Search Results (207)

Objective: We evaluated the feasibility of a machine-learning (ML) model based on clinical features and radiomics from [¹⁸F]FDG PET/CT images to differentiate between infected and non-infected intracavitary vascular grafts and endografts (iVGEI). Methods: Three ML models were developed: one based on pre-treatment criteria to diagnose a vascular graft infection (“MAGIC-light features”), another using radiomics features from diagnostic [¹⁸F]FDG-PET scans, and a third combining both datasets. The training set included 92 patients (72 iVGEI-positive, 20 iVGEI-negative), and the external test set included 20 iVGEI-positive and 12 iVGEI-negative patients. The abdominal aorta and iliac arteries in the PET/CT scans were automatically segmented using SEQUOIA and TotalSegmentator and manually adjusted, extracting 96 radiomics features. The best-performing models for the MAGIC-light features and PET-radiomics features were selected from 343 unique models. Most relevant features were combined to test three final models using ROC analysis, accuracy, sensitivity, and specificity. Results: The combined model achieved the highest AUC in the test set (mean ± SD: 0.91 ± 0.02) compared with the MAGIC-light-only model (0.85 ± 0.06) and the PET-radiomics model (0.73 ± 0.03). The combined model also achieved a higher accuracy (0.91 vs. 0.82) than the diagnosis based on all the MAGIC criteria and a comparable sensitivity and specificity (0.70 and 1.00 vs. 0.76 and 0.92, respectively) while providing diagnostic information at the initial presentation. The AUC for the combined model was significantly higher than the PET-radiomics model (p = 0.02 in the bootstrap test), while other comparisons were not statistically significant. Conclusions: This study demonstrated the potential of ML models in supporting diagnostic decision making for iVGEI. A combined model using pre-treatment clinical features and PET-radiomics features showed high diagnostic performance and specificity, potentially reducing overtreatment and enhancing patient outcomes. Full article

Artificial Intelligence (AI) and machine learning (ML) are increasingly being applied across the transplantation care pathway, supporting tasks such as donor–recipient matching, immunological risk stratification, early detection of graft dysfunction, and optimisation of immunosuppressive therapy. This review provides a structured synthesis of current AI applications in transplantation, with a focus on underrepresented areas including real-time graft viability assessment, adaptive immunosuppression, and cross-organ immune modelling. The review also examines the translational infrastructure needed for clinical implementation, such as federated learning, explainable AI (XAI), and data governance. Evidence suggests that AI-based models can improve predictive accuracy and clinical decision support when compared to conventional approaches. However, limitations related to data quality, algorithmic bias, model transparency, and integration into clinical workflows remain. Addressing these challenges through rigorous validation, ethical oversight, and interdisciplinary collaboration will be necessary to support the safe and effective use of AI in transplant medicine. Full article

Background and Objectives: Despite significant advances in surgical techniques and perioperative care, major adverse cardiovascular events (MACE) remain a leading cause of postoperative morbidity and mortality in patients undergoing coronary artery bypass grafting and/or aortic valve replacement. Accurate preoperative risk stratification is essential yet often limited by models that overlook atrial mechanics and underutilized biomarkers. Materials and Methods: This study aimed to develop an interpretable machine learning model for predicting perioperative MACE by integrating clinical, biochemical, and echocardiographic features, with a particular focus on novel physiological markers. A retrospective cohort of 131 patients was analyzed. An Extreme Gradient Boosting (XGBoost) classifier was trained on a comprehensive feature set, and SHapley Additive exPlanations (SHAPs) were used to quantify each variable’s contribution to model predictions. Results: In a stratified 80:20 train–test split, the model initially achieved an AUC of 1.00. Acknowledging the potential for overfitting in small datasets, additional validation was performed using 10 independent random splits and 5-fold cross-validation. These analyses yielded an average AUC of 0.846 ± 0.092 and an F1-score of 0.807 ± 0.096, supporting the model’s stability and generalizability. The most influential predictors included total atrial conduction time, mitral and tricuspid annular orifice areas, and high-density lipoprotein (HDL) cholesterol. These variables, spanning electrophysiological, structural, and metabolic domains, significantly enhanced discriminative performance, even in patients with preserved left ventricular function. The model’s transparency provides clinically intuitive insights into individual risk profiles, emphasizing the significance of non-traditional parameters in perioperative assessments. Conclusions: This study demonstrates the feasibility and potential clinical value of combining advanced echocardiographic, biochemical, and machine learning tools for individualized cardiovascular risk prediction. While promising, these findings require prospective validation in larger, multicenter cohorts before being integrated into routine clinical decision-making. Full article

Introduction: Liver transplantation remains the definitive treatment for end-stage liver disease but faces critical challenges including organ shortages and preservation difficulties, particularly with extended criteria donor (ECD) grafts. Hypothermic machine perfusion (HMP) represents a promising alternative to traditional static cold storage (SCS). Methods: This retrospective study analyzed outcomes from 62 liver transplant recipients between 2016 and 2025, comparing 8 grafts preserved by HMP using the Liver Assist^® system and 54 grafts preserved by SCS. Parameters assessed included postoperative complications, hemodynamic stability, ischemia times, and survival outcomes. Results: HMP significantly reduced surgical (0% vs. 75.9%, p = 0.01) and biliary complications (0% vs. 34.4%, p = 0.004), improved hemodynamic stability post-reperfusion (∆MAP%: 1 vs. 21, p = 0.006), and achieved superior one-year survival rates (100% vs. 84.4%). Despite longer ischemia periods, grafts treated with HMP exhibited fewer adverse effects from ischemia-reperfusion injury. Discussion: These findings highlight the substantial benefits of HMP, particularly in improving graft quality from marginal donors and reducing postoperative morbidity. Further adoption of this technology could significantly impact liver transplantation outcomes by expanding the viable donor pool. Conclusions: The study underscores the effectiveness of hypothermic machine perfusion (HMP) as a superior preservation method compared to traditional static cold storage (SCS), HMP appears to be associated with improved short-term outcomes in liver transplantation. By substantially reducing postoperative complications and enhancing graft viability, HMP emerges as a pivotal strategy for maximizing the use of marginal donor organs. Further research and broader clinical implementation are recommended to validate these promising results and to fully harness the potential of HMP in liver transplantation. Full article

Background/Objectives: Challenges in normothermic machine perfusion (NMP) remain, particularly concerning the duration for which individual organs can be safely preserved. We hypothesize that optimal preservation can be achieved by perfusing organs together in a multivisceral block. Therefore, our aim was to establish a platform for ex situ multivisceral organ perfusion. Methods: Multivisceral grafts containing the liver, kidneys, pancreas, spleen, and intestine were obtained from Yorkshire pigs. Three generation (gen) set-ups were tested during the iterative design process, and minor changes were made throughout. Gen 1 (n = 4) used a custom-designed single perfusion circuit. Gen 2 (n = 3) employed a dual perfusion circuit. Gen 3 (n = 4) featured a single perfusion circuit with an optimized basin and reservoir. Grafts underwent NMP using an autologous blood-based perfusate, while hemostatic parameters and function were assessed. Results: Comparing Gen 1 versus Gen 3, the mean aortic flow improved (1.018 vs. 2.089 L), resistance decreased (0.224 vs. 0.038), urine output increased (51.90 vs. 271.3 mL), oxygen consumption rose (43.56 vs. 49.52 mL O₂/min), perfusate lactate levels dropped (10.44 vs. 3.10 mmol/L), and the pH became more physiological (7.27 vs. 7.30). Cellular injury trended lower in Gen 3. Histological evaluation demonstrated minimal differences in Gens 2 and 3. Conclusions: We demonstrate the feasibility of abdominal multivisceral NMP for up to 8 h. Adequate arterial flow, stable perfusate pH, and high oxygen consumption in setup 3 indicated organ viability. Multivisceral perfusion may serve as a plat-form for long-term NMP. Full article

Organ shortage is a major challenge in transplantation, prompting the use of extended criteria donor grafts. These require improved preservation techniques and reliable methods to assess graft function. This study aimed to evaluate changes in the kidney metabolome following three preservation methods: normothermic ex vivo kidney perfusion (NEVKP), hypothermic machine perfusion (HMP) and static cold storage (SCS) in porcine autotransplant models. A chemical biopsy allowed minimally invasive sampling of metabolites, which were analyzed using liquid chromatography coupled with high-resolution mass spectrometry. The results highlighted metabolites affected by ischemia and oxidative stress in donor kidneys, as well as changes specific to each preservation method. Differences were observed immediately after transplantation and reperfusion and several days post-surgery. NEVKP was associated with the activation of physiological anti-oxidative and anti-inflammatory mechanisms, suggesting potential protective effects. However, some metabolites had dual roles, which may influence future graft treatment designs. HMP and SCS, while reducing energy demand in cells, also limit physiological repair mechanisms. These findings provide a basis for improving graft assessment and organ preservation, with chemical biopsy serving as both a tool for discovery and a potential diagnostic method for monitoring graft quality. Full article

Background and Objectives: The goal of this study was to introduce a novel device, the iMPACT implant planer, designed to machine (create a complete smooth surface) contaminated implant surfaces intraorally, promoting peri-implant tissue healing and possible re-osseointegration, and the new Quadrant protocol, evaluating them in vitro and clinically. The null hypothesis was that there would be no improvement in the clinical parameters for the implants with peri-implantitis (PI) treated with the new protocol and tool. Materials and Methods: The Quadrant protocol was used in conjunction with the iMPACT tool, which primarily functions to remove biofilm and microbial contaminants from the exposed implant surface, while simultaneously preparing the surface through standardized implantoplasty, thereby enhancing the potential for re-osseointegration. An in vitro analysis was developed, and three medium/long-term cases were presented, detailing the procedures and outcomes. Results: The in vitro assessment showed smooth surfaces after treatment. Different areas presented minimal particles (<1 μm) on the implant surface, with a high content of titanium (Ti) and tungsten (W). In case 1, severe and advanced peri-implantitis around implants #46 and #47 was found. A combination of resective (Quadrant + iMPACT) and regenerative surgery was used for treatment, along with a buccal single flap (BSF). Significant clinical and radiographic improvements were observed at 14 and 43 months postoperatively, including vertical bone gain with re-osseointegration and stable probing depths (PDs). In the second case, a severe PI and prosthesis instability were observed. Resective (Quadrant + iMPACT) and regenerative procedures were applied. At 3 and 12 months postoperatively, clinical and radiographic evaluations demonstrated significant improvements with re-osseointegration, including PDs reduced to 0–1 mm and a vertical bone gain of approximately 6.5 mm. In case 3, mandibular implants from 42 to 47 exhibited inflammation, suppuration, and moderate-to-severe bone loss. Just resective surgery (Quadrant + iMPACT), without grafting, was performed. At 6- and 12-month follow-ups, clinical and radiographic assessments showed the resolution of inflammation, stable bone levels, and healthy peri-implant gingiva. Conclusions: Favorable outcomes were achieved using the iMPACT and Quadrant protocols in the three clinical cases, resulting in re-osseointegration when combined with regenerative procedures. The favorable medium/long-term outcomes achieved, despite the patient’s complex medical history and, at times, inconsistent oral hygiene, underscore the potential efficacy of such interventions. Full article

This study aims to improve the performance of wood–plastic composites (WPCs) composed of cotton stalk powder and residual film particles. Additionally, it aims to promote the efficient utilization of cotton stalk biochar. The composites were prepared using modified cotton stalk biochar and xylem powder as the matrix, maleic anhydride grafted high-density polyethylene (MA-HDPE) as the coupling agent, and polyethylene (PE) residual film particles as the filler. The WPCs were fabricated through melt blending using a twin-screw extruder. Mechanical properties were evaluated using a universal testing machine and texture analyzer, Shore D hardness was measured using a durometer, and microstructure was analyzed using a high-resolution digital optical microscope. A systematic investigation was conducted on the effect of biochar content on material properties. The results indicated that modified biochar significantly enhanced the mechanical and thermal properties of the WPCs. At a biochar content of 80%, the material achieved optimal performance, with a hardness of 57.625 HD, a bending strength of 463.159 MPa, and a tensile strength of 13.288 MPa. Additionally, thermal conductivity and thermal diffusivity decreased to 0.174 W/(m·K) and 0.220 mm²/s, respectively, indicating improved thermal insulation properties. This research provides a novel approach for the high-value utilization of cotton stalks and residual films, offering a potential solution to reduce agricultural waste pollution in Xinjiang and contributing to the development of low-cost and high-performance WPCs with wide-ranging applications. Full article

In this study, a flame-retardant wood-polymer composite was produced using huntite-hydromagnesite mineral, recognized for its non- flammability properties. In this context, wood-polymer composites were produced with the co-rotating twin-screw extrusion technique, while polypropylene was applied as the composite matrix, medium density fiberboard waste and inorganic huntite-hydromagnesite mineral were used as the reinforcement material. The proportion of wood powder additives was changed to 10% and 20%, and the huntite and hydromagnesite ratio was changed to 30%, 40%, 50% and 60%. Maleic anhydride grafted polypropylene, i.e., MAPP, was applied as a binder at a rate of 3%. Polypropylene, wood fibers, mineral powders, and MAPP blended in the mixer were processed in the extruder and turned into granules. Structural, morphological, thermal, mechanical, and flame-retardant properties of the composites were analyzed using XRD, SEM, FTIR, TGA, tensile testing, and the UL-94 vertical flammability test. Test samples were prepared to evaluate the physical and mechanical properties with a compression molding machine. It was concluded that the composites gained significant flame retardancy with the addition of huntite hydromagnesite. The potential for using this material in various fields and its compliance with the principles of circular economy and the Sustainable Development Goals (SDG 12) were noted. Full article

In Maxillofacial Reconstruction Applications (MRA), nonunion is one of the critical complications after the reconstruction process and fracture treatment, including bone grafts and vascularized flap. Nonunion describes the failure of a fractured bone to heal and mend after an extended period. Different systems and methods have been developed to monitor bone regeneration and fracture healing during and after the treatment. However, the developed systems have limitations and are yet to be used in MRA. The proposed smart reconstruction plate is a microdevice that could be used in MRA for wireless monitoring of fracture healing by measuring the forces applied to the reconstruction plate. The device is wireless and can transmit the acquired data to a human–machine interface or an application. The designed system is small and suitable for use in MRA. The results of finite element analysis, as well as experimental verification, showed the functionality of the proposed system in measuring small changes on the surface strain of the reconstruction plate and determining the corresponding load. By using the proposed system, continuous monitoring of bone regeneration and fracture healing in oral and maxillofacial areas is possible. Full article

Background and Objectives: Postoperative delirium (POD) is a frequent and severe complication following cardiac surgery, particularly in high-risk patients undergoing coronary artery bypass grafting (CABG) and aortic valve replacement (AVR). Despite extensive research, predicting POD remains challenging due to the multifactorial and often non-linear nature of its risk factors. This study aimed to improve POD prediction using an interpretable machine learning approach and to explore the combined effects of clinical, biochemical, and perioperative variables. Materials and Methods: This study included 131 patients who underwent CABG or AVR. POD occurrence was assessed using standard diagnostic criteria. Clinical, biochemical, and perioperative variables were collected, including patient age, sedation type, and mechanical ventilation status. Machine learning analysis was performed using an XGBoost classifier, with model interpretation achieved through SHapley Additive exPlanations (SHAP). Univariate logistic regression was applied to identify significant predictors, while SHAP analysis revealed variable interactions. Results: POD occurred in 34.3% of patients (n = 45). Patients who developed POD were significantly older (67.7 ± 6.5 vs. 64.5 ± 8.7 years, p = 0.020). Sedation with mechanical ventilation and the type of sedative used were strongly associated with POD (both p < 0.001). Sedation during mechanical ventilation showed the strongest association (OR = 2520.0; 95% CI: 80.9–78,506.7; p < 0.00001). XGBoost classifier achieved excellent performance (AUC = 0.998, accuracy = 97.6%, F1 score = 0.976). SHAP analysis identified sedation, mechanical ventilation, and their interactions with fibrinogen, troponin I, leukocyte parameters, and lung infection as key predictors. Conclusions: This study demonstrates that an interpretable machine learning approach can enhance POD prediction, providing insights into the combined impact of multiple clinical, biochemical, and perioperative factors. Integration of such models into perioperative workflows may enable early identification of high-risk patients and support individualized preventive strategies. Full article

This study uses the melt compounding method to recycle polypropylene-based car bumper waste (PP-CBW) in order to produce nanocomposite films for mulch application. The nanocomposite films were compounded by mixing virgin linear low-density polyethylene (LLDPE) with PP-CBW at a constant ratio of 4:1 in the presence of different percentages of nanofillers. Nanocomposites reinforced with nanoclays were compatibilized with an anhydride grafted polyethylene (PE-g-MAH), at a constant compatibilizer-to-clay ratio equal to 3, to improve the adherence between the nonpolar matrix and the hydrophilic nanoclay and acrylic paint present in the car bumper. An extruder with a corotating twin screw was used to produce blends of different compositions. To create nanocomposite films, the mixtures were further processed in a blown film extruder. The effect of the presence of nanoclays on the barrier, thermal, and mechanical properties of the nanocomposite films was investigated. The dispersion of clay layers in the matrix was examined by atomic force microscopy (AFM). The results indicate that 3 wt% of clay loading maximized the tensile strength in the transverse direction (TD) and machine direction (MD). A 1 wt% clay loading increased the MD tear resistance by 66% and manifested an optimum dart impact strength. Significant improvements in thermal and barrier properties were also achieved in the presence of 3 wt% clay loading. Full article

Background: Cardiovascular diseases (CVDs) are responsible for 32.4% of all deaths across the European Union (EU), and several CVD risk scores have been developed, with variable results. Retinal microvascular changes have been proposed as potential biomarkers for cardiovascular risk, especially in coronary heart diseases (CHDs). This study aims to identify the retinal microvascular features associated with CHDs and evaluate their potential use in a CHD screening algorithm in conjunction with traditional risk factors. Methods: We performed a two-center cross-sectional study on 120 adult participants—36 patients previously diagnosed with severe CHDs and scheduled for coronary artery bypass graft surgery (CHD group) and 84 healthy controls. A brief medical history and a clinical profile were available for all cases. All patients benefited from optical coherence tomography angiography (OCTA), the use of which allowed several parameters to be quantified for the foveal avascular zone and superficial and deep capillary plexuses. We evaluated the precision of several classification models in identifying patients with CHDs based on traditional risk factors and OCTA characteristics: a conventional logistic regression model and four machine learning algorithms: k-Nearest Neighbors (k-NN), Naive Bayes, Support Vector Machine (SVM) and supervised logistic regression. Results: Conventional multiple logistic regression had a classification accuracy of 78.7% based on traditional risk factors and retinal microvascular features, while machine learning algorithms had higher accuracies: 81% for K-NN and supervised logistic regression, 85.71% for Naive Bayes and 86% for SVM. Conclusions: Novel risk scores developed using machine learning algorithms and based on traditional risk factors and retinal microvascular characteristics could improve the identification of patients with CHDs. Full article

Background/Objectives: Solid organ transplantation remains a critical life-saving treatment for end-stage organ failure, yet it faces persistent challenges, such as organ scarcity, graft rejection, and postoperative complications. Artificial intelligence (AI) has the potential to address these challenges by revolutionizing transplantation practices. Methods: This review article explores the diverse applications of AI in solid organ transplantation, focusing on its impact on diagnostics, treatment, and the evolving market landscape. We discuss how machine learning, deep learning, and generative AI are harnessing vast datasets to predict transplant outcomes, personalized immunosuppressive regimens, and optimize patient selection. Additionally, we examine the ethical implications of AI in transplantation and highlight promising AI-driven innovations nearing FDA evaluation. Results: AI improves organ allocation processes, refines predictions for transplant outcomes, and enables tailored immunosuppressive regimens. These advancements contribute to better patient selection and enhance overall transplant success rates. Conclusions: By bridging the gap in organ availability and improving long-term transplant success, AI holds promise to significantly advance the field of solid organ transplantation. Full article

End-stage renal disease (ESRD) is a serious and lethal disease that carries with it a high morbidity and mortality rate if left untreated. Treating ESRD is conducted via renal replacement therapy and/or kidney transplantation, with the latter being the preferred option given the better outcomes and quality of life for the patients. However, as ESRD rises in prevalence, kidney transplantation rates remain largely unchanged. In every kidney transplantation, ischemia–reperfusion injury (IRI) is inevitable and the effect this has on the kidney depends based on donor type. IRI works through a variety of molecular mechanisms, primarily mitochondrial oxidative stress and programmed cell death mechanisms. Given the urgency to ensure the best outcomes for these limited kidney transplants, there has been a continued effort to find various potential therapeutic mechanisms to counteract IRI preoperatively, intraoperatively, and postoperatively. These include hypothermic machine perfusion, ischemic conditioning, nanoparticle removal of free radicals, peptide-based therapies, microRNA, and more. There is an ongoing effort to find the best way to mitigate IRI in kidney transplantation and this is being achieved through a better understanding of the molecular mechanisms of IRI. Full article