Quan Wang, Yaowei Dai, Alberto Aiolfi, Marco Manna, Aldo Ricioppo, Xiaonan Liu, Vincenzo Pezzi, Nicola Leone, Luigi Bonavina
Surgical management of gastroesophageal reflux disease (GERD) is limited by non-technical challenges, including variability in patient selection, incomplete physiological assessment, imprecise procedure choice, and heterogeneity of intraoperative judgment. Artificial intelligence (AI) offers a promising approach to address these limitations. To enhance decision reproducibility and explainability, we advocate for the integration of AI models based on machine learning with formal logic-based reasoning. This neuro-symbolic approach enables the formal encoding of clinical knowledge, the management of incomplete or conflicting evidence, and the generation of transparent, rule-based recommendations. In the context of antireflux surgery, such hybrid methods are expected to improve decision-making for patient selection and procedure tailoring, and to assist intraoperative quality control for precise hernia repair and optimal wrap configuration. By combining data-driven AI perception with transparent logic, there is the potential to enhance patient’s safety, allow physiology-informed individualized treatment, reduce inter-surgeon variability, and provide better postoperative outcomes.