Background:Artificial intelligence (AI) has rapidly emerged as a transformative tool in gastroenterology, providing significant enhancements in diagnostic accuracy and clinical efficiency. Aim: This systematic review aims to investigate AI-based diagnostic tools utilized in gastroenterology, with a focus on their clinical integration, usability, and validation status. Materials And Methods: A comprehensive literature search was conducted using PubMed and Medline, following the PRISMA2020 flowchart. The focus was on AI-based diagnostic tools and their applications in gastroenterology over the past decade. Results: We identified and analysed 22 studies published over the past ten years that evaluated artificial intelligence (AI)–based models for diagnosis, prognostication, and quality improvement across a wide range of gastrointestinal (GI) diseases. With a few exceptions, the majority of the studies indicated that integrating AI into existing diagnostic modalities enhanced diagnostic accuracy. Conclusion: AI-based diagnostic tools demonstrate significant advancements in the detection of gastrointestinal (GI) diseases, improving accuracy across various modalities. Although the majority of studies indicate favourable performance metrics, wider clinical adoption necessitates standardized validation, multicentre trials, and enhanced transparency of the models.
Kaw et al. (Fri,) studied this question.