Artificial intelligence in inflammatory bowel disease: implications for clinical practice and future directions

Abstract

biochemical investigations. [3][4][5] Endoscopic evaluation defines the location and pattern of inflammation (e.g., segmental or continuous, mild or severe) and can also identify noninflammatory pathology (e.g., dysplasia). 3 Endoscopic and histologic improve ments correlate with better outcomes and are treatment targets in the management of IBD. 6,7 Using an inflammatory pathway-based approach to inform treatment decisions may be more useful than classifying disease by organ involvement alone. 8 The complexity of IBD management lends itself to artificial intelligence (AI) as a means of improving clinical practice (Fig. 1). 3 Comprised of machine learning, deep learning, and neural networks, AI can help optimize IBD diagnosis, refine assessment of macroscopic and microscopic disease severity, and improve disease monitoring. [9][10][11]

Potential Oral Microbial Markers for Differential Diagnosis of Crohn’s Disease and Ulcerative Colitis Using Machine Learning Models

“…ML has found applications in various domains, including healthcare. In the context of IBD diagnosis, ML techniques can be utilized with diverse data sources, such as endoscopic images, histopathology slides, blood tests, fecal biomarkers, and electronic health records [ 29 ]. The gut microbiome, in particular, holds great promise as a valuable data source for ML-based approaches in IBD.…”

Could histologic healing be a new treatment target in patients with ulcerative colitis?

“…The added value of histologic healing over endoscopic healing in predicting prognosis, such as long-term remission [ 7 , 8 ], as well as for cancer prevention [ 9 ], has been well demonstrated in UC [ 10 ]. Histologic remission is a desirable therapeutic goal to prevent long-term complications [ 2 ].…”

“…Nevertheless, histologic healing is not a feasible treatment target in all patients. Obtaining a mucosal biopsy requires subjective decisions on biopsy location; moreover, the optimal number of specimens is unclear, interpretation of the findings by pathologists is often delayed, and the biopsy itself is invasive and costly [ 10 ]. Consequently, the risks and benefits must be carefully weighed.…”

“…Consequently, the risks and benefits must be carefully weighed. In addition, the lack of standardized reporting protocols limits the clinical utility of histological remission [ 2 , 10 ]. With continuing advances in computer-aided diagnostic systems that predict histologic activity, there will be less need for biopsies and therefore also for the opinion of expert pathologists, which will reduce costs.…”

“…With continuing advances in computer-aided diagnostic systems that predict histologic activity, there will be less need for biopsies and therefore also for the opinion of expert pathologists, which will reduce costs. These systems will also facilitate the establishment of reproducible and standardized reporting methods [ 10 , 11 ]. In the meantime, further large-scale, multi-center, long-term studies are necessary to develop a standardized histological remission assessment system and to determine the benefits of histologic healing relative to the risks and costs.…”