Artificial intelligence (AI) is rapidly reshaping adult cardiac surgery, enabling more accurate diagnostics, personalized risk assessment, advanced surgical planning, and proactive postoperative care. Preoperatively, deep-learning interpretation of ECGs, automated CT/MRI segmentation, and video-based echocardiography improve early disease detection and refine risk stratification beyond conventional tools such as EuroSCORE II and the STS calculator. AI-driven 3D reconstruction, virtual simulation, and augmented-reality platforms enhance planning for structural heart and aortic procedures by optimizing device selection and anticipating complications. Intraoperatively, AI augments robotic precision, stabilizes instrument motion, identifies anatomy through computer vision, and predicts hemodynamic instability via real-time waveform analytics. Integration of the Hypotension Prediction Index into perioperative pathways has already demonstrated reductions in ventilation duration and improved hemodynamic control. Postoperatively, machine-learning early-warning systems and physiologic waveform models predict acute kidney injury, low-cardiac-output syndrome, respiratory failure, and sepsis hours before clinical deterioration, while emerging closed-loop control and remote monitoring tools extend individualized management into the recovery phase. Despite these advances, current evidence is limited by retrospective study designs, heterogeneous datasets, variable transparency, and regulatory and workflow barriers. Nonetheless, rapid progress in multimodal foundation models, digital twins, hybrid OR ecosystems, and semi-autonomous robotics signals a transition toward increasingly precise, predictive, and personalized cardiac surgical care. With rigorous validation and thoughtful implementation, AI has the potential to substantially improve safety, decision-making, and outcomes across the entire cardiac surgical continuum.

Lymph node evaluation is a central determinant of oncologic quality in the surgical management of non-small-cell lung cancer (NSCLC). Accurate assessment of hilar and mediastinal lymph nodes underpins pathologic staging, informs postoperative treatment decisions, and remains essential for prognostic stratification and assessment of resection completeness. Although international guidelines provide clear recommendations, real-world data consistently demonstrate substantial variability in lymph node staging practices, with inadequate evaluation frequently observed across institutions and surgical settings. Insufficient nodal assessment, manifested as the omission of mediastinal staging, limited station sampling, or low lymph node yield, is associated with reduced nodal upstaging, inappropriate omission of adjuvant therapy, higher recurrence rates, and inferior long-term survival. Contemporary guidance from major societies, including the National Comprehensive Cancer Network, European Society of Thoracic Surgeons, International Association for the Study of Lung Cancer, and the Commission on Cancer, has increasingly converged on a station-based definition of adequacy, emphasizing systematic evaluation of both N1 and N2 nodal stations rather than reliance on absolute node counts alone. In parallel, preoperative mediastinal staging algorithms have evolved toward routine use of endobronchial and esophageal ultrasound as first-line invasive modalities, reserving surgical mediastinoscopy for selected high-risk or inconclusive cases. Evidence from randomized trials, population-level databases, and meta-analyses indicates that thorough nodal assessment improves staging accuracy and survival, while recent data support the selective use of lobe-specific or tailored lymphadenectomy in carefully staged, low-risk early disease. Finally, emerging quality improvement interventions, including standardized specimen handling, operative checklists, and multidisciplinary feedback mechanisms, have demonstrated measurable improvements in guideline adherence and patient outcomes. This narrative review integrates contemporary evidence and guideline recommendations to outline a practical framework for implementing reliable, high-quality lymph node staging in modern lung cancer surgery.

Objective: Textbook outcome (TO) is a multidimensional composite quality metric that integrates several desirable short-term outcomes into a single measure representing the “ideal” perioperative course. Unlike traditional indicators that focus narrowly on mortality or single complications, TO captures the complexity of cardiothoracic care, encompassing oncologic adequacy, absence of major complications, avoidance of reintervention and readmission, and timely discharge. Methods: In this systematic review, we synthesize evidence on the definition, incidence, determinants, prognostic impact, and limitations of TO across cardiothoracic surgery (lung and esophageal resections, lung transplantation, cardiac surgery, and adult heart transplantation) in accordance with the PRISMA guidelines. Results: Reported achievement rates range from 24% to 66% in thoracic series, 30% after Norwood palliation, 37–45% after adult heart transplantation, and 52% in a contemporary national cohort of lung transplantation, with wide between-center variability. Achieving TO is consistently associated with improved overall and disease-free survival, lower costs, and enhanced benchmarking. Determinants of failure include inadequate lymph node dissection, prolonged operative time, advanced comorbidity, pretransplant organ support, and socioeconomic disadvantage. Heterogeneity of definitions, limited incorporation of patient-reported outcomes, and equity concerns remain barriers to its successful use. Outside transplantation, benchmarking of TO in adult cardiac procedures (e.g., CABG/valve) remains limited and non-standardized. Conclusions: We argue for harmonized, procedure-specific core TO sets aligned with widely available registry fields, integration of equity-sensitive risk adjustment, and prospective validation. TO is poised to become a cornerstone metric of quality assessment and improvement in cardiothoracic surgery.

Near misses—clinical events that could have resulted in patient harm but did not—are increasingly recognized as critical yet underutilized sources of insight in surgical quality improvement. In thoracic surgery, where procedures are physiologically demanding and care pathways are highly interdependent, near misses frequently precede major complications and expose latent system vulnerabilities rather than isolated technical errors. A structured narrative review methodology was employed, including a targeted literature search of major biomedical databases and thematic synthesis of relevant studies. This narrative review synthesizes evidence from patient safety science, surgical quality literature, and thoracic surgery—specific outcomes research to examine how near misses can be systematically leveraged to improve care. We discuss the transition from individual-centered explanations of adverse events to system-based models that emphasize human factors, communication, escalation pathways, and organizational culture. Particular attention is given to contemporary quality frameworks such as failure to rescue and textbook outcome, which highlight the importance of early recognition, coordinated response, and recovery from complications rather than complication avoidance alone. We further explore the central role of psychological safety and leadership behaviors in enabling meaningful learning from near misses. By reframing near misses as actionable data rather than anecdotal “close calls,” quality improvement emerges as a core professional responsibility in thoracic surgery. We conclude that excellence in thoracic surgery should be defined not by the absence of complications, but by the capacity of surgical systems to learn, adapt, and prevent future harm.

Aortic valve disease is increasingly recognized as a chronic, progressive condition in which the initial valve intervention exerts a decisive influence on all subsequent therapeutic options. The persistence of prosthesis–patient mismatch (PPM), often driven by implantation of small surgical prostheses (≤21–23 mm), is associated with higher residual transvalvular gradients, attenuated left ventricular reverse remodeling, inferior long-term survival, and compromised outcomes following valve-in-valve (ViV) transcatheter procedures. Accumulating clinical and imaging evidence indicates that aortic annular enlargement (AAE), particularly using contemporary Y-incision and extended “roof” reconstruction techniques, can safely and reproducibly expand the annulus, sinuses of Valsalva, and sinotubular junction, thereby permitting implantation of larger prostheses and substantially reducing the risk of PPM. Insights from computational fluid dynamics further demonstrate that annular and root enlargement favorably alters postoperative flow dynamics, resulting in lower peak velocities, reduced pressure gradients, and more physiologic flow patterns in both primary surgical valve replacement and simulated ViV settings. From a lifetime management perspective, valve diameter optimization emerges as a critical determinant of both immediate hemodynamic performance and future procedural feasibility. Surgical programs that adopt a systematic approach to anatomic assessment, valve sizing strategy, PPM surveillance, and ViV preparedness may achieve meaningful improvements in short- and long-term outcomes. This review integrates anatomic, operative, hemodynamic, and quality-oriented evidence to support consideration of valve upsizing as a central principle in contemporary aortic valve replacement.

Obesity is a common and potentially modifiable barrier to heart transplant candidacy in patients supported by a durable left ventricular assist device (LVAD). Approximately 15% of LVAD recipients carry a body mass index (BMI) of 35 kg/m² or greater; the 2024 International Society for Heart and Lung Transplantation guideline considers weight loss to a BMI below 35 kg/m² reasonable before listing, within an individualized assessment, and only 18.6% of these patients achieve a 10% weight reduction through supportive care alone. Two interventions can close this gap. Anti-obesity medications, principally glucagon-like peptide-1 receptor agonists (GLP-1 RAs), reduce BMI gradually without a procedural intervention; however, the largest LVAD series reports a BMI reduction from 38.3 to 36.2 kg/m² at one year with 26% of patients who began above 35 kg/m² falling below it, and efficacy depends on continued adherence and insurance coverage. In the FIGHT trial, liraglutide showed a non-significant, numerically unfavorable signal in recently hospitalized patients with advanced heart failure with reduced ejection fraction who were not on mechanical support. Metabolic bariatric surgery, most often laparoscopic sleeve gastrectomy, delivers a BMI reduction of 6 to 10 kg/m² within 6 to 12 months and was associated with a threefold higher probability of subsequent transplantation in an observational Medicare cohort, at the cost of serious 30-day complications in 11.3% of LVAD recipients compared with 2.5% of non-LVAD bariatric patients. This narrative review compares mechanisms, LVAD-specific liabilities, and published outcomes of both strategies, including cardiovascular and arrhythmic outcomes, and reframes the choice as a trade-off between the speed of BMI reduction and the distribution of risk over time. We propose a hypothesis-generating selection framework, based on expert opinion, that considers excess BMI above threshold, expected time on device, bleeding profile, and gastrointestinal tolerance, and we define the evidence gaps that a prospective study should address.