Search

Purpose: This review aims to explore the clinical and research applications of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in understanding, predicting, and managing obesity. It assesses the use of AI tools to identify obesity-related risk factors, predict outcomes, personalize treatments, and improve healthcare interventions for obesity. Methods: A comprehensive literature search was conducted using PubMed and Google Scholar, with keywords including "artificial intelligence", "machine learning", "deep learning", "obesity", "obesity management", and related terms. Studies focusing on AI's role in obesity research, management, and therapeutic interventions were reviewed, including observational studies, systematic reviews, and clinical applications. Results: This review identifies numerous AI-driven models, such as ML and DL, used in obesity prediction, patient stratification, and personalized management strategies. Applications of AI in obesity research include risk prediction, early detection, and individualization of treatment plans. AI has facilitated the development of predictive models utilizing various data sources, such as genetic, epigenetic, and clinical data. However, AI models vary in effectiveness, influenced by dataset type, research goals, and model interpretability. Performance metrics such as accuracy, precision, recall, and F1-score were evaluated to optimize model selection. Conclusions: AI offers promising advancements in obesity management, enabling more personalized and efficient care. While technology presents considerable potential, challenges such as data quality, ethical considerations, and technical requirements remain. Addressing these will be essential to fully harness AI's potential in obesity research and treatment, supporting a shift toward precision healthcare.

Background: The choice of prosthesis for aortic valve replacement (AVR) remains challenging. The risk of anticoagulation complications vs. the risk of aortic valve reintervention should be weighed. This study compared the outcomes of bioprosthetic vs. mechanical AVR in patients older and younger than 50., Methods: This retrospective study was conducted from 2009 to 2019 and involved 292 adult patients who underwent isolated AVR. The patients were divided according to their age (above 50 years or 50 years and younger) and the type of valves used in each age group. The outcomes of bioprosthetic valves (Groups 1a (>50 years) and 1b (≤50 years)) were compared with those of mechanical valves (Groups 2a (>50 years) and 2b (≤50 years)) in each age group., Results: The groups had nearly equal rates of preexisting comorbidities except for Group 1b, in which the rate of hypertension was greater (32.6% vs. 14.7%; p = 0.025). This group also had higher rates of old stroke (8.7% vs. 0%, p = 0.011) and higher creatinine clearance (127.62 (108.82-150.23) vs. 110.02 (84.87-144.49) mL/min; p = 0.026) than Group 1b. Patients in Group 1a were significantly older than Group 2a (64 (58-71) vs. 58 (54-67) years; p = 0.002). There was no significant difference in the NYHA class between the groups. The preoperative ejection fraction and other echocardiographic parameters did not differ significantly between the groups. Re-exploration for bleeding was more common in patients older than 50 years who underwent mechanical valve replacement ( p = 0.021). There was no difference in other postoperative complications between the groups. The groups had no differences in survival, stroke, or bleeding rates. Aortic valve reintervention was significantly greater in patients ≤ 50 years old with bioprosthetic valves. There were no differences between groups in the changes in left ventricular mass, ejection fraction, or peak aortic valve pressure during the 5-year follow-up., Conclusions: The outcomes of mechanical and bioprosthetic valve replacement were comparable in patients older than 50 years. Using bioprosthetic valves in patients younger than 50 years was associated with a greater rate of valve reintervention, with no beneficial effect on the risk of bleeding or stroke.

Background: New-onset postoperative atrial fibrillation (PoAF) is one of the most frequent yet serious complications following cardiac surgery. Long-term consequences have not been thoroughly investigated, and studies have included different cardiac operations. The objectives were to report the incidence and short- and long-term outcomes in patients with PoAF after mitral valve surgery., Methods: This is a retrospective cohort study of 1401 patients who underwent mitral valve surgery from 2009 to 2020. Patients were grouped according to the occurrence of PoAF ( n = 236) and the nonoccurrence of PoAF ( n = 1165). Long-term outcomes included mortality, heart failure rehospitalization, stroke, and mitral valve reinterventions., Results: The overall incidence of PoAF was 16.8%. PoAF was associated with higher rates of operative mortality (8.9% vs. 3.3%, p < 0.001), stroke (6.9% vs. 1.5%, p < 0.001), and dialysis (13.6% vs. 3.5%, p < 0.001). ICU and hospital stays were significantly longer in patients with PoAF ( p < 0.001 for both). PoAF was significantly associated with an increased risk of mortality [HR: 1.613 (95% CI: 1.048-2.483); p = 0.03], heart failure rehospitalization [HR: 2.156 (95% CI: 1.276-3.642); p = 0.004], and stroke [HR: 2.722 (95% CI: 1.321-5.607); p = 0.007]. However, PoAF was not associated with increased mitral valve reinterventions [HR: 0.938 (95% CI: 0.422-2.087); p = 0.875]., Conclusions: Atrial fibrillation after mitral valve surgery is a common complication, with an increased risk of operative mortality. PoAF was associated with lower long-term survival, increased heart failure rehospitalization, and stroke risk. Future studies are needed to evaluate strategies that can be implemented to improve the outcomes of these patients.

Background: It is unclear whether peripheral arterial cannulation is superior to central arterial cannulation for postcardiotomy veno-arterial extracorporeal membrane oxygenation (VA-ECMO)., Methods: A systematic review was conducted using PubMed, Scopus, and Google Scholar to identify studies on postcardiotomy VA-ECMO for the present individual patient data (IPD) meta-analysis. Analysis was performed according to the intention-to-treat principle., Results: The investigators of 10 studies agreed to participate in the present IPD meta-analysis. Overall, 1269 patients were included in the analysis. Crude rates of in-hospital mortality after central versus peripheral arterial cannulation for VA-ECMO were 70.7% vs. 63.7%, respectively (adjusted OR 1.38, 95% CI 1.08-1.75). Propensity score matching yielded 538 pairs of patients with balanced baseline characteristics and operative variables. Among these matched cohorts, central arterial cannulation VA-ECMO was associated with significantly higher in-hospital mortality compared to peripheral arterial cannulation VA-ECMO (64.5% vs. 70.8%, p = 0.027). These findings were confirmed by aggregate data meta-analysis, which showed that central arterial cannulation was associated with an increased risk of in-hospital mortality compared to peripheral arterial cannulation (OR 1.35, 95% CI 1.04-1.76, I 2 21%)., Conclusions: Among patients requiring postcardiotomy VA-ECMO, central arterial cannulation was associated with an increased risk of in-hospital mortality compared to peripheral arterial cannulation. This increased risk is of limited magnitude, and further studies are needed to confirm the present findings and to identify the mechanisms underlying the potential beneficial effects of peripheral VA-ECMO.