The global demand for cosmetic procedures is accelerating, with over 1.6 million aesthetic surgical procedures performed in the US in 2023. Concurrently, AI is transforming surgical practice through advanced analytics, predictive modeling, and computer vision. Cosmetic surgery, characterized by subjective outcomes and limited standardized metrics, presents a unique opportunity for AI integration to enhance precision, objectivity, and patient communication. Following PRISMA 2020 guidelines, we systematically searched MEDLINE/PubMed, Embase, and the Cochrane Library (January 2020−July 2025) for studies applying AI, machine learning, deep learning, computer vision, or large language models to cosmetic or aesthetic procedures. Eligible designs included randomized controlled trials, observational studies, diagnostic accuracy studies, feasibility studies, and prediction model development. Two reviewers independently screened titles/abstracts, assessed full texts, extracted data, and evaluated risk of bias using ROBINS-I for non-randomized studies. Of 3941 records, 38 met the inclusion criteria. AI applications spanned preoperative planning (predictive risk modeling, 3D outcome simulation), intraoperative guidance (augmented reality overlays), and postoperative monitoring (smartphone-based complication detection, objective aesthetic scoring). Benefits included improved patient–surgeon communication, enhanced risk stratification, and standardized outcome measurement. However, most studies were early-phase, with limited external validation, heterogeneous datasets, and inconsistent outcome metrics. Risk of bias was moderate to serious in most studies. AI in cosmetic surgery shows significant potential but remains in early clinical adoption. Progress requires multicenter validation, standardized datasets, explainable algorithms, and clear regulatory frameworks. Large language model—driven tools may accelerate development and integration, provided ethical, equitable, and patient-centered principles guide implementation.

Background and Objectives: Metabolic and bariatric surgery is the most effective long-term intervention for severe obesity, associated with significant reductions in weight, associated medical problems, and cancer risk. While the overall safety profile of metabolic and bariatric surgery has improved, early postoperative complications still occur and may lead to prolonged hospitalization, reintervention, or increased morbidity. This study aimed to identify independent preoperative and perioperative predictors of early postoperative complications following metabolic and bariatric surgery. Materials and Methods: We conducted a retrospective cohort study of 927 patients who underwent metabolic and bariatric surgery at a single tertiary medical center between December 2017 and March 2022. Early postoperative complications, defined as those occurring during the index hospitalization or within 90 days, were recorded and graded using the Clavien-Dindo classification. Univariate analyses were performed to identify candidate predictors, followed by multivariable logistic regression using an unpenalized model. Odds ratios (ORs) and corresponding 95% confidence intervals (CIs) were estimated using maximum likelihood methods with Wald-based intervals. Results: Eighty-four patients (9.1%) experienced postoperative complications, with 38% requiring invasive intervention. Bleeding was the most common complication (46%), followed by leak/intra-abdominal abscess (24%) and cardiorespiratory events (18%). Independent predictors of complications included obstructive sleep apnea (OR: 1.93), bariatric surgery within the past 5 years (OR: 2.39). Conclusions: OSA and recent previous surgery increase the risk of early complications after metabolic and bariatric surgery. These findings support integrating specific risk factors into preoperative planning to improve surgical outcomes.

To evaluate the impact of high and low Body mass index (BMI) on 90-day postoperative outcomes in patients with Crohn's disease (CD). This retrospective cohort study (2017-2019) included 271 patients undergoing abdominal surgery, categorized as underweight (BMI 30). Primary outcomes were 90-day overall and severe (Clavien-Dindo >2) complications and total length of stay (LOS). The cohort comprised 64 underweight, 189 normal/overweight, and 18 obese patients. Multivariable analysis revealed that underweight status was independently associated with higher overall complications (OR = 2.0, p = 0.045), severe complications (OR = 3.05, p = 0.018), and increased total LOS (beta = 3.43, p = 0.003). While obesity showed a trend toward higher morbidity in univariable analysis, it did not maintain independent significance after adjustment (p = 0.159). Underweight status is a significant independent predictor of poor 90-day postoperative outcomes in patients with CD, necessitating targeted preoperative nutritional optimization.