The impact of artificial intelligence algorithms on management of patients with irritable bowel syndrome: A systematic review

Abstract

Introduction: Distinguishing Irritable Bowel Syndrome (IBS) from other diseases is one of the most difficult tasks for gastroenterologists. Because IBS symptoms overlap with those of another disease, these obstacles can misdiagnose and impose significant socioeconomic burdens on society. As a result of Artificial Intelligence's (AI) considerable potential, it can be suggested that these issues be improved or eliminated. AI enables machines to simulate human thought and reasoning processes. Thus, these machines can exhibit appropriate responses and reasoning to resolve complex situations problems. Therefore, AI can play a significant role in predicting, diagnosing, and managing IBS. However, no systematic review has been conducted in this field. To this end, the purpose of our paper was to determine the AI algorithms' applications in IBS. Methods: A systematic review was conducted by searching major databases, such as Web of Science, PubMed, and Scopus, for studies written in English that discussed the application of AI algorithms in IBS up to November 8, 2021. We incorporated a variety of keywords, including ''artificial intelligence'' and ''irritable bowel syndrome.'' Two expert authors evaluated articles independently, and any disagreements were resolved with the assistance of a third reviewer. This review included eligible studies that met the inclusion criteria. Results: Initially, 508 articles from databases and six studies from the gray literature search were returned. After eliminating duplicates, screening studies, and considering inclusion and exclusion criteria, 20 studies were selected for the final review. The conducted studies indicate that AI techniques can aid in IBS screening and diagnosis, as well as patient classification and overall IBS management and treatment. Additionally, we found that support vector machine (SVM) demonstrated significantly higher specificity (100%), and random forest demonstrated significantly higher accuracy (98.5%) than other algorithms. Conclusions: According to articles, utilizing AI algorithms for predicting, diagnosing, and managing IBS is cost-effective and can be incorporated into health service organizations' strategic planning as an effective strategy for improving the quality of diagnosis and management of this disease.

Keywords

• Irritable bowel syndrome
• Artificial intelligence
• Diagnosis
• Treatment
• Management