Introduction. Inflammatory bowel diseases (IBD), including Crohn's disease (CD) and ulcerative colitis (UC), are chronic immune-inflammatory pathologies of the gastrointestinal tract. This study focuses on the role of artificial intelligence (AI) in the morphological diagnosis of IBD, endoscopic visualization, outcome prediction, and patient monitoring. Aim: To summarize data on the application of AI methods in the diagnosis and treatment of IBD, including digital image analysis, remission prediction, inflammation activity evaluation, and the automation of histological and endoscopic assessment processes. Materials and methods. Modern studies on the use of machine learning (ML) and deep learning (DL) technologies in the diagnosis of IBD were analyzed. Special attention was paid to histological image processing methods, neural network algorithms for inflammation staging, and the use of AI for real-time endoscopic visualization. Results. AI technologies provide more accurate and objective determination of histological inflammation activity using Geboes, Nancy, and Robarts indices. Deep neural networks (CNN) enable automatic classification of inflammation stages and the detection of residual inflammation, which is critical for preventing relapses and reducing colorectal cancer risk. Endocytoscopy and real-time visualization algorithms improve the accuracy of early detection of mucosal dysplasia. Neural networks and other ML algorithms demonstrate high sensitivity and specificity in distinguishing CD from UC and assessing histological remission. Conclusion. AI is becoming an integral part of IBD diagnostics, enhancing the accuracy of morphological studies, optimizing endoscopic methods, and reducing error rates. Integrating AI into clinical practice expands treatment possibilities, including personalized approaches and long-term patient monitoring.