Search Results (6,409)

Drought is a complex environmental hazard to ecosystems and society. Decision-making on drought management options requires evaluating and predicting the extremity of future drought events. In this regard, quantifiable indices such as the standardized precipitation index (SPI), the standardized precipitation evapotranspiration index (SPEI), and the standardized streamflow index (SSI) have been commonly used to characterize meteorological and hydrological drought. In general, the estimation and prediction of the indices require an extensive range of precipitation (SPI and SPEI) and discharge (SSI) datasets in space and time domains. However, there is a challenge for long-term and spatially extensive data availability, leading to the insufficiency of data in estimating drought indices. In this regard, this study uses satellite precipitation data to estimate and predict the drought indices. SPI values were calculated from the precipitation data obtained from the Centre for Hydrometeorology and Remote Sensing (CHRS) data portal for a study water basin. This study employs a hydrological model for calculating discharge and drought in the overall basin. It uses random forest (RF) and support vector regression (SVR) as machine learning models for SSI prediction for time scales of 1- and 3-month periods, which are widely used for establishing interactions between predictors and predictands that are both linear and non-linear. This study aims to evaluate drought severity variation in the overall basin using the hydrological model and compare this result with the machine learning model’s results. The results from the prediction model, hydrological model, and the station data show better correlation. The coefficients of determination obtained for 1-month SSI are 0.842 and 0.696, and those for the 3-month SSI are 0.919 and 0.862 in the RF and SVR models, respectively. These results also revealed more precise predictions of machine learning models in the longer duration as compared to the shorter one, with the better prediction result being from the SVR model. The hydrological model-evaluated SSI has 0.885 and 0.826 coefficients of determination for the 1- and 3-month time durations, respectively. The results and discussion in this research will aid planners and decision-makers in managing hydrological droughts in basins. Full article

Background/Objectives: The recurrence of glioblastoma is an inevitable event in this disease’s course. In this study, we sought to identify the metabolomic signature in patients with recurrent glioblastomas undergoing surgery and radiation therapy. Methods: Blood samples collected prospectively from six patients with recurrent IDH-wildtype glioblastoma who underwent one surgery at diagnosis and a second surgery at relapse were analyzed using untargeted gas chromatography–time-of-flight mass spectrometry to measure metabolite abundance. The data analysis techniques included univariate analysis, correlation analysis, and a sample t-test. For predictive modeling, machine learning (ML) algorithms such as multinomial logistic regression, gradient boosting, and random forest were applied to predict the classification of samples in the correct treatment phase. Results: Comparing samples after the first surgery and after the relapse surgeries to the pre-operative samples showed a significant decrease in sorbitol and mannitol; there was a significant increase in urea, oxoproline, glucose, and alanine. After chemoradiation, two metabolites, erythritol and 6-deoxyglucitol, showed a decrease, with a cut-off of three and a significant reduction for 6-deoxyglucitol, while 2,4-difluorotoluene and 9-myristoleate showed an increase post radiation, with a fold-change cut-off of three. The gradient-boosting ML model achieved a high performance for the prediction of tumor conditions in patients with glioblastoma who had undergone relapse surgery. Conclusions: We developed an ML predictor for tumor phase based on the plasma metabolomic profile. Our study suggests the potential of combining metabolomics with ML as a new tool to stratify the risk of tumor progression in patients with glioblastoma. Full article

Due to model errors caused by local variations in cloud precipitation processes, there are still significant uncertainties in current predictions and simulations of short-duration heavy rainfall. To tackle this problem, the effects of warming on cloud-precipitation efficiency was analyzed utilizing a weather research and forecasting (WRF) model. The analysis focused on a rainstorm corridor event that took place in July 2020. Rainstorm events from 4–6 July formed a narrow rain belt with precipitation exceeded 300 mm in the middle and lower reaches of the Yangtze River. Temperature sensitivity tests revealed that warming intensified the potential temperature gradient between north and south, leading to stronger upward motion on the front. It also strengthened the southwest wind, which resulted in more pronounced precipitation peaks. Warming led to a stronger accumulation and release of convective instability energy. Convective available potential energy (CAPE) and convective inhibition (CIN) both increased correspondingly with the temperature. The precipitation efficiency increased sequentially with 2 °C warming to 27.4%, 31.2%, and 33.1%. Warming can affect the cloud precipitation efficiency by both promoting and suppressing convective activity, which may be one of the reasons for the enhancement of extreme precipitation under global warming. The diagnostic relationship between upward moisture flux and lower atmospheric stability during precipitation evolution was also revealed. Full article

Schizophrenia is a complex neuropsychiatric disorder characterized by disruptions in brain connectivity and cognitive functioning. Continuous monitoring of neural activity is essential, as it allows for the detection of subtle changes in brain connectivity patterns, which could provide early warnings of cognitive decline or symptom exacerbation, ultimately facilitating timely therapeutic interventions. This paper proposes a novel approach for detecting schizophrenia-related abnormalities using deep learning (DL) techniques applied to electroencephalogram (EEG) data. Using an openly available EEG dataset on schizophrenia, the focus is on preprocessed event-related potentials (ERPs) from key electrode sites and applied transfer entropy (TE) analysis to quantify the directional flow of information between brain regions. TE matrices were generated to capture neural connectivity patterns, which were then used as input for a hybrid DL model, combining convolutional neural networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The model achieved a performant accuracy of 99.94% in classifying schizophrenia-related abnormalities, demonstrating its potential for real-time mental health monitoring. The generated TE matrices revealed significant differences in connectivity between the two groups, particularly in frontal and central brain regions, which are critical for cognitive processing. These findings were further validated by correlating the results with EEG data obtained from the Muse 2 headband, emphasizing the potential for portable, non-invasive monitoring of schizophrenia in real-world settings. The final model, integrated into the NeuroPredict platform, offers a scalable solution for continuous mental health monitoring. By incorporating EEG data, heart rate, sleep patterns, and environmental metrics, NeuroPredict facilitates early detection and personalized interventions for schizophrenia patients. Full article

(1) Background: donor-derived circulating free DNA (dd-cfDNA), an innovative biomarker with great potential for the early identification and prevention of graft damage. (2) Methods: Samples were collected prospectively and the study was performed retrospectively to analyze dd-cfDNA plasma levels in 30 kidney transplant patients during their post-transplant follow-up (15 days, 3, 6, and 9 months), to determine if the result could be of interest in the identification of possible adverse events, especially rejection. The aim was to verify whether the data on sensitivity, specificity, NPV, and PPV compare with reference values and creatinine values. (3) Results: We observed levels of dd cfDNA > 1% in six of nine patients with active rejection (ABMR or TCMR) and elevated values (>0.5%) in two other patients in this rejection group. Our results show low values of sensitivity = 50%, specificity = 61.11%, rejection NPV = 64.71%, and rejection PPV = 46.13% of the technique compared to reference values previously published. With respect to creatinine, only for TCRM, we observed better results for dd-cfDNA in these parameters than in creatinine. Also, our data suggest that dd-cfDNA could help to differentiate those patients with dnDSAs that are going to through rejection better than creatinine, specially at 15 d post transplant. In this study, this appears to have no positive predictive value for borderline rejection (BR) or TCMR IA. (4) Conclusions: plasma levels of dd-cfDNA could be considered an additional or alternative biomarker for graft rejection monitoring in early post-kidney transplant up to several months before its clinical presentation, especially for patients with suspected TCMR or ABMR. Full article

Monitoring of operations has become a critical activity in forestry, aiming to provide the data required by planning and production management. Conventional methods, on the other hand, come at a high expense of resources. A neural network was trained, validated, and tested in this study based on multi-modal data to classify relevant operational events in mechanized weed control operations. The architecture of a neural network was tuned in terms of the number of hidden layers and neurons, and the regularization term was set at various values to obtain optimally tuned models for three data modalities: triaxial acceleration data coupled with speed extracted from GNSS signals (AS), triaxial acceleration (A), and speed alone (S). In the training and validation phase, the models based on AS and A achieved a very high classification accuracy, accounting for 92 to 93% when considering four relevant events. In the testing phase, which was run on unseen data, the classification accuracy reached figures of 91 to 92%, indicating a good generalization ability of the models. The results point out that multimodal data are able to provide the features for distinguishing events and add spatial context to the monitored operations, standing as a suitable solution for offline, partly automated monitoring. Future studies are required to see how the capabilities of online, real-time technologies such as deep learning coupled with computer vision can add more context and improve classification performance. Full article

A new concept of time, termed natural time, was introduced in 2001. This new concept reveals unique dynamic features hidden behind time-series originating from complex systems. In particular, it was shown that the analysis of natural time enables the study of the dynamical evolution of a complex system and identifies when the system enters a critical stage. Hence, natural time plays a key role in predicting impending catastrophic events in general. Several such examples were published in a monograph in 2011, while more recent applications were compiled in the chapters of a new monograph that appeared in 2023. Here, we summarize the application of natural time analysis in various complex systems, and we review the most recent findings of natural time analysis that were not included in the previously published monographs. Specifically, we present examples of data analysis in this new time domain across diverse fields, including condensed-matter physics, geophysics, earthquakes, volcanology, atmospheric sciences, cardiology, engineering, and economics. Full article

Fall risk assessment is becoming an important concern, with the realization that falls, and more importantly fainting occurrences, in most cases require immediate medical attention and can pose huge health risks, as well as financial and social burdens. The development of an accurate inertial sensor-based fall risk assessment tool combined with machine learning algorithms could significantly advance healthcare. This research aims to investigate the development of a machine learning approach for falling and fainting detection, using wearable sensors with an emphasis on forward falls. In the current paper we address the problem of the lack of inertial time-series data to differentiate the forward fall event from normal activities, which are difficult to obtain from real subjects. To solve this problem, we proposed a forward dynamics method to generate necessary training data using the OpenSim software, version 4.5. To develop a model as close to the real world as possible, anthropometric data taken from the literature was used. The raw X and Y axes acceleration data was generated using OpenSim software, and ML fall prediction methods were trained. The machine learning (ML) accuracy was validated by testing with data acquired from six unique volunteers, considering the forward fall type. Full article

Resilience has been used as a building performance metric that measures the building’s capability of absorption, response, and recovery from one or a series of disruptive events, e.g., extreme weather events or power outage events. With respect to resilience, in relation to the moisture performance of the building envelope (moisture resilience), this aspect has not yet been thoroughly explored nor defined. Given the expected increase in annual precipitation in certain regions of Canada as induced by climate change effects occurring both currently and in the future, the moisture resilience of building envelops will require immediate attention given that wall assemblies of buildings are predicted to be subjected to excessive moisture loads in the coming years. In this study, the moisture resilience of wood frame wall assemblies to mould growth was described from three aspects: (i) absorption—the ability of the wall to maintain a low level of relative humidity on the OSB; (ii) response—the fluctuation of the relative humidity on the OSB; and (iii) recovery—the rate at which the relative humidity recovers to an acceptable level. The metrics used to demonstrate the relative impact of these factors on moisture performance were also developed. The results have revealed a robust correlation between moisture performance and the relative influence of various newly defined aspects of moisture resilience. Full article

Background: Artificial intelligence has become a valuable tool for diagnosing and detecting postoperative complications early. Through imaging and biochemical markers, clinicians can anticipate the clinical progression of patients and the risk of long-term complications that could impact the quality of life or even be life-threatening. In this context, artificial intelligence is crucial for identifying early signs of complications and enabling clinicians to take preventive measures before problems worsen. Materials and methods: This observational study analyzed medical charts from the electronic archive of the Clinical Emergency Hospital in Galați, Romania, covering a four-year period from 2018 to 2022. A neural network model was developed to analyze various socio-demographic and paraclinical data. Key features included patient demographics, laboratory investigations, and clinical outcomes. Statistical analyses were performed to identify significant risk factors associated with deep venous thrombosis (DVT). Results: The analysis revealed a higher prevalence of female patients (60.78%) compared to male patients, indicating a potential gender-related risk factor for DVT. The incidence of DVT was highest among patients aged 71 to 90 years, affecting 56.86% of individuals in this age group, suggesting that advanced age significantly contributes to the risk of developing DVT. Additionally, among the DVT patients, 15.69% had a body mass index (BMI) greater than 30, categorizing them as obese, which is known to increase the risk of thrombotic events. Furthermore, this study highlighted that the highest frequency of DVT was associated with femur fractures, occurring in 52% of patients with this type of injury. The neural network analysis indicated that elevated levels of direct bilirubin (≥1.5 mg/dL) and prothrombin activity (≤60%) were strong predictors of fracture-related complications, with sensitivity and specificity rates of 78% and 82%, respectively. These findings underscore the importance of monitoring these laboratory markers in at-risk populations for early intervention. Conclusions: This study identified critical risk factors for developing DVT, including advanced age, high BMI, and femur fractures, which necessitate longer recovery periods. Additionally, the findings indicate that elevated direct bilirubin and prothrombin activity play a significant role in predicting DVT development. These results suggest that AI can effectively enhance the anticipation of clinical evolution in patients, aiding in early intervention and management strategies. Full article

Reflex syncope (RS) is the most prevalent form of syncope, yet its pathophysiology and clinical presentation are not well understood. Despite controversy, the ‘ventricular theory’ remains the most plausible hypothesis to explain RS in susceptible patients. Certain assumptions regarding the geometry and function of the heart are essential in supporting this theory. Given these considerations, the goal of this review was to try to integrate data on heart morphology and function in a phenotype of a patient susceptible to RS. Previous research suggests that a small left ventricle and atria, in addition to a normo- or hypercontractile myocardium, predispose to more syncopal events. These findings have been confirmed in different subsets of patients, including those with small heart and chronic fatigue syndrome, highlighting common pathophysiologic pathways in these subgroups of population. Heart geometry and function seem to play a role in different treatment strategies for RS patients, including the administration of medications, pacing, and possibly cardioneural ablation. In addition, parameters related to the geometry of the heart chambers and of the electrical activation of the heart seem to have predictive value for syncope recurrence. These parameters could be included in the future and improve the accuracy of predictive models for RS. Full article

Background: Heart failure (HF) is a chronic disease with a steadily increasing prevalence, high mortality, and social and economic costs. Furthermore, every hospitalization for acute HF is associated with worsening prognosis and reduced life expectancy. In order to prevent hospitalizations, it would be useful to have instruments that can predict them well in advance. Methods: We performed a review on remote monitoring of heart failure through implantable devices. Results: Precise multi-parameter algorithms, available for ICD and CRT-D patients, have been created, which also use artificial intelligence and are able to predict a new heart failure event more than 30 days in advance. There are also implantable pulmonary artery devices that can predict hospitalizations and reduce the impact of heart failure. The proper organization of transmission and alert management is crucial for clinical success in using these tools. Conclusions: The full implementation of remote monitoring of implantable devices, and in particular, the use of new algorithms for the prediction of acute heart failure episodes, represents a huge challenge but also a huge opportunity. Full article

Oxidative stress and inflammation accompany endothelial dysfunction that results from the excessive or uncontrolled production of reactive oxygen and nitrogen species (RONS) in older adults. This study was designed to assess the usefulness of serum oxi-inflammatory component combinations in vascular disease prediction and prevention with regard to sex. Women (n = 145) and men (n = 50) aged 72.2 ± 7.8 years participated in this project. The females demonstrated the elevated production of hydrogen peroxide (H₂O₂₎ and nitric oxide (NO) responsible for intravascular low-density lipoprotein oxidation. NO generation was enhanced in the women, but its bioavailability was reduced, which was expressed by a high 3-nitrotyrosine (3-NitroT) concentration. The relation of NO/3-NitroT (r_s = 0.811, p < 0.001) in the women and NO/3-NitroT (r_s = −0.611, p < 0.001) in the men showed that sex determines endothelial dysfunction. RONS generation in the women simultaneously promoted endothelial regeneration, as demonstrated by a ~1.5-fold increase in circulating progenitor cells. Inflammation-specific variables, such as the neutrophil-to-lymphocyte ratio, the systemic immune inflammation index, and the neutrophil-to-high-density lipoprotein (HDL) ratio, were reduced in the women and showed their diagnostic utility for clinical prognosis in vascular dysfunction, especially the C-reactive-protein-to-HDL ratio (AUC = 0.980, specificity 94.7%, sensitivity 93.3%, OR = 252, 95% CI 65–967, p < 0.001). This study is the first to have revealed sex-specific changes in the oxi-inflammatory response, which can generate the risk of cardiovascular events at an older age. Full article

Rill erosion is a major issue on a global scale, and predicting the presence, position, and development of erosive forms on hillslopes is a significant challenge for the scientific community. Several plot-scale investigations confirmed the reliability of the terrestrial photogrammetric (TP) technique for studying rill erosion and the reliability of a method for extracting the rill network from Digital Surface Models (DSMs) and measuring the corresponding volume. In this paper, for an intense erosive event that occurred at the Sparacia experimental area (Sicily, Southern Italy), TP surveys of three plots, with different length and steepness, incised by rills, were performed to reconstruct the DSMs. For each plot, the rill network was extracted from the DSMs, and the non-contributing network was distinguished from the contributing one, from which the soil loss and the consequent eroded volumes V were determined. The specific aims were to (i) establish the effect of plot steepness on rill depths and some morphometric characteristics of the drainage rill network; (ii) test and calibrate the relationship between V and the total rill length L, using all rill measurements available in the literature and those obtained in this study; and (iii) modify the V–L relationship by including climate forcing and assessing the related performance. The rill depths, h, the drainage frequency, and drainage density of the rill networks detected in the three plots were compared. The analysis demonstrated that h and the morphometric parameters of the contributing rill network increase with plot steepness s. In particular, the mean depth increases from 2.79 to 4.85 cm for slope increasing from 14.9 to 26%. Moreover, the drainage frequency of the contributing rill network varies from 0.16 m⁻² for s = 14.9% to 0.47 m⁻² for s = 26%, while the drainage density of the contributing rill network varies from 0.92 m⁻¹ for s = 14.9% to 2.1 m⁻¹ for s = 26%. Finally, using the data available in the literature and those obtained in this investigation, an empirical relationship between V and the total rill length L was firstly tested and then rearranged considering the event rainfall erosivity R_e. Including R_e in the rearranged equation guaranteed the best performance in V estimation. Full article

Wind shear presents a considerable hazard to aviation safety, especially during the critical phases of takeoff and landing. Accurate forecasting of wind shear events is essential to mitigate these risks and improve both flight safety and operational efficiency. This paper introduces a hybrid Temporal Convolutional Networks and Tree-Based Models (TCNs-TBMs) framework specifically designed for time series modeling and the prediction of wind shear intensity. The framework utilizes the ability of TCNs to capture intricate temporal patterns and integrates it with the predictive strengths of TBMs, such as Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Categorical Boosting (CatBoost), resulting in robust forecast. To ensure optimal performance, hyperparameter tuning was performed using the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), enhancing predictive accuracy. The effectiveness of the framework is validated through comparative analyses with standalone machine learning models such as XGBoost, RF, and CatBoost. The proposed TCN-XGBoost model outperformed these alternatives, achieving a lower Root Mean Squared Error (RMSE: 1.95 for training, 1.97 for testing), Mean Absolute Error (MAE: 1.41 for training, 1.39 for testing), and Mean Absolute Percentage Error (MAPE: 7.90% for training, 7.89% for testing). Furthermore, the uncertainty analysis demonstrated the model’s reliability, with a lower mean uncertainty (7.14 × 10⁻⁸) and standard deviation of uncertainty (6.48 × 10⁻⁸) compared to other models. These results highlight the potential of the TCNs-TBMs framework to significantly enhance the accuracy of wind shear intensity predictions, emphasizing the value of advanced time series modeling techniques for risk management and decision-making in the aviation industry. This study highlights the framework’s broader applicability to other meteorological forecasting tasks, contributing to aviation safety worldwide. Full article