Abstract
Artificial intelligence (AI) is increasingly influencing the field of endo-bariatrics by bringing greater precision, personalization, and efficiency to the management of obesity and metabolic diseases. This chapter examines how AI can be integrated across endoscopic bariatric and metabolic therapies (EBMTs from patient selection, to pre-procedure planning, intra-op support, and long-term follow-up. Traditionally, EBMT outcomes have often depended on the operator’s experience, which can lead to variability in results and a lack of standardized practice. AI technologies such as machine learning, deep learning, computer vision, and predictive analytics can help overcome these limitations by enabling more data-driven decisions, automatic recognition of anatomical structures, and real-time procedural support. In the pre-procedure stage, AI can assist with advanced imaging analysis, volumetric assessment, and simulation models that help clinicians plan individualized treatment strategies. During procedures, AI-assisted visualization systems, robotic support, depth sensing, and predictive tools for complications may improve procedural safety and consistency. Post-procedure, AI-enabled mobile applications and wearable device can allow continuous monitoring of patients, provide behavioral guidance, and help detect complications at an early stage, and improve long-term outcomes. Aditionally, AI may also improve workflow efficiency, reduce costs, standardize training, and help expand access to EBMTs. However, wider use of AI in endo-bariatrics faces several challenges such as concerns about data bias, lack of transparency, medico-legal responsibility, and unequal global access. Therefore, careful evaluation of AI systems is essential for safe implementation. AI has the potential to shift endo-bariatrics from a largely technique-dependent field to a more predictive, data-driven, and precision-based discipline.

This publication has 64 references indexed in Scilit: