Search Results (37)

Contemporary intensive care operates in an environment with high-complexity cases, large volumes of information, and vast physiological, biological, and therapeutic data, collected from laboratory results, investigations, and therapies for organ support, as well as from systems that operate in parallel. The lack of interoperability contributes to information overload, alarm fatigue, and delayed decision-making. The Smart ICU concept has been developed to address these limitations by integrating medical devices, information systems, and artificial intelligence into a unified system that allows interoperable data integration and predictive analytics. Aim: The purpose of this article is to provide a narrative review of the Smart ICU concept, with a specific focus on the cardiac intensive care unit. It summarizes Smart ICU architecture, data integration, clinical support, and applicability in monitoring perioperative inflammation in cardiac surgery. We describe the Smart ICU architecture, from data acquisition to storage and analytics, highlighting the differences between Smart ICU, artificial intelligence, and Tele-ICU, and we underline predictive analytics as a supportive tool, as well as its influence on clinical outcomes. Cardiac ICU application: Cardiac ICUs offer a data-dense, temporally well-defined model following cardiac surgery with cardiopulmonary bypass, where data concerning patients’ hemodynamics, perfusion data, and biological and inflammatory markers intertwine. Cardiac Smart ICU models could recognize early signs of hemodynamic compromise and low cardiac output states and identify early indicators of post-cardiac surgery complications. Neutrophil activation and complete blood count-derived indices may be used as dynamic biological data for Smart Cardiac ICU models. Conclusion: The Smart Cardiac ICU may support earlier risk stratification, and therefore earlier diagnostic and therapeutic interventions, but its clinical value requires prospective, multicenter validation. Cardiopulmonary bypass-induced inflammation may offer an ideal setting to integrate physiological, procedural, and immunological data into bedside predictive models. Full article

Myocardial strain imaging, derived from speckle-tracking echocardiography (STE), has evolved from a research tool into a reproducible technique for detecting subclinical myocardial dysfunction. Recent advances in automated contouring and artificial intelligence have improved feasibility, reproducibility, and analysis speed, making multichamber strain assessment increasingly accessible in perioperative practice. Perioperative cardiovascular complications, including myocardial injury after non-cardiac surgery (MINS), postoperative atrial fibrillation (POAF), and heart failure, are associated with substantial postoperative morbidity and mortality. Conventional echocardiographic parameters, particularly left ventricular ejection fraction (LVEF), lack sensitivity for detecting early myocardial dysfunction. By quantifying myocardial deformation, strain imaging identifies subtle abnormalities in ventricular and atrial mechanics before conventional echocardiographic abnormalities become evident. Among available parameters, left ventricular global longitudinal strain (LV-GLS) and left atrial reservoir strain (LASr) provide the strongest evidence for perioperative risk stratification, with impaired values independently associated with MINS and POAF, respectively. Right ventricular strain (RV-GLS, RV-FWLS) and right atrial reservoir strain (RASr) remain promising but less standardized parameters supported mainly by observational data. Despite these advances, several barriers continue to limit widespread implementation, including vendor variability, the lack of standardized thresholds, and the absence of validated transesophageal echocardiography (TEE)-specific reference values. Importantly, current evidence supports myocardial strain primarily as a tool for risk stratification rather than for guiding therapy. No randomized trial has demonstrated that strain-guided perioperative management improves clinical outcomes, and its incremental value beyond established perioperative tools, including clinical risk scores, biomarkers, and conventional echocardiography, remains to be established. This review aims to provide a practical framework for the perioperative use of myocardial strain by summarizing the current evidence, clarifying its methodological limitations, simplifying its acquisition and interpretation for non-expert users, distinguishing established clinical applications from future research directions, and identifying the key evidence gaps that must be addressed before strain-guided strategies can be incorporated into routine perioperative care. Full article

Background/Objectives: Mitral valve surgery is associated with substantial perioperative heterogeneity and risk of postoperative complications. Although established risk scores such as EuroSCORE II provide population-level prognostic estimates, their performance may be limited in specific surgical populations and institutional settings. This pilot study aimed to develop and internally validate an interpretable center-specific machine learning model for perioperative risk stratification following mitral valve surgery and to explore its translational implementation through a prototype clinical application. Methods: A retrospective single-center study was conducted including 211 consecutive patients undergoing mitral valve surgery with ring implantation. Routinely available demographic, laboratory, and perioperative variables were evaluated as candidate predictors. The primary endpoint was a composite of major postoperative complications, including in-hospital mortality, stroke, conversion to sternotomy, and rethoracotomy. Predictive approaches included logistic regression, LASSO regression, and random forest classification. Internal validation was performed using 5-fold cross-validation and bootstrap resampling. Model explainability was assessed using regression coefficients and SHAP (SHapley Additive exPlanations) analysis. Results: The composite endpoint occurred in 34 patients (16.1%). In the complete-case final logistic regression model, apparent discrimination reached an AUC of 0.750 (95% CI 0.643–0.858), with a Brier score of 0.105. In the predefined train-test evaluation, the simplified logistic regression model achieved a test-set AUC of 0.67, while 5-fold cross-validation yielded a mean AUC of 0.75. LASSO regression achieved the highest cross-validated AUC (0.78), although with marked discrepancy between test-set and cross-validation performance, suggesting model instability. Across models, higher age, serum creatinine concentration, cardiopulmonary bypass duration, and cross-clamp time were associated with increased complication risk, whereas higher hemoglobin levels were associated with lower risk. Conclusions: This pilot study demonstrates the feasibility of developing interpretable center-specific machine learning models for perioperative risk stratification following mitral valve surgery. Simplified regression-based approaches provided clinically transparent predictions with moderate discriminatory performance, while penalized models showed potential for improved generalizability. Further multicenter validation is required before clinical implementation. Full article

Cardiac surgery remains a high-risk, resource-intensive domain in which perioperative complications significantly influence clinical outcomes, institutional performance, and healthcare expenditure. Despite advances in technique and protocol standardization, contemporary perioperative management largely relies on static risk stratification and reactive quality assessment. This narrative review synthesizes the current evidence on artificial intelligence (AI) and machine learning for perioperative risk prediction in cardiac surgery, spanning acute kidney injury, mortality, prolonged mechanical ventilation, postoperative atrial fibrillation, and intensive care unit deterioration, and critically appraises the methodological limitations, validation gaps, and fairness concerns that constrain clinical translation. Across these applications, predictive models have demonstrated incremental discrimination over conventional risk scores, yet remain predominantly endpoint-specific, single-institution, and disconnected from prospective clinical implementation. Building on this evidence, we propose Preventive Cardiovascular Intelligence (PCInt) as one possible organizing framework that integrates predictive analytics, dynamic risk trajectory modeling, and structured quality improvement methodologies, and we outline how such a framework might be operationalized across the surgical lifecycle. PCInt is presented as a conceptual proposal requiring prospective validation rather than as a validated system. We conclude by discussing implementation barriers, regulatory and ethical considerations, and priorities for future research toward anticipatory, value-based perioperative cardiovascular care. Full article

Generative Artificial Intelligence (GenAI) in cardiac surgery refers to the integration of advanced computational models, such as Large Language Models (LLMs), to automate and enhance clinical decision-making, preoperative risk assessment, and surgical education. In the context of surgical training, it functions as a personalized pedagogical tool that supports various learning activities, ranging from information acquisition and clinical inquiry to procedural practice, while requiring rigorous human oversight to ensure patient safety and clinical accuracy. (1) Background: Generative Artificial Intelligence (GenAI) is increasingly integrated into health professions education, offering new opportunities for learning; however, its specific application and pedagogical mapping in high-stakes fields such as cardiac surgery remain underexplored. This systematic review investigates how GenAI is utilized in cardiac surgery and surgical education, aligning these uses with Laurillard’s six learning types. (2) Methods: Following the PRISMA 2020 guidelines, we searched the Web of Science Core Collection for studies on GenAI in cardiac surgery, resulting in 42 studies that met the inclusion criteria. Study quality was appraised using the Medical Education Research Study Quality Instrument (MERSQI). (3) Results: GenAI applications most frequently supported clinical inquiry (93.8%) and practice (68.8%), demonstrating expanding efficiency across commercial and open-source models (including ChatGPT-4o, Gemini AI, and emerging reasoning architectures such as DeepSeek) for knowledge acquisition and medical production. While it significantly improves individualized learning and preoperative assessment workflows, its practical role in Discussion and Collaboration remains heavily underutilized, highlighting a distinct shift toward individualized solo professional workflows. (4) Conclusions: GenAI provides a transformative and scalable approach to cardiac surgical training by offering personalized and accessible knowledge retrieval. However, clinical educators and governance bodies must deliberately balance these immediate productivity benefits with long-term concerns regarding structural “hallucinations,” data verifiability, and the preservation of collaborative competencies within modern multidisciplinary Heart Teams. Full article

Artificial intelligence (AI) is rapidly transforming cardiovascular medicine, with growing applications in pediatric cardiology. AI techniques, particularly machine learning and deep learning, enable the analysis of complex and heterogeneous data, supporting diagnosis, risk stratification, and clinical decision-making. This paper provides an overview of current AI applications in this field, discusses existing challenges, and explores future perspectives. In pediatric cardiology, AI has shown promising results across multiple domains. In electrocardiography, AI algorithms improve diagnostic accuracy and enable early detection of cardiac conditions, even in asymptomatic patients, while facilitating telecardiology-based care pathways. In cardiac auscultation, AI-assisted digital stethoscopes enhance the distinction between innocent and pathological murmurs, supporting primary care physicians and optimizing referral to pediatric cardiologic centers. Multimodality imaging represents one of the most advanced areas of AI applications. In echocardiography, magnetic resonance and computed tomography, AI improves image acquisition, view classification, and automated quantification, contributing to more standardized and reproducible assessments. Additionally, emerging technologies such as virtual reality, integrated with AI, offer innovative tools for education, surgical planning, and patient-specific modelling. Despite these advances, several limitations remain, including limited availability of large pediatric datasets, challenges in model generalizability and issues related to interpretability and integration into clinical workflows. In conclusion, AI represents a powerful complementary tool in pediatric cardiology, with the potential to improve diagnostic accuracy, optimize healthcare resources and support the transition toward precision medicine. Full article

Background: Traditional intraoperative sizing for sutureless aortic valves, such as the Corcym Perceval Plus (CPP), often relies on subjective tactile feedback, which can lead to excessive over-sizing. Significant over-sizing is associated with complications like increased trans-prosthetic gradients, valve thrombosis, and conduction disturbances requiring permanent pacemakers. This study aims to develop an AI-driven predictive recommendation system using Multidetector Computed Tomography (MDCT) data to optimize valve sizing and improve patient outcomes. Methods: Data were collected from 380 consecutive patients who underwent aortic valve replacement with a CPP prosthesis between 2011 and 2026. Two machine learning models were trained using preoperative MDCT features, including annular area, perimeter, and diameters. The first model predicted “normal” clinical labels, while the second used “penalized” labels adjusted for postoperative hemodynamic performance to discourage over-sizing. The dataset was split into training (80%) and testing (20%) subsets. Results: The mean patient age was 77.6 years. The model using normal labels achieved an overall accuracy of 91.84% (68.75% on the test set). The penalized label model showed improved performance with an overall accuracy of 92.89% (72.16% on the test set). MDCT provided highly reproducible objective metrics superior to echocardiography for calculating optimal sizing. Conclusions: The AI-driven recommendation system proves to be a reliable and reproducible tool for preoperative planning. By transitioning from subjective tactile assessment to predictive modeling, surgeons can better select valve sizes that minimize complications, particularly in minimally invasive approaches. Full article

Aortic valve stenosis (AS) is assessed by echocardiography in clinical practice. Conventionally, the aortic valve area, peak transaortic valve velocity/gradient and the mean transvalvular gradient determine if the AS is categorized as mild, moderate or severe. Recently, the entity of paradoxical low-flow, low-gradient AS despite normal left ventricular ejection fraction (LVEF) was described and flow (as determined by stroke volume indexed to body surface area) was used to further categorize AS. The new European Society of Cardiology (ESC) and the European Association for Cardio-Thoracic Surgery (EACTS) guidelines in 2025 recommended a new phenotype-based classification, which improved the prognostication of AS. There are now five phenotypes: (1) concordant high-gradient AS; (2) low-flow, low-gradient AS with reduced LVEF; (3) low-flow, low-gradient AS with preserved LVEF; (4) normal-flow, low-gradient AS with preserved LVEF; and (5) discordant high-gradient AS. These appear to have different underlying pathophysiology, and hence prognostication and therapy. In addition, categories of AS in the setting of reduced LVEF are further divided based on their responses to dobutamine or exercise stress, which may result in different therapeutic strategies. In the transaortic valvular replacement (TAVR) versus the surgical aortic valve replacement (SAVR) era, the classification of these AS groups may have differing implications on the appropriate interventions. Furthermore, there are investigations on the effect of AS on the left ventricle and other chambers and stages of AS based on the extent of cardiac damage, which may have important prognostic value post-AVR. On the other spectrum, there are new developments in imaging analysis, such as using artificial intelligence. This state-of-the-art paper will comprehensively review the important updates in AS and its clinical implications. Full article

Background: Artificial intelligence (AI) is progressively entering perioperative medicine; however, its role in preoperative anesthetic decision-making remains insufficiently characterized. We evaluated the concordance between anesthesiologist-selected anesthetic techniques and algorithm-generated recommendations in a cohort of adult patients undergoing non-cardiac surgery. Methods: This retrospective observational study included adult patients (≥18 years) undergoing elective non-cardiac surgery between January 2024 and January 2025 at two international centers (Mexico and Italy). Clinical, demographic, and surgical variables were extracted from electronic medical records. For each case, a structured anonymized vignette was submitted to ChatGPT (version 5.0, medical configuration) to obtain an independent recommendation regarding anesthetic technique. Concordance between AI-generated and clinician-selected techniques was assessed using agreement analysis and stratified by country and surgical specialty. Results: A total of 1965 patients were analyzed. Overall concordance between ChatGPT recommendations and anesthesiologist-selected techniques was 84.6%. Agreement remained stable across centers (Mexico 84.3%; Italy 88.7%). Disagreement rates varied by surgical specialty, with the highest values observed in vascular and proctologic surgery (28.6%), followed by urology (21.1%) and thoracic surgery (18.8%). Orthopedic procedures—particularly shoulder arthroscopy—accounted for a relevant proportion of divergences, where AI frequently favored regional techniques over general anesthesia. No specialty demonstrated discordance exceeding 30%. Conclusions: AI-generated anesthetic recommendations demonstrated substantial concordance with expert clinical decision-making across heterogeneous surgical settings. These findings support the potential integration of AI within a hybrid decision-making framework, complementing—rather than replacing—anesthesiologist expertise in contemporary perioperative care. Full article

Artificial intelligence (AI) is rapidly reshaping cardiovascular (CV) medicine, driving a paradigm shift toward truly personalized and data-driven care. This comprehensive review examines the conceptual foundations, clinical applications, and future implications of AI across the CV continuum, spanning prevention, diagnosis, risk stratification, and therapy. Core AI methodologies (including machine learning, deep learning, natural language processing, and computer vision) are discussed in the context of cardiology’s uniquely data-rich environment, encompassing imaging, electrocardiography, electronic health records, wearable devices, and multi-omics data. This systematic review highlights major clinical domains where AI has demonstrated a substantial impact, including CV imaging, ECG interpretation, hypertension and heart failure management, coronary artery disease, acute coronary syndromes, interventional cardiology, and cardiac surgery. AI-driven predictive analytics enable early detection of subclinical disease, improved prognostication, and individualized prevention strategies, while wearable technologies and remote monitoring platforms facilitate continuous, real-world patient surveillance. Emerging applications in pharmacotherapy, drug repurposing, and genomics further reinforce AI’s role in advancing precision cardiology. Equally emphasized are the ethical, legal, and social challenges accompanying AI adoption, such as algorithmic bias, data privacy, cybersecurity, interpretability, and regulatory oversight. Our review underscores the necessity of rigorous clinical validation, transparent model design, and seamless integration into clinical workflows to ensure safety, equity, and physician trust. Ultimately, AI is best positioned as an augmentative tool that complements (but does not replace!) clinical expertise. By fostering hybrid intelligence that integrates human judgment with computational power, AI has the potential to redefine CV care delivery, improve outcomes, and support a more proactive, patient-centered healthcare model. Full article

Risk assessment for immediate mortality is a vital component of the preoperative assessment in elective cardiac surgeries of the adult population. It is generally used to inform consent and plan postoperative care, but can also help identify patients who need preoperative optimization. Risk assessment for open cardiac interventions remains difficult, as an absolute risk assessment tool is still lacking. In this narrative review, we examine recent data on the predictive performance of commonly used risk assessment tools in cardiac surgery and explore missed opportunities to improve predictive performance, including overlooked independent predictors and alternative calculation strategies, such as machine learning. The literature shows that the most popular risk assessment tools are the Parsonnet score, EuroSCORE II, STS-PROM, and ACEF. These have reasonable discriminative capabilities across most populations but occasionally suffer from poor calibration and over- or underprediction. Preoperative inflammation, functional status, physical performance, nutrition, and frailty are potentially relevant clinical factors that could improve mortality prediction modeling using traditional approaches. By far, the largest advancement comes from artificial intelligence-based models that demonstrate superior predictive capabilities utilizing the same predictors. These models are still in development, have not received external validation, are not yet trusted by physicians, and may not be accessible to all institutions due to computing limitations, and thus are not ready for global rollout. Further research in identifying novel predictors of mortality is required, and efforts are needed to validate machine learning models in external cohorts. Full article

Background/Objectives: Early tracheostomy seems favorable in prolonged ventilated patients after surgery. Hence, predicting tracheostomy after cardiac surgery is essential. Recently proposed prediction models aim to support this decision-making process, but their diagnostic validity across other patient populations remains uncertain. Methods: A retrospective single-center study was performed at a university hospital. The patient sample included consecutive patients between 2010 and 2020 who underwent cardiac surgery. Patients who underwent tracheostomy after cardiac surgery were assigned to the intervention group. Control group patients, who had not undergone tracheostomy, were randomly assigned to the group. An existing model was evaluated by receiver operating characteristics curve analysis. Four sets of risk features were chosen depending on results from regression analysis, lasso regularization, random forest or clinical domain knowledge. Newly developed models were created using machine learning methods: random forest, naïve Bayes, nearest neighbor and deep learning. Multiple models were trained with either feature set and then assessed using confusion matrices on an independent test set. Results: A total of 4744 patients were included in this study. One-hundred and eighteen patients were included in the tracheostomy group. Diagnostic accuracy of the existing model showed insufficient discrimination (area under the curve (AUC) = 0.57). Likewise, newly developed models also showed overall poor diagnostic discrimination across all feature sets and algorithms. Conclusions: This study shows the diagnostic limitations of retrospective clinical data for the diagnostic prediction of tracheostomy, thereby informing the design of future prospective diagnostic studies. Training new models should not rely on retrospective data alone. Instead, prospective data collection and integration of physiological or imaging-based diagnostics could likely contribute to the development of a good classifier. Full article

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. Full article

Over the past three decades, cardiac surgery has undergone a deep transformation, shifting from full median sternotomy to minimally invasive (MICS) and micro-invasive techniques. These approaches aim to achieve equivalent therapeutic outcomes while reducing surgical trauma, postoperative pain, hospitalization time, and healthcare costs. Minimally invasive strategies are now widely applied to aortic and mitral valve surgery, coronary artery bypass grafting, atrial fibrillation ablation, and combined procedures. Key advancements such as sutureless prostheses, video- and robotic-assisted systems, and enhanced imaging technologies have improved surgical precision and clinical outcomes while promoting faster recovery and superior cosmetic results. Evidence from randomized trials and observational studies demonstrates that MICS provides mortality and morbidity rates comparable to conventional surgery, with additional benefits in high-risk, elderly, and frail patients. Micro-invasive transcatheter interventions, particularly transcatheter aortic valve implantation (TAVI) and transcatheter mitral repair or replacement, have further expanded therapeutic options for patients unsuitable for open-heart surgery. Their success has fostered debate not between conventional and minimally invasive surgery, but between minimally invasive and micro-invasive approaches. Hybrid procedures—combining surgical and percutaneous techniques—exemplify a multidisciplinary evolution aimed at tailoring treatment to patient-specific anatomy, comorbidities, and risk profiles. Despite clear advantages, these techniques present challenges, including a steep learning curve, increased procedural costs, and the requirement for specialized equipment and institutional expertise. Optimal patient selection based on clinical risk assessment and advanced imaging remains essential. Future directions include refinement of robotic platforms, artificial intelligence-based decision support, miniaturization of instruments, and broader validation of emerging technologies in younger and low-risk populations. Minimally and micro-invasive cardiac surgery represent a paradigm shift toward patient-centered care, offering reduced physiological burden, improved functional recovery, and long-term outcomes comparable to conventional techniques. As innovation continues, these approaches are poised to become integral to modern cardiac surgical practice. Full article

Transesophageal echocardiography (TEE) has long been established as a cornerstone imaging modality in cardiac surgery and perioperative medicine. In recent years, however, its role has expanded into emergency and intensive care settings, where rapid and accurate hemodynamic assessment is crucial for survival. Point-of-care TEE provides advantages over transthoracic echocardiography when acoustic windows are limited, particularly in mechanically ventilated or critically unstable patients, allowing continuous high-quality visualization of cardiac function, volume status, and great vessel pathology to guide immediate therapeutic interventions. This narrative review examines the evolving role of TEE in acute settings, with emphasis on its application in shock, cardiac arrest, pulmonary embolism, tamponade, and its value in extracorporeal membrane oxygenation (ECMO) cannulation. Advances such as three-dimensional TEE, miniaturized probes, and the integration of artificial intelligence are also discussed, as potential drivers of innovation. While bridging technological progress with clinical practice, TEE emerges as a versatile tool in critical care. However, its broader adoption is still limited by probe availability, operator training, and institutional resources. Overcoming these barriers will be essential to translating technological advances into widespread practice. Full article