Search Results (23)

Artificial intelligence (AI) is entering cardiac surgery through predictive modelling, multimodal imaging, perioperative monitoring, workflow automation, and emerging computer-vision applications. The most mature evidence concerns risk prediction before and after surgery. Even in this domain, however, systematic reviews show that improvements over conventional statistical models are often modest and that routine clinical implementation remains limited. In surgical education, simulation, automated video analysis, and objective performance metrics may expand opportunities for deliberate practice and provide feedback that is less dependent on individual observers. Most of this evidence comes from general, laparoscopic, urological, and robotic surgery rather than cardiac-specific training, and its transferability should not be assumed. The same technologies also create risks. Automation bias, cognitive off-loading, reduced exposure to failure management, and displacement of mentor–trainee interaction may weaken the independent judgement on which safe cardiac surgery depends. Opaque models, dataset shift, inequitable performance, and uncertain accountability add further clinical and ethical concerns. This narrative review examines the current and emerging roles of AI across the cardiac surgical pathway and in cardiothoracic training, while distinguishing demonstrated applications from plausible but unproven uses. We propose a human-in-command framework based on external validation, local performance testing, transparent intended use, preserved manual and crisis-management competencies, simulation of technology failure, faculty oversight, competency-based credentialing, and continuous audit. AI should be judged not by technical novelty alone but by whether it improves care while preserving the ability of surgeons and teams to operate safely when the technology is unavailable or wrong. Full article

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

Artificial intelligence (AI) is increasingly integrated into emergency general surgery (EGS), where rapid diagnosis, accurate decision-making, and timely intervention are essential for improving patient outcomes. Recent advances in machine learning, deep learning, computer vision, and predictive analytics have enabled AI-assisted systems to support clinicians throughout the perioperative workflow. Current applications include radiologic image interpretation, diagnosis of acute abdominal conditions, surgical workflow recognition, intraoperative anatomical guidance, postoperative complication prediction, and intensive care monitoring. AI technologies may improve diagnostic accuracy, optimize operative planning, enhance surgical safety, and facilitate personalized perioperative management. In minimally invasive surgery, computer vision and real-time data analysis have shown promising results for intraoperative decision support and surgical education. However, important limitations remain, including concerns regarding data quality, algorithm transparency, ethical governance, regulatory approval, and implementation disparities between healthcare systems. In addition, much of the current evidence is derived from retrospective or highly specialized datasets, limiting broad clinical applicability. This narrative review summarizes the current clinical applications of AI in emergency general surgery and discusses emerging technologies, existing challenges, and future perspectives regarding the integration of AI into acute surgical care. Full article

Pulse oximetry is an essential standard monitor in modern anesthetic practice, enabling continuous noninvasive assessment of arterial oxygen saturation and pulse rate throughout the perioperative period. Since its introduction into clinical medicine, pulse oximetry has significantly improved patient safety by facilitating early detection of hypoxemia and physiologic deterioration. Despite its widespread use, clinicians may underrecognize the technical principles, physiologic assumptions, and limitations that influence measurement accuracy. This review provides a perioperative perspective on pulse oximetry, including the physics of photoplethysmography, sensor technologies, and practical considerations for optimal probe placement and signal acquisition. Sources of inaccuracy such as motion artifact, low perfusion states, dyshemoglobinemias, ambient light interference, skin pigmentation, and venous pulsation are discussed in detail. The review further examines perioperative applications across preoperative evaluation, intraoperative monitoring, and postoperative recovery, while also exploring advanced parameters including perfusion index (PI) and pleth variability index (PVI). Emerging innovations such as multi-wavelength systems and artificial intelligence (AI)-enhanced signal analysis are also highlighted. A comprehensive understanding of pulse oximetry allows anesthesiologists to appropriately interpret monitor data, recognize device limitations, and optimize perioperative patient care. Full article

Background: Isolated Perfusion Chemotherapy (IPC) with balloon occlusion creates transient ischemic tissue compartments while patients remain exposed to significant perioperative heat loss. Active warming during these phases is commonly avoided due to theoretical concerns regarding impaired heat distribution and potential local heat accumulation in ischemic tissue. This study investigated the thermal safety of forced-air warming during IPC under these conditions. Methods: In this prospective observational study, 31 patients undergoing IPC were monitored during balloon-induced vascular occlusion. Convective warming was applied using a forced-air system set to 43 °C. Core temperature was measured rectally, and local temperatures were continuously recorded at gluteal, lumbar, and interscapular sites. Temperature trajectories and maximum values during occlusion were analysed descriptively. Results: Local temperature increases during ischemia were limited, with a maximum increase of 2.3 °C at the lumbar site. Absolute temperatures remained well below the predefined safety threshold of 39.5 °C at all skin measurement sites (maximum observed 37.7 °C). Core temperature remained stable throughout the occlusion phase. No evidence of local heat accumulation, threshold exceedance, or thermal skin reactions was observed. Conclusions: Under conditions of controlled application, close temperature monitoring, and short ischemic intervals, forced-air warming during IPC did not result in local overheating or clinically relevant thermal exposure. These findings challenge the prevailing precautionary approach of avoiding active warming during vascular isolation and provide prospective clinical evidence supporting a reassessment of temperature management strategies toward actively maintained normothermia in isolated perfusion chemotherapy. Full article

General approaches of head and neck surgery involve varied procedures with developing perioperative care and a renewed effort on regional anaesthesia (RA) for intraoperative and postoperative analgesia. Due to the rich innervation and focus on enhanced recovery after surgery (ERAS), RA techniques, particularly ultrasound-guided ones, are becoming popular as part of an opioid-sparing multimodal analgesic regimen. However, the evidence base is heterogeneous and synthesised clinical guidance is needed. This narrative review, performed according to the Scale for the Assessment of Narrative Review Articles (SANRA) framework, summarises the existing literature on the role of RA in head and neck surgery, including anatomical basis, types of techniques used for RA, clinical applications, immediate outcomes and implementation. We conducted a comprehensive literature search, including studies published between January 2000 and October 2025 in English, across the PubMed/MEDLINE, Scopus, and Cochrane Library databases. Understanding of the anatomy of cervical plexus (C1–C4) and cranial nerves such as trigeminal V is basic to delineation of techniques into superficial (e.g., SCPB), deep and selective cranial nerve blocks. The evidence about decreases in postoperative pain intensity, opioid consumption (especially 24 h post-op) and decreased length of stay, largely through studies on thyroidectomy, has been consistent for SCPB as an adjunct to general anaesthesia. Ultrasound-guided regional anaesthesia (UGRA) has significantly enhanced precision and safety, reducing risks such as phrenic nerve paresis, although the concern for even higher complication rates remains with deeper or bilateral blocks. Although beneficial outcomes have been demonstrated, the literature is plagued by small and heterogeneous trials, variable block protocols, and a lack of data in complex oncologic resections or reconstructive settings. For successful implementation, there is a need for structured training programmes of anaesthesiologists and surgeons involved in the procedure performing UGRA together, institutional protocols on standardised technique, patient monitoring and outcomes auditing. RA is a useful and safe adjunct to head and neck surgery, providing analgesia in the short term and contributing to improved recovery during the perioperative period. Further studies should be conducted through large-scale, standardised trials to resolve the contributions of blocks in complex surgical cases and implement best practices for both training and clinical integration. Full article

Background/Objectives: Musculoskeletal disorders and their surgical treatment significantly affect global disability, healthcare utilization, and costs. Artificial intelligence (AI) is a key enabler of data-driven musculoskeletal care. Their applications include diagnostic imaging, surgical planning, risk prediction, rehabilitation, and digital health ecosystems. This narrative review synthesizes current evidence on the use of AI in orthopaedics and musculoskeletal care across five areas: diagnostic imaging, surgical planning and intraoperative augmentation, predictive analytics and patient-reported outcomes, rehabilitation intelligence and teleorthopaedics, and system-level management. An additional task is to identify translational gaps and priorities for safe, ethical, and equitable implementation of AI. Methods: A structured narrative review was conducted using targeted searches in PubMed, Scopus, and Web of Science supplemented by semantic and citation-based explorations in Semantic Scholar, OpenAlex, and Google Scholar. The main search period was January 2019 to December 2025. The retrieved peer-reviewed articles were analyzed for clinical relevance to human musculoskeletal care, quantitative outcomes, and the translational implications of the results. From the broader pool of eligible publications, 40 clinically relevant studies were selected for detailed synthesis covering imaging, surgical planning, predictive modeling, rehabilitation, and system-level applications. Owing to the significant heterogeneity in the model architectures, datasets, and endpoints, the results were organized into five predefined thematic areas. Results: The most mature evidence is for AI-assisted detection of bone fractures on radiographs, identification of implants, and use of sizing templates in preoperative planning for arthroplasty, where deep learning systems have achieved expert-level diagnostic performance (e.g., fracture detection sensitivity of approximately 90% and specificity of approximately 92% and implant identification accuracy of 97–99%) and improved the accuracy of preoperative planning compared to conventional templating. AI-based planning increases the likelihood of reducing intraoperative corrections, shortening surgery time, reducing blood loss, and improving the final functional outcomes. Predictive models can support the stratification of risk for complications, rehospitalizations, and patient-reported outcomes, although external validation remains limited and is often single-center at this stage of research. Emerging applications in rehabilitation and teleorthopaedics, including sensor-based monitoring and learning systems integrated with Patient-Reported Outcome Measures (PROMs), are conceptually promising, but are mainly limited to feasibility or pilot studies. Conclusions: AI is beginning to influence musculoskeletal care, moving beyond pattern recognition toward integrated, patient-centered decision support throughout the perioperative and rehabilitation periods. Its widespread use remains constrained by limited multicenter validation, dataset bias, algorithmic opacity, and immature regulatory and governance frameworks. Future work should prioritize prospective multicenter impact studies, repeatable revalidation of local models, integration of PROM and teleorthopedic data with health learning systems, and adaptation to changing regulatory requirements to enable safe, ethical, effective, and equitable implementation in routine orthopedic practice. Full article

Background: In head and neck reconstructive surgery, flap loss remains a major complication and continues to represent a significant challenge in perioperative management. Although free tissue transfer is widely used, unsatisfactory outcomes are still reported across different flap procedures. Anaesthetic management plays an important role in influencing flap perfusion through its effects on systemic haemodynamics, regional blood flow, and microcirculation. However, there is currently no consensus on universally acceptable haemodynamic targets, and the impact of intraoperative strategies appears to be highly application-specific. Materials and Methods: This narrative review was conducted in accordance with the 2019 SANRA guidelines. PubMed^® was used as the primary database for literature selection. Relevant studies addressing anaesthetic management in head and neck free flap surgery were reviewed, with a particular focus on intraoperative haemodynamic control, ischemia–reperfusion injury, fluid and transfusion management, vasoactive agents, and advanced monitoring techniques. Results: Ischemia–reperfusion injury represents a major mechanism of vascular compromise in free flap surgery and has a significant impact on microcirculatory perfusion. The literature suggests that several anaesthetic strategies—including goal-directed fluid therapy, cautious use of vasopressors, and advanced haemodynamic monitoring—may support intraoperative haemodynamic stability and improve flap perfusion. Nevertheless, the magnitude of haemodynamic improvement achievable with these strategies and their effect on graft survival vary according to patient characteristics, surgical factors, and flap type. Conclusions: Current evidence indicates that anaesthetic management has the potential to contribute to improved intraoperative haemodynamic control in head and neck free flap reconstruction, thereby supporting graft viability. However, haemodynamic targets and management strategies cannot be generalised and should be interpreted within specific clinical contexts. Rather than aiming for optimisation, future research should focus on defining acceptable clinical outcomes for individual applications and on evaluating whether achievable haemodynamic improvements are sufficient to reduce flap-related complications to clinically acceptable levels. Full article

As artificial intelligence (AI) continues to expand across clinical environments, healthcare is transitioning from static decision-support tools to dynamic, autonomous agents capable of reasoning, coordination, and continuous interaction. In the context of geriatric medicine, a field characterized by multimorbidity, cognitive decline, and the need for long-term personalized care, this evolution opens new frontiers for delivering adaptive, assistive, and trustworthy digital support. However, the autonomy and interconnectivity of these systems introduce heightened cybersecurity and ethical challenges. This paper presents a Secure Agentic AI Architecture (SAAA) tailored to the unique demands of geriatric healthcare. The architecture is designed around seven layers, grouped into five functional domains (cognitive, coordination, security, oversight, governance) to ensure modularity, interoperability, explainability, and robust protection of sensitive health data. A review of current AI agent implementations highlights limitations in security, transparency, and regulatory alignment, especially in multi-agent clinical settings. The proposed framework is illustrated through a practical use case involving home-based care for elderly patients with chronic conditions, where AI agents manage medication adherence, monitor vital signs, and support clinician communication. The architecture’s flexibility is further demonstrated through its application in perioperative care coordination, underscoring its potential across diverse clinical domains. By embedding trust, accountability, and security into the design of agentic systems, this approach aims to advance the safe and ethical integration of AI into aging-focused healthcare environments. Full article

Artificial intelligence (AI) is rapidly transforming anesthesiology practice across perioperative settings. This review explores the evolution and implementation of hybrid decision-making models that integrate AI capabilities with human clinical expertise. From historical foundations to current applications, we examine how machine learning algorithms, deep learning networks, and big data analytics are enhancing anesthetic care. Key applications include perioperative risk prediction, AI-assisted patient education, automated analysis of clinical records, airway management support, predictive hemodynamic monitoring, closed-loop anesthetic delivery systems, and pain management optimization. In procedural contexts, AI demonstrates promising utility in regional anesthesia through anatomical structure identification and needle navigation, monitoring anesthetic depth via EEG analysis, and improving quality control in endoscopic sedation. Educational applications include intelligent simulators for procedural training and academic productivity tools. Despite significant advances, implementation challenges persist, including algorithmic bias, data security concerns, clinical validation requirements, and ethical considerations regarding AI-generated content. The optimal integration model emphasizes a complementary approach where AI augments rather than replaces clinical judgment—combining computational efficiency with the irreplaceable contextual understanding and ethical reasoning of the anesthesiologist. This hybrid paradigm reinforces the anesthesiologist’s leadership role in perioperative care while enhancing safety, precision, and efficiency through technological innovation. As AI integration advances, continued emphasis on algorithmic transparency, rigorous clinical validation, and human oversight remains essential to ensure that these technologies enhance rather than compromise patient-centered anesthetic care. Full article

Background: Continuous glucose monitoring (CGM) has changed the clinical practice in diabetes management during pregnancy; however, its application during caesarean section remains understudied. This feasibility study evaluates the performance, reliability, and clinical utility of two CGM systems—FreeStyle Libre 2 and Medtronic Guardian Connect—during caesarean delivery and the early postpartum period in a patient with pregestational diabetes mellitus (PGDM). Methods: A prospective, single-patient study was conducted. A 32-year-old woman with type 1 diabetes underwent elective caesarean section at 38 weeks of gestation. Both CGM systems were applied over 18 h prior to surgery and monitored continuously through the intraoperative and five-day postpartum period. Glucose data, device performance, and usability were assessed. Results: Both CGM systems provided uninterrupted, high-quality glucose data throughout the perioperative period, including during spinal anaesthesia, surgical manipulation, and postoperative recovery. No sensor displacement nor signal loss occurred. Glycaemic readings remained within the normoglycaemic range (90–100 mg/dL) during surgery, with mild elevations observed during anaesthesia initiation. Postoperatively, both systems showed comparable glucose trends, with slightly lower readings from FreeStyle Libre 2. Conclusions: CGM is feasible and reliable during caesarean section in PGDM patients. These findings support the integration of CGM into obstetric surgical care and highlight the need for larger studies to validate clinical benefits. Full article

This study evaluated the application of the BCG Sense1 wearable device for monitoring the heart rate (HR) and the respiratory rate (RR) in dogs, comparing its performance to the gold standard ECG under awake and anesthetized conditions. Data were collected from twelve dogs, with six awake beagles and six anesthetized client-owned dogs. Bland–Altman analysis and linear regression revealed strong correlations between BCG and ECG under both awake and anesthetized conditions (HR: r = 0.97, R² = 0.94; RR: r = 0.78, R² = 0.61, and p < 0.001). While slight irregularities were noted in respiratory rate measurements in both groups, potentially affecting the concordance between methods, BCG maintained a significant correlation with ECG under anesthesia (HR: r = 0.96, R² = 0.92; RR: r = 0.85, R² = 0.72, and p < 0.01). The wearable BCG-Sense 1 sensor enables continuous monitoring over 24 h, while ECG serves as the gold standard reference. These findings prove that BCG can be a good alternative to ECG for the monitoring of vital signs in clinical, perioperative, intraoperative, and postoperative settings. The strong correlation between the BCG and ECG signals in awake and anesthetized states highlights the prospects of BCG technology as a revolutionary method in veterinary medicine. As a non-invasive and real-time monitoring system, the BCG Sense1 device strengthens clinical diagnosis and reduces physiological variations induced by stress. Full article

Postoperative atrial fibrillation (POAF) is the most common arrhythmia following cardiac surgery. This review critically explores the interplay between cardiopulmonary bypass (CPB) and aortic cross-clamping (ACC) times in POAF development. CPB disrupts systemic homeostasis by inducing inflammatory cascades, oxidative stress, and ischemia–reperfusion injury. Prolonged ACC times further exacerbate myocardial ischemia and structural remodeling, with durations exceeding 60–75 min consistently linked to an increased POAF risk. However, variability in outcomes across studies reveals the complex, multifactorial nature of POAF pathogenesis. Patient-specific variables, such as baseline comorbidities and myocardial protection strategies, modulate these risks, emphasizing the need for personalized surgical approaches. Despite advancements in myocardial protection techniques and anti-inflammatory strategies, the incidence of POAF remains persistently high, indicating a gap in translating mechanistic insights into effective interventions. Emerging biomarkers, including microRNAs (e.g., miR-21, miR-483-5p, etc.) and markers of myocardial injury like troponin I, offer potential for enhanced risk stratification and targeted prevention. However, their clinical applicability requires further validation in diverse patient populations. This review underscores the critical need for integrative research that combines clinical, molecular, and procedural variables to elucidate the nuanced interplay of factors driving POAF. Future directions include leveraging advanced intraoperative monitoring tools, refining thresholds for CPB and ACC times, and developing individualized perioperative protocols. Full article

Background: Acute kidney injury (AKI) is a critical medical condition characterized by a sudden decline in renal function, often resulting in severe complications and increased mortality. In the context of spine surgery, particularly for adult spine deformities, the risk of AKI is significant due to the complexity and duration of these procedures, as well as the substantial intraoperative blood loss and hemodynamic instability they can entail. Despite advancements in surgical and perioperative care, AKI remains a major concern. This paper presents a case report of AKI following spine deformity surgery and conducts a comprehensive literature review to evaluate the incidence and risk factors associated with AKI in this specific surgical population. Methods: A systematic literature search was conducted across the PubMed, Medline, and Cochrane Library databases, focusing on studies published between January 2000 and December 2023. The inclusion criteria targeted studies reporting on adult patients undergoing spine surgery, specifically detailing the incidence and risk factors of AKI. Exclusion criteria included studies on pediatric patients, non-English publications, and those lacking clear AKI diagnostic criteria. Data from the selected studies were independently extracted by two reviewers and analyzed using descriptive statistics and meta-analysis techniques where applicable. The case report highlights a patient who developed AKI following extensive spine surgery for Adult Spine Deformity (ASD), detailing the clinical course, diagnostic approach, and management strategies employed. Results: The literature review revealed that the incidence of AKI in spine surgery varies widely and is influenced by factors such as patient demographics, type of surgery, and perioperative management. Identified risk factors include significant blood loss, prolonged operative time, intraoperative hypotension, and the use of nephrotoxic drugs. The findings underscore the importance of vigilant perioperative monitoring and proactive management strategies to mitigate the risk of AKI. These strategies include optimizing hemodynamic stability, minimizing blood loss, and careful management of nephrotoxic medications. Conclusions: By integrating a detailed case report with a thorough review of the existing literature, this paper aims to enhance the understanding of AKI in spine surgery and inform clinical practices to improve patient outcomes. Full article

Surgery is a common first-line treatment for many types of disease, including cancer. Mortality rates after general elective surgery have seen significant decreases whilst postoperative complications remain a frequent occurrence. Preoperative assessment tools are used to support patient risk stratification but do not always provide a precise and accessible assessment. Wearable sensors (WS) provide an accessible alternative that offers continuous monitoring in a non-clinical setting. They have shown consistent uptake across the perioperative period but there has been no review of WS as a preoperative assessment tool. This paper reviews the developments in WS research that have application to the preoperative period. Accelerometers were consistently employed as sensors in research and were frequently combined with photoplethysmography or electrocardiography sensors. Pre-processing methods were discussed and missing data was a common theme; this was dealt with in several ways, commonly by employing an extraction threshold or using imputation techniques. Research rarely processed raw data; commercial devices that employ internal proprietary algorithms with pre-calculated heart rate and step count were most commonly employed limiting further feature extraction. A range of machine learning models were used to predict outcomes including support vector machines, random forests and regression models. No individual model clearly outperformed others. Deep learning proved successful for predicting exercise testing outcomes but only within large sample-size studies. This review outlines the challenges of WS and provides recommendations for future research to develop WS as a viable preoperative assessment tool. Full article