Eating behavior encompasses the psychological, physiological, and environmental factors influencing food intake. Dysregulation in eating behavior, such as emotional eating, binge eating, or loss of satiety signals, contributes to excessive caloric intake and weight gain. These behaviors are often linked to hormonal imbalances, stress, or genetic predisposition. Obesity is a chronic, multifactorial disease characterized by excessive body fat accumulation, with a body mass index (BMI) ≥ 30 kg/m² often used for diagnosis. It is associated with significant morbidity, including type 2 diabetes, cardiovascular disease, and obstructive sleep apnea. Pathophysiological mechanisms underlying obesity include insulin resistance, leptin dysregulation, and altered gut microbiota, which perpetuate metabolic derangements. Lifestyle interventions remain first-line treatment, but sustained weight loss is challenging for many patients. Bariatric surgery is a therapeutic option for individuals with severe obesity (BMI ≥ 40 kg/m² or ≥35 kg/m² with comorbidities) who have failed conservative management. Procedures such as Roux-en-Y gastric bypass and sleeve gastrectomy alter gastrointestinal anatomy, promoting weight loss through restriction, malabsorption, and hormonal modulation (e.g., increased GLP-1 secretion). Bariatric surgery improves obesity-related comorbidities and enhances quality of life. However, it requires lifelong medical follow-up to address potential nutritional deficiencies and ensure sustainable outcomes.

Background and Objectives: Up until now, behavioral interventions and pharmacological therapies were the main approach available for the management of obesity. Diet and exercise, when used as a singular therapeutic method, are inadequate for a successful outcome. Research shows promising results for the surgical treatment of obesity, especially in the area of bariatric surgery (BaS). The relevance of this study is the valuable analysis of the evolution of obese patients with increased cardiovascular risk. Materials and Methods: The patients eligible for BaS commonly suffer from multiple chronic conditions, including type 2 diabetes, obstructive sleep apnea, cardiovascular diseases, and non-alcoholic fatty liver disease. Additionally, obesity contributes to an increased probability of developing certain types of cancer, osteoarthritis, urinary incontinence, and chronic kidney disease. In this review, we focused especially on the cardiovascular status of obese patients who underwent bariatric procedures. Results: BaS has been found to be strongly associated with a reduced incidence of severe complications in individuals with a history of myocardial infarction (MI) and severe obesity. Specifically, this procedure is linked to a lower occurrence of major adverse cardiovascular events and a decrease in overall mortality. Also, BaS is correlated with a reduced risk of recurrent MI and the development of new-onset heart failure. Conclusions: The results of BaS involve a significant amelioration of the BMI, contributing to a considerable decrease in cardiovascular risk factors and to a notable refinement in the cardiovascular structure and function.

Artificial intelligence (AI) is having a major impact in the field of bariatric surgery (BS) as it helps improve outcomes for patients with severe obesity. This advanced technology optimises clinical decision-making processes and helps reduce the risks associated with surgery. In the context of bariatrics, AI is used to identify suitable patients, and monitor postoperative recovery but also to predict complications that may occur. BS is an effective solution for treating severe obesity, a condition characterised by the excessive accumulation of body fat, which can lead to serious health problems. However, this surgical field faces challenges in terms of patient selection and follow-up. By implementing machine learning (ML) algorithms and advanced imaging technologies, AI offers advantages to surgeons in performing interventions with increased precision and efficiency. The integration of AI into BS brings significant benefits to both patients and healthcare professionals, thereby facilitating the development of a personalised and safe approach to obesity management. Through this review, we aim to explore the potential, benefits, and risks of using AI in the context of BS.

Background: Obesity affects both physical and mental health, and bariatric patients often show high levels of psychological distress. Cardiac adipose tissue, which includes epicardial and pericardial fat, is an active fat depot linked to inflammation and cardiovascular risk. Its relationship with anxiety has not been well studied, especially in bariatric candidates. Methods: This cross‑sectional study included 29 adults undergoing preoperative evaluation for bariatric surgery. All participants completed the Hamilton Anxiety Rating Scale and underwent CT imaging to measure epicardial and pericardial adipose tissue thickness. Additional adiposity measures included BMI, waist circumference, abdominal wall thickness, and adipose tissue density. Correlations and simple linear regressions were used to examine associations between anxiety severity and adiposity markers. Group differences across obesity grades were assessed with one‑way ANOVA. Results: Higher anxiety scores were strongly associated with greater pericardial fat thickness (r = 0.621, p < 0.001), epicardial fat thickness (r = 0.667, p < 0.001), BMI (r = 0.840, p < 0.001), waist circumference (r = 0.748, p < 0.001), and abdominal wall thickness (r = 0.494, p = 0.007). Both pericardial and epicardial fat thickness significantly predicted Hamilton total score in regression models. Conclusion: Anxiety severity in bariatric patients is closely related to several markers of adiposity, especially cardiac adipose tissue thickness. These findings suggest that cardiac adipose tissue may play a meaningful role in the psychological profile of individuals with severe obesity. Integrating both biological and psychological factors may improve the assessment and care of bariatric candidates.Artificial intelligence, especially deep learning techniques, is starting to play an increasingly important role in the assessment of epicardial and pericardial adipose tissue. It allows for automated segmentation and quantification based on CT images, providing high accuracy and reducing the time required for data processing. Recent artificial intelligence models, such as convolutional neural networks and U-Net architectures, have demonstrated significant agreement with manual measurements performed by specialists, which supports the possibility of their integration into routine clinical assessment. In the case of bariatric patients, these technologies can increase the accuracy of cardiac adipose tissue assessment and facilitate a broader understanding of the relationship between obesity, cardiovascular risk and the associated psychological impact.