AI-Based Predictive Modelling for Post-Surgical Complications in Bariatric Surgery
DOI:
https://doi.org/10.64149/J.Carcinog.24.6s.762-773Keywords:
Artificial Intelligence (AI); bariatric surgery; predictive modelling; post-surgical complications; machine learning (ML); deep learning (DL); risk stratification; clinical decision support; precision medicine; secondary researchAbstract
Obesity is one of the greatest health problems in the world, and bariatric surgery has arisen as the best way of maintaining the normal weight and metabolism. Nevertheless, anastomotic leaks, infections, and pulmonary embolism are also significant clinical issues after the surgical procedure. The conventional risk assessment instruments are not usually strong enough to consider the multifactorial and dynamic nature of such complications. The proposed research explores the usage of Artificial Intelligence (AI)-based predictive modelling in detecting and preventing post-surgical complications in bariatric surgery using a secondary descriptive research design. Based on peer-reviewed articles and 2015 to 2025 datasets, in the analysis, AI algorithms such as Random Forests, Support Vector Machines, and Neural Networks, outperform traditional scoring systems. The results indicate that AI models can combine complicated clinical, demographic, and biochemical data and enhance accuracy and early complication detection to promote personalized care and efficient resource allocation. Although some issues such as interpretability of data and insufficient multicentre validation currently exist, AI-based predictive models demonstrate great promise in improving the safety of surgery, postoperative outcomes, and promoting precision medicine in bariatric surgery.
