European Journal of Biomedical and Pharmaceutical Sciences

MACHINE LEARNING IN THE CLASSIFICATION OF IRRITABLE BOWEL SYNDROME SUBTYPES: A SYSTEMATIC REVIEW

Ome Valentina Akpughe, Damola John Akinmoladun, Azka Ali*, Tania M. Cobena Bravo, Maryfortune Ugoeze Chilaka, Roshan Goswami, Prince Agbakahi, Nkechi Enemuo, Amarachi Adaeze Uzoma, Akpevwoghene Victor Erhiano, Efe Okunzuwa, Shwetha Gopal, Victor Chiedozie Ezeamii, Godswill Nwadiei and Jovita Oge Echere

ABSTRACT

Background: Irritable Bowel Syndrome (IBS) is a common gastrointestinal disorder characterized by chronic abdominal pain and altered bowel habits. Due to the heterogeneity in clinical presentations and pathophysiological mechanisms, accurate diagnosis and subtype classification of IBS present significant challenges. Recent advancements in machine learning (ML) and artificial intelligence (AI) have opened up new avenues for improving diagnostic accuracy and disease classification. This systematic review aimed to critically appraise and summarize the recent literature on the use of ML in the diagnosis and subtype classification of IBS. Methods: We conducted a comprehensive literature search of PubMed, Scopus, and Web of Science, focusing on research published within the last twenty years. The studies were screened, and data were extracted systematically. We included original research studies that applied AI and ML approaches in diagnosing and classifying IBS. Results: Our review synthesized 10 studies, each exploring a different aspect of ML applications, including clinical symptoms, bowel sound features, and microbiome profiles. The findings showed significant potential for ML in IBS diagnosis and subtype differentiation. Several studies showed promising results with high diagnostic accuracy, exceeding 90% in some cases, demonstrating the potential of ML models in non-invasively differentiating IBS from other gastrointestinal disorders and identifying IBS subtypes accurately. Conclusion: Despite promising results, challenges persist. Most studies were based on small sample sizes and lacked external validation, underlining the need for further robust and extensive research. However, this systematic review showcases the potential of ML in the evolving landscape of IBS diagnosis and subtype classification and highlights areas for future research.

Keywords: Irritable Bowel Syndrome; Machine Learning; Artificial Intelligence; Diagnosis; Subtype Classification; Systematic Review; Gastrointestinal Disorders.