Search Results (152)

Over the past four decades, cardioprotective research has revealed an extraordinary complexity of cellular and molecular mechanisms capable of mitigating ischemia/reperfusion injury (IRI). Among these, ischemic conditioning has emerged as one of the most influential discoveries: brief episodes of ischemia followed by reperfusion activate protective programs that reduce myocardial damage. These effects can be elicited locally (pre- or postconditioning) or remotely (remote conditioning), acting mainly through paracrine signaling and mitochondria-linked kinase pathways, with both early and delayed windows of protection. We have contributed to clarifying the roles of mitochondria, oxidative stress, prosurvival kinases, connexins, extracellular vesicles, and sterile inflammation, particularly via activation of the NLRP3 inflammasome. Despite robust preclinical evidence, clinical translation of these approaches has remained disappointing. The challenges largely stem from experimental models that poorly reflect real-world clinical settings—such as advanced age, comorbidities, and multidrug therapy—as well as the reliance on surrogate endpoints that do not reliably predict clinical outcomes. Nevertheless, interest in multi-target protective strategies remains strong. New lines of investigation are focusing on emerging mediators—such as gasotransmitters, extracellular vesicles, and endogenous peptides—as well as targeted modulation of inflammatory responses. Future perspectives point toward personalized cardioprotection tailored to patient metabolic and immune profiles, with special attention to high-risk populations in whom IRI continues to represent a major clinical challenge. Full article

This paper presents Feedback-Based Validation Learning (FBVL), a novel approach that transforms the role of validation datasets in deep learning. Unlike conventional methods that utilize validation datasets for performance evaluation post-training, FBVL integrates these datasets into the training process. It employs real-time feedback to optimize the model’s weight adjustments, enhancing prediction accuracy and overall model performance. Importantly, FBVL preserves the integrity of the validation process by using prediction outcomes on the validation dataset to guide training adjustments, without directly accessing the dataset. Our empirical study conducted using the Iris dataset demonstrated the effectiveness of FBVL. The Iris dataset, comprising 150 samples from three species of Iris flowers, each characterized by four features, served as an ideal testbed for demonstrating FBVL’s effectiveness. The implementation of FBVL led to substantial performance improvements, surpassing the accuracy of the previous best result by approximately 7.14% and achieving a loss reduction greater than the previous methods by approximately 49.18%. When FBVL was applied to the Multimodal EmotionLines Dataset (MELD), it showcased its wide applicability across various datasets and domains. The model achieved a test-set accuracy of 70.08%, surpassing the previous best-reported accuracy by approximately 3.12%. These remarkable results underscore FBVL’s ability to optimize performance on established datasets and its capacity to minimize loss. Using our FBVL method, we achieved a test set f1_score micro of 70.07%, which is higher than the previous best-reported value for f1_score micro of 67.59%. These results demonstrate that FBVL enhances classification accuracy and model generalization, particularly in scenarios involving small or imbalanced datasets, offering practical benefits for designing more efficient and robust neural network architectures. Full article

Pavement performance models are considered a key element in pavement management systems since they can predict the future condition of pavements using historical data. Several indicators are used to evaluate the condition of pavements (such as the pavement condition index, rutting depth, and cracking severity), and the international roughness index (IRI), which is the most widely employed worldwide. This study aimed to develop an accurate IRI prediction model. Ten prediction methods were trained on a dataset of 35 independent variables. The performance of the methods was compared, and the light gradient boosting machine was identified as the best-performing method for IRI prediction. Then, the SHAP was synchronized with the best-performing method to prioritize variables based on their relative influence on IRI. The results suggested that initial IRI, mean annual temperature, and the duration between data collections had the strongest relative influence on IRI prediction. Another objective of this study was to determine the optimal uncertainty model for IRI prediction. In this regard, 12 uncertainty models were developed based on different conformal prediction methods. Gray relational analysis was performed to identify the optimal uncertainty model. The results showed that Minmax/80 was the optimal uncertainty model for IRI prediction, with an effective coverage of 93.4% and an average interval width of 0.256 m/km. Finally, a further analysis was performed on the outcomes of the optimal uncertainty model, and initial IRI, duration, annual precipitation, and a few distress parameters were identified as uncertain. The results of the framework indicate in which situations the predicted IRI may be unreliable. Full article

In recent decades, numerous studies have investigated the application of Artificial Intelligence (AI), and more precisely of Artificial Neural Networks (ANNs), in the prediction of complex technical parameters, particularly in the field of road infrastructure management. Among them, prediction of the widely used International Roughness Index (IRI) has attracted much attention due to its importance in pavement maintenance planning. This study focuses on predicting future IRI values using traditional regression models and neural networks, specifically Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) networks, on two highway sections, each analyzed in two experimental setups. The models consider only traffic and structural road characteristics as variables. The results show that the LSTM method provides significantly lower prediction errors for both highway sections, indicating better performance in capturing roughness trends over time. These results confirm that ANNs are a useful tool for engineers by predicting future IRI values, as they help to extend pavement life and reduce overall maintenance costs. The integration of machine learning into pavement evaluation is a promising step forward in ongoing efforts to optimize pavement management. Full article

Background/Objectives: Different surgical techniques are available in cases of missing or insufficient capsular bag support. Next to the anterior chamber or iris-fixated intraocular lenses (IOL), the implantation of the Carlevale IOL provides a sutureless and scleral fixated treatment method. Methods: In a retrospective single-center study, the perioperative data of 100 patients who consecutively received a scleral fixated Carlevale IOL combined with a 25 gauge (G) pars plana vitrectomy between September 2021 and June 2024 were investigated. The intraoperative and postoperative results were analyzed in terms of complication rates and refractive outcomes. Results: IOL dislocation was the most common surgical indication (50%) for sutureless Carlevale IOL implantation, followed by postoperative aphakia in 35 patients (35%). Nearly every fourth patient (24%) had a preoperative traumatic event, and 21% had pseudoexfoliation (PEX) syndrome. The average surgery time was 60.2 (±20.1) min. Intraoperative intraocular hemorrhage occurred in seven cases, and IOL haptic breakage in two patients. Temporary intraocular pressure fluctuations represented the most common postoperative complications (28%). Severe complications such as endophthalmitis or retinal detachment were not observed in our cohort. The mean refractive prediction error was determined in 67 patients and amounted to an average of −0.7 ± 2.0 diopters. The best corrected visual acuity (BCVA) at the last postoperative follow-up showed an improvement of 0.2 ± 0.5 logMAR (n = 76) compared to the preoperative BCVA (p = 0.0002). The postoperative examination was performed in 72% of the patients, and the mean follow-up period amounted to 7.2 ± 6.4 months. Conclusions: Overall, sutureless and scleral fixated implantation of the Carlevale IOL represents a valuable therapeutic option in the treatment of aphakia and lens as well as IOL dislocation in the absence of capsular bag support with minor postoperative complications and positive refractive outcomes. Full article

Predicting the behaviour of the Earth’s ionosphere is crucial for the ground-based and spaceborne technologies that rely on it. This paper presents a novel way of inferring ionospheric electron density profiles and electron temperature profiles using machine learning. The analysis is based on the Nearest Neighbour (NNB) and Radial Basis Function (RBF) regression models. Synthetic data sets used to train and validate these two inference models are constructed using the International Reference Ionosphere (IRI 2020) model with randomly chosen years (1987–2022), months (1–12), days (1–31), latitudes (−60 to 60°), longitudes (0, 360°), and times (0–23 h), at altitudes ranging from 95 to 600 km. The NNB and RBF models use the constructed ionosonde-like profiles to infer complete ISR-like profiles. The results show that the inference of ionospheric electron density profiles is better with the NNB model than with the RBF model, while the RBF model is better at inferring the electron temperature profiles. A major and unexpected finding of this research is the ability of the two models to infer full electron temperature profiles that are not provided by ionosondes using the same truncated electron density data set used to infer electron density profiles. NNB and RBF models generally over- or underestimate the inferred electron density and electron temperature values, especially at higher altitudes, but they tend to produce good matches at lower altitudes. Additionally, maximum absolute relative errors for electron density and temperature inferences are found at higher altitudes for both NNB and RBF models. Full article

Gait refers to the walking pattern of an individual and it varies from person to person. Consequently, it can be considered to be a biometric feature, similar to the face, iris, or fingerprints, and can easily be used for human identification purposes. Person identification using gait analysis has direct applications in user authentication, visual surveillance and monitoring, and access control—to name a few. Naturally, gait analysis has attracted many researchers both from academia and industry over the past few decades. Within a small population, the accuracy of person identification could be very high; however, with the growing number of people in a given gait database, identifying a person only from gait becomes a daunting task. Hence, the focus of researchers in this field has exhibited a paradigm shift to a broader problem of sex and age prediction using different biometric parameters—with gait analysis obviously being one of them. Recent works on sex and age prediction using gait pattern obtained from the inertial sensors lacks an analysis of the features being used. In this paper, we propose a number of features inherent to gait data and analyze key features from the time–series data of accelerometer and gyroscopes for the automatic recognition of sex and the prediction of age. We have trained various traditional machine learning models and achieved the highest accuracy of 94% in sex prediction and an $R^2$ score of 0.83 in age estimation. Full article

This study proposes a deep learning-based vertical decomposition model for ionospheric Total Electron Content (TEC), which establishes a nonlinear mapping from macroscale TEC data to vertically layered electron density (Ne) spanning 60–800 km by integrating geomagnetic indices (AE, SYM-H) and solar activity parameters (F10.7). Utilizing global TEC grid data (spatiotemporal resolution: 1 h/5.625° × 2.8125°) provided by the International GNSS Service (IGS), a Multilayer Perceptron (MLP) model was developed, taking spatiotemporal coordinates, altitude, and space environment parameters as inputs to predict logarithmic electron density ln(Ne). Experimental validation against COSMIC-2 radio occultation observations in 2019 demonstrates the model’s capability to capture ionospheric vertical structures, with a prediction performance significantly outperforming the International Reference Ionosphere model IRI-2020: root mean square error (RMSE) decreased by 34.16%, and the coefficient of determination (R²) increased by 28.45%. This method overcomes the reliance of traditional electron density inversion on costly radar or satellite observations, enabling high-spatiotemporal-resolution global ionospheric profile reconstruction using widely available GNSS-TEC data. It provides a novel tool for space weather warning and shortwave communication optimization. Current limitations include insufficient physical interpretability and prediction uncertainty in GNSS-sparse regions, which could be mitigated in future work through the integration of physical constraints and multi-source data assimilation. Full article

Subclinical chronic kidney disease (sCKD) predisposes one to acute kidney injury (AKI) and chronic kidney disease (CKD). Reduced kidney functional reserve (KFR) detects sCKD in preclinical studies and predicts AKI after cardiac surgery. We evaluated renal protection in a rat model of kidney injury where ischaemia–reperfusion injury (IRI) was induced after sCKD. Dual treatment boosting nicotinamide adenine dinucleotide (NAD) by nicotinamide riboside (NR) combined with the mitochondria-targeted antioxidant SkQR1 protected the KFR and reduced structural kidney damage, including markers of vascular integrity and the relative blood volume (rBV). The dual treatment upregulated Sirt1 and Nrf2, increased the nuclear localisation of the mitochondrial biogenesis regulator PGC-1α and the mitochondrial protein marker COX4, and upregulated the antioxidant gene NOQ1. These observations suggest mitochondrial protection and modulation of the cellular redox state provided long-term structural and functional protection against kidney injury superimposed on background sCKD. Full article

Objectives: Intraocular lens dislocation is a well-recognized complication of cataract surgery, necessitating secondary interventions such as retropupillary iris-claw IOL implantation. While effective, this procedure requires larger incisions that may induce significant astigmatism. This study aimed to (1) evaluate anterior chamber changes following retropupillary ICIOL implantation and (2) compare surgically induced astigmatism between corneal and scleral incision techniques. Methods: In this prospective cohort study, patients with IOL dislocation underwent 25-gauge pars plana vitrectomy with ICIOL implantation. Anterior chamber depth, volume, and angle configuration were measured across 12 meridians preoperatively, at 1–1.5 months (short-term), and 5–6 months (long-term). Surgically induced astigmatism was compared between the corneal and scleral incision groups. Statistical analysis included Shapiro–Wilk, Mann–Whitney U, and repeated-measures ANOVA tests. Results: This prospective study included 40 patients (22 females, 18 males) with a mean age of 76.3 ± 5.38 years (range 65–86). Significant reductions in ACD and ACV occurred postoperatively (p < 0.05), with partial recovery at long-term follow up. Surgically induced astigmatism was markedly higher with corneal incisions versus scleral approaches (p < 0.01 short term; p < 0.05 long term). Anterior chamber angle changes varied by meridian but stabilized by 6 months. Conclusions: Retropupillary ICIOL implantation induces predictable anterior segment remodeling, with scleral incisions offering superior refractive stability. Surgical planning should prioritize scleral techniques to minimize surgically induced astigmatism while maintaining anatomical efficacy. Future innovations in IOL design may further reduce incision-related complications. Full article

Understanding the depth and severity of corrosion is crucial for predicting the long-term durability and economic viability of Zn-based structures. This study investigates the relationship between meteorological and pollution parameters on the corrosion rate of zinc using an artificial neural network (ANN) model trained on global data. The model incorporates temperature, time of wetness (TOW), SO₂ concentration, Cl⁻ concentration, and exposure time as input variables, with corrosion depth as the output. The ANN model demonstrated high predictive accuracy, achieving correlation coefficients of 0.99 and 0.95 for the training and test datasets, respectively, indicating strong agreement with the experimental data. A graphical user interface was developed to facilitate the practical application of the model. Sensitivity analysis using the index of relative importance (IRI) identified the SO₂ concentration and TOW as the most influential factors, emphasizing their critical role in zinc corrosion. These findings enhance our understanding of the Zn corrosion dynamics and provide valuable insights into corrosion prevention strategies. A user-friendly graphical user interface (GUI) was developed using Java, enabling accurate prediction of the corrosion depth in zinc with approximately 95% accuracy without requiring prior knowledge of neural networks or programming. Full article

Background/Objectives: To assess the association of residential-level maternal particulate matter of 2.5 μm diameter or less (PM_2.5) exposure during pregnancy with anterior segment dysgenesis (ASD) risk. Methods: This study used data from children diagnosed with ASD (i.e., aniridia, iris hypoplasia, Peters anomaly, Axenfeld–Rieger syndrome, or primary congenital glaucoma) by an experienced pediatric ophthalmologist at a National Referral Center for Rare Diseases between 2004 and 2021 and their biological mothers. Individual PM_2.5 exposure concentration was assessed by reference to residential addresses and district-specific PM_2.5 concentrations predicted by the universal Kriging prediction model. Results: The study included 2328 children (582 ASD cases and 1746 controls [1:3 matched for birth year, sex, and birth-place]). The mean (SD) annual PM_2.5 exposure was 29.2 (16.9) μg/m³. An IQR increase in PM_2.5 during the preconception period (11.6 μg/m³; RR, 1.18; 95% CI, 1.03–1.34), the 1st trimester (11.1 μg/m³; RR, 1.15; 95% CI, 1.03–1.27), and the 2nd trimester (11.2 μg/m³; RR 1.14; 95% CI, 1.01–1.29) significantly increased ASD risk. Meanwhile, the association between IQR increase in PM_2.5 during the 3rd trimester and ASD risk showed borderline significance (11.0 μg/m³; RR, 1.10; 95% CI, 0.99–1.21). An IQR increase in PM_2.5 (6.9 μg/m³) from the preconception period to the 3rd trimester was associated with a significantly increased risk of ASD (RR, 1.13; 95% CI, 1.08–1.20). Conclusions: The findings of this study suggest that PM_2.5 exposure during the preconception period and pregnancy is associated with increased risk of ASD, supporting a need for further improvements in air quality to prevent congenital ocular anomalies. Full article

The heat treatment process of Ti-6Al-4V alloy alters its microstructural features such as prior-β grain size, Widmanstatten α lath thickness, Widmanstatten α volume fraction, grain boundary α lath thickness, total α volume fraction, α colony size, and α platelet length. These microstructural features affect the material’s mechanical properties (UTS, YS, and %EL). The relationship between microstructural features and mechanical properties is very complex and non-linear. To understand these relationships, we developed an artificial neural network (ANN) model using experimental datasets. The microstructural features are used as input parameters to feed the model and the mechanical properties (UTS, YS, and %EL) are the output parameters. The influence of microstructural parameters was investigated by the index of relative importance (IRI). The mean edge length, colony scale factor, α lath thickness, and volume fraction affect UTS more. The model-predicted results show that the UTS of Ti-6Al-4V decreases with the increase in prior β grain size, Widmanstatten α lath thickness, grain boundaries α thickness, colony scale factor, and UTS increases with mean edge length. Full article

This study proposes an explainable extreme gradient boosting (XGBoost) model for predicting the international roughness index (IRI) and identifying the key influencing factors. A comprehensive dataset integrating multiple data sources, such as structure, climate and traffic load, is constructed. A voting-based feature selection strategy is adopted to identify the key influencing factors, which are used as inputs for the prediction model. Multiple machine learning (ML) models are trained to predict the IRI with the constructed dataset, and the XGBoost model performs the best with the coefficient of determination ($R^2$) reaching 0.778. Finally, interpretable techniques including feature importance, Shapley additive explanations (SHAP) and partial dependency plots (PDPs) are employed to reveal the mechanism of influencing factors on IRI. The results demonstrate that climate conditions and traffic load play a critical role in the deterioration of IRI. This study provides a relatively universal perspective for IRI prediction and key factor identification, and the outputs of the proposed method contribute to making scientific maintenance strategies of roads to some extent. Full article

Background: Cardiac arrest (CA) is a leading cause of mortality and morbidity, with survivors often developing post-cardiac arrest syndrome (PCAS), characterized by systemic inflammation, ischemia–reperfusion injury (IRI), and multiorgan dysfunction. Acute kidney injury (AKI), a frequent complication, is associated with increased mortality and prolonged intensive care unit (ICU) stays. This study evaluates AKI incidence and progression in cardiac arrest patients managed with different temperature protocols and explores urinary biomarkers’ predictive value for AKI risk. Methods: A prospective, single-center observational study was conducted, including patients with Return of Spontaneous Circulation (ROSC) post-cardiac arrest. Patients were stratified into three groups: therapeutic hypothermia (TH) at 33 °C, Targeted Temperature Management (TTM) at 35 °C, and no temperature management (No TTM). AKI was defined using KDIGO criteria, with serum creatinine and urinary biomarkers (TIMP-2 and IGFBP7) measured at regular intervals during ICU stay. Results: AKI incidence at 72 h was 31%, varying across protocols. It was higher in the No TTM group at 24 h and in the TH and TTM groups during rewarming. Persistent serum creatinine elevation and fluid imbalance were notable in the TH group. Biomarkers indicated moderate tubular stress in the TTM and No TTM groups. Conclusions: AKI is a frequent complication post-cardiac arrest, with the rewarming phase identified as critical for renal vulnerability. Tailored renal monitoring, biomarker-guided risk assessment, and precise temperature protocols are essential to improve outcomes. Full article