterization.

Despite the effectiveness and widespread availability of these techniques, inflammatory changes mimicking dysplasia coupled with lack of IBD-dedicated training pose a significant challenge. With current recommendations suggesting onsite training courses led by experts, it is essential to develop and disseminate validated training reporting and ultimately improve disease management. 

In this prospective multicenter international study, an IBD-dedicated online training module—OPtical diagnosis Training to Improve dysplasia Characterization in Inflammatory Bowel Disease (OPTIC-IBD)—covering IBD surveillance, optical enhancement tools, lesion characterization, classification systems, and final self-assessment questions was developed. The study primarily aimed to evaluate the feasibility of the training module as a validated tool to improve diagnostic accuracy in IBD-associated dysplastic lesions (validation phase).

In addition, the lasting effect of the training over a minimum of 2 months was evaluated with additional randomized re-training following the post-course assessment (sustainability phase).

Among the 117 and 75 participants who completed the validation and sustainability phases, respectively, most were trainees and less experienced endoscopists. Participation in the course led to significant improvement in diagnostic accuracy for dysplasia from 70.8% (interquartile range [IQR], 58.3-79.2) to 75.0% (IQR, 64.6-79.2), particularly among less experienced endoscopists and primarily because of increased specificity (from 62.5% [IQR, 50.0-75.0] to 75.0% [IQR, 62.5-87.5]). These improvements were sustained for at least 2 months post-training in all groups except for novices and were not significantly influenced by additional training received.

Moreover, confidence in histological prediction significantly increased overall and was maintained in the post-training phase. More than 90% of participants recommended the module, especially because of its image-based teaching approach and concise and focused content.

IBD-dedicated endoscopy requires specific skills and advanced expertise to distinguish dysplastic from nondysplastic lesions and to avoid misclassification.

Although artificial intelligence tools could improve lesion characterization, they cannot replace the need for training to gather sufficient confidence in judging and relying on artificial intelligence characterization. The OPTIC-IBD module represents a step forward in training modules to be integrated into clinical practice, as optimized characterization and standardized reports derive optimized lesion management, ultimately improving patient outcomes.

Iacucci_figure

Graphical Abstract

Read the full article online.

The information presented in Endoscopedia reflects the opinions of the authors and does not represent the position of the American Society for Gastrointestinal Endoscopy (ASGE). ASGE expressly disclaims any warranties or guarantees, expressed or implied, and is not liable for damages of any kind in connection with the material, information, or procedures set forth.

Leave a Comment