Search Results (691)

Residual congestion (RC) at discharge predicts adverse outcomes in heart failure with reduced ejection fraction (HFrEF). Its impact on the implementation of guideline-directed medical therapies (GDMT) remains unclear. N-terminal pro-B-type natriuretic peptide (NT-proBNP) trajectory during hospitalisation reflects RC and may be associated with GDMT implementation. The aim was to assess whether discharge NT-proBNP and a fall in NT-proBNP < 30% during hospitalisation (ΔNT-proBNP < 30%) predict GDMT underuse in acute HFrEF. In this prospective observational study, NT-proBNP was measured at hospital admission and 48–72 h before discharge. Provision of individual GDMT drug classes was assessed and GDMT underuse was defined as prescription of <3 key GDMT drug classes at discharge. 391 HFrEF patients (mean age, 69.9 ± 13.1years, 67.3% male) were included. ΔNT-proBNP < 30% was identified in 108 (27.6%). Higher discharge NT-proBNP was independently associated with lower likelihood of prescribing ACE-inhibitors, sacubitril/valsartan, eplerenone/spironolactone, or empagliflozin/dapagliflozin. ΔNT-proBNP < 30% was associated with 17% higher odds of GDMT underuse (95% confidence interval, 1.10–1.31, p < 0.001), regardless of clinical characteristics or in-hospital management. Patients with ΔNT-proBNP < 30% were discharged on lower doses of titratable GDMT medications. In-hospital NT-proBNP burden and trajectory, as markers of RC, are associated with GDMT underutilisation at discharge in acute HFrEF. Addressing RC may impact treatment quality in acute HFrEF. Full article

Background/Objectives: Endoscopic variceal ligation (EVL) is a common treatment for preventing variceal bleeding in patients with advanced chronic liver disease (ACLD). However, its acute hemodynamic impact is typically assessed using invasive methods, and there is data on short-term spleen stiffness (SS) dynamics are limited. This pilot study aimed to quantify short-interval changes in liver stiffness (LS) and SS following EVL using transient elastography (TE), and to explore their associations with clinical and laboratory parameters. Methods: This prospective observational study enrolled adults with advanced liver disease undergoing esophagogastroduodenoscopy (EGD) with or without EVL at a tertiary center. Liver and spleen TE were performed in a fasted state immediately before endoscopy and repeated within 12 h after EVL. Organ-specific probes and predefined quality criteria were used, and non-parametric methods were applied to assess within-patient changes and correlations. Results: Fifty patients were included in the study: 21 underwent EVL, while the remaining 29 underwent diagnostic endoscopies only. The most common cause was alcohol-related liver disease. Within the EVL subgroup, the median liver stiffness (LSM) increased from 27.6 kPa to 45.1 kPa, and the median spleen stiffness (SSM) increased from 59.9 kPa to 98.3 kPa, both within 12 h. While these increases showed a uniform direction, they did not reach statistical significance. A higher baseline SS predicted a greater LS increase, and stiffness measures correlated with creatinine, disease duration, Child–Pugh class, albumin and ascites. Conclusions: Short-term increases in liver and spleen stiffness following EVL are consistent with acute hemodynamic alterations, such as increased hepatic perfusion and splenic congestion, rather than structural remodeling. These findings, beyond changes in stiffness alone, support the feasibility of integrating TE, particularly the measurement of SS, into early peri-procedural hemodynamic surveillance after EVL. They also justify larger studies with serial time points and direct portal pressure validation. Full article

Background: Chronic obstructive pulmonary disease (COPD) is a major cause of morbidity, mortality, and healthcare utilization. Lung volume reduction surgery improves outcomes in a select cohort but portends high morbidity. Bronchoscopic lung volume reduction (BLVR) is a less invasive, reversible manner of lung volume reduction, using one-way valves to improve lung function, quality of life, and exercise capacity. Nevertheless, knowledge gaps persist regarding factors that predict procedural success. Methods: We retrospectively reviewed 142 patients who underwent BLVR at the University of Chicago between December 2018 and July 2024 to assess the relationship between comorbidities and procedural outcomes. Using logistic and multinomial regression, we determined odds ratios (ORs) for a binary outcome of success and failure and relative risk ratios (RRRs) for failure sub-categories relative to procedural success. Results: We observed a procedural success rate of 48.1% and pneumothorax prevalence of 21.8%. After adjusting for age, sex, race, and body mass index (BMI), comorbidities associated with procedural failure included chronic kidney disease (CKD), congestive heart failure (CHF), anemia, and a BMI, Obstruction, Dyspnea and Exercise (BODE) Index of 5 or greater. Obstructive sleep apnea (OSA) was associated with procedural success. Conclusions: Comorbidities associated with dyspnea appear to have a significant effect on procedural success in BLVR. Full article

Traditional routing algorithms optimizing for distance or travel time are inadequate for electric vehicles (EVs), which require energy-aware planning considering battery constraints and charging infrastructure. This work presents an energy-optimal routing system for EVs that integrates personalized consumption modeling with real-time environmental data. The system employs a Long Short-Term Memory (LSTM) neural network to predict State-of-Charge (SoC) consumption from real-world driving data, learning directly from spatiotemporal features including velocity, temperature, road inclination, and traveled distance. Unlike physics-based models requiring difficult-to-obtain parameters, this approach captures nonlinear dependencies and temporal patterns in energy consumption. The routing framework integrates static map data, dynamic traffic conditions, weather information, and charging station locations into a weighted graph representation. Edge costs reflect predicted SoC drops, while node penalties account for traffic congestion and charging opportunities. An enhanced A* algorithm finds optimal routes minimizing energy consumption. Experimental validation on a Nissan Leaf shows that the proposed end-to-end SoC estimator significantly outperforms traditional approaches. The model achieves an RMSE of 36.83 and an $R^2$ of 0.9374, corresponding to a 59.91% reduction in error compared to physics-based formulas. Real-world testing on various routes further confirms its accuracy, with a Mean Absolute Error in the total route SoC estimation of 2%, improving upon the 3.5% observed for commercial solutions. Full article

Short-term traffic prediction is vital for intelligent transportation systems, enabling adaptive congestion control, real-time signal management, and dynamic route planning for autonomous vehicles (AVs). This study introduces a custom Transformer-based deep learning framework for joint forecasting of traffic flow and vehicle speed, leveraging handcrafted positional encoding and stacked multi-head attention layers to model multivariate traffic patterns. Evaluated against baselines including Long Short-Term Memory (LSTM), Support Vector Machine (SVM), Random Tree, and Random Forest on the Next-Generation Simulation (NGSIM) dataset, the model achieves 94.2% accuracy (Root Mean Squared Error (RMSE) 0.16) for flow and 92.1% accuracy for speed, outperforming traditional and deep learning approaches. A hybrid evaluation metric, integrating RMSE and threshold-based accuracy tailored to AV operational needs, enhances its practical relevance. With its parallel processing capability, this framework offers a scalable, real-time solution, advancing AV ecosystems and smart mobility infrastructure. Full article

Tan sheep are a characteristic and economically important local breed in the Ningxia Hui Autonomous Region of China, where respiratory diseases continue to pose challenges to animal health and production. In this study, a Pasteurella multocida strain (P6) was isolated from the lung tissue of a single Tan sheep presenting with severe and fatal respiratory disease, and subjected to case-based genomic and pathogenic characterization. The isolate was identified as capsular serotype A based on biochemical profiling, 16S rRNA gene sequencing, kmt-1 PCR, and capsular typing. To provide supportive evidence of virulence potential, a murine infection model was employed, in which P6 induced acute clinical signs and severe pulmonary lesions, including congestion, edema, hemorrhage, and fibrinous inflammatory exudation. Whole-genome sequencing revealed that strain P6 possesses a 2,289,251 bp genome with a GC content of 40.2%, encoding 2155 predicted genes and multiple mobile genetic elements, including genomic islands, prophages, transposons, and a CRISPR locus. Phylogenetic analysis based on seven housekeeping genes placed P6 in close relationship with strains 166CV and 103220, distinct from several rodent- and avian-derived isolates. Functional genomic analyses identified numerous genes associated with carbohydrate metabolism, secondary metabolite biosynthesis, host–pathogen interaction, virulence-related functions, and antimicrobial resistance. Comparative genomic analysis with the reference strain PM70 indicated a largely conserved functional framework, accompanied by a significant enrichment of mobilome-associated genes, suggesting enhanced genomic plasticity. Overall, this study provides a descriptive genomic overview of a P. multocida isolate associated with respiratory disease in Tan sheep and highlights its genetic features and potential adaptive capacity, while acknowledging the limitations inherent to a single-case investigation. Full article

This study developed a fire evacuation simulation model for a six-level underground station to evaluate evacuation efficiency under both dynamic and static conditions, including structural damage, smoke propagation, and real-time crowd congestion. Two representative pathfinding algorithms, Dijkstra’s and A*, were applied to analyze evacuation performance across eight fire scenarios occurring at different locations within the station. When only static factors were considered, both algorithms yielded identical maximum evacuation times, indicating comparable performance. However, the A* algorithm exhibited a significantly shorter computation time than Dijkstra’s, demonstrating higher operational efficiency. When dynamic variables such as real-time congestion and smoke-induced visibility reduction were introduced, the maximum evacuation times varied irregularly between the two algorithms. This outcome suggests that, under dynamic fire conditions, route guidance based solely on current information rather than predictive modeling may lead to suboptimal evacuation outcomes. Therefore, this study emphasizes the importance of establishing a predictive disaster management system capable of forecasting fire and smoke propagation, as well as a centralized control system that can dynamically distribute evacuees to enhance evacuation efficiency in deep underground stations. Full article

Background: Elastography is a non-invasive technique used to assess tissue stiffness. There are two main types of elastography: shear-wave elastography and strain imaging. Both are useful for evaluating the degree of liver fibrosis (LF). Shear-wave imaging is influenced by fibrosis and hepatic congestion, whereas strain imaging primarily reflects fibrosis progression and is less affected by congestion. We previously reported the clinical usefulness of combinational elastography in patients with heart failure (HF). However, its prognostic significance in this population remains unclear. Accordingly, in this prospective study, we aimed to evaluate the prognostic impact of combinational elastography in patients with HF. Methods: We included 77 patients with HF (median age: 79 years). Shear-wave imaging was used to obtain shear-wave velocity (Vs), whereas the liver fibrosis index (LF index) was derived from strain imaging. The Vs/LF index (V/L) was used as a prognostic indicator based on combinational elastography. Cardiac events were defined as cardiac death or hospitalization due to HF. Results: During a median follow-up of 716 days, 17 cardiac deaths or hospitalizations for HF were observed. The V/L demonstrated a cut-off value of 1.2 for predicting cardiac death or hospitalization for HF, with an area under the curve of 0.80, sensitivity of 0.82, and specificity of 0.68. Kaplan–Meier analysis demonstrated that patients with a high V/L (≥1.2) had significantly higher rates of hospitalization for HF than those with a low V/L (<1.2; log-rank test, p < 0.001). Conclusions: Combinational elastography demonstrated prognostic utility in patients with HF and may serve as a novel, non-invasive tool for assessing hepatic congestion. Full article

Tunnels have significantly expanded human activity spaces and alleviated urban congestion and environmental pollution on the surface. However, fires and associated smoke propagation in tunnels pose common and critical challenges in underground space utilization. Previous studies have primarily focused on smoke control under standard atmospheric conditions, emphasizing isolated parameters such as jet velocity or heat release rate (HRR), while overlooking key factors like environmental pressure and fire source proximity that influence smoke buoyancy and containment efficacy. One of the key problems remains unsolved: the comprehensive mechanisms governing transverse air curtain performance in variable-pressure and proximity scenarios. This study utilized Fire Dynamics Simulator (FDS6.7.1) software to conduct numerical simulations, aiming to elucidate the underlying incentives and explore the phenomena of smoke–thermal interactions. The analysis systematically evaluates the influence of four critical parameters: HRR (1–15 MW), fire-to-curtain distance (5–95 m), air curtain jet velocity (6–16 m/s), and ambient pressure (40–140 kPa). Results show that (1) jet velocity emerges as the dominant factor, with exponential enhancement in thermal containment efficiency at velocities above 10 m/s due to intensified shear forces; (2) escalating HRR weakens isolation, leading to disproportionate downstream temperature rises and diminished efficacy; (3) fire proximity within 10 m disrupts curtain integrity via high-momentum smoke impingement, amplifying thermal gradients; and (4) elevated ambient pressure dampens smoke buoyancy while augmenting air curtain momentum, yielding improved containment efficiency and reduced temperatures. This paper is helpful for the design and operation of thermal applications in underground infrastructures, providing predictive models for optimized smoke control systems. The contour maps reveal the field-distribution trends and highlight the significant influence of the air curtain and key governing parameters on the thermal field and smoke control performance. This work delivers pivotal theoretical and practical insights into the advanced design and optimization of aerodynamic smoke control systems in tunnel safety engineering Full article

One of the key functions of Air Traffic Management (ATM) is to balance airspace capacity and demand. Despite measures that are taken during the strategic and pre-tactical phases of flight, demand–capacity imbalances still occur in flight, often manifesting as localised regions of high traffic complexity, known as hotspots. These hotspots emerge dynamically, leaving air traffic controllers with limited anticipation time and increased workload. This paper proposes a Machine Learning (ML) framework for the prediction and resolution of hotspots in congested en-route airspace up to an hour in advance. For hotspot prediction, the proposed framework integrates trajectory prediction, spatial clustering, and complexity assessment. The novelty lies in shifting complexity assessment from a sector-level perspective to the level of individual hotspots, whose complexity is quantified using a set of normalised, sector-relative metrics derived from historical data. For hotspot resolution, a Reinforcement Learning (RL) approach, based on Proximal Policy Optimisation (PPO) and a novel neural network architecture, is employed to act on airborne flights. Three single-clearance type agents—a speed agent, a flight-level agent, and a direct routing agent—and a multi-clearance type agent are trained and evaluated on thousands of historical hotspot scenarios. Results demonstrate the suitability of the proposed framework and show that hotspots are strongly seasonal and mainly occur along traffic routes. Furthermore, it is shown that RL agent performance tends to degrade with hotspot complexity in terms of certain performance metrics but remains the same, or even improves, in terms of others. The multi-clearance type agent solves the highest percentage of hotspots; however, the FL agent achieves the best overall performance. Full article

Traffic flow prediction is a fundamental component of intelligent transportation systems and plays a critical role in traffic management and autonomous driving. However, accurately modeling highway traffic remains challenging due to dynamic congestion propagation, lane-level heterogeneity, and non-recurrent traffic events. To address these challenges, this paper proposes an improved attention-mechanism spatio-temporal graph convolutional network, termed AMSGCN, for highway traffic flow prediction. AMSGCN introduces an adaptive adjacency matrix learning mechanism to overcome the limitations of static graphs and capture time-varying spatial correlations and congestion propagation paths. A hierarchical multi-scale spatial attention mechanism is further designed to jointly model local congestion diffusion and long-range bottleneck effects, enabling an adaptive spatial receptive field under congested conditions. To enhance temporal modeling, a gating-based fusion strategy dynamically balances periodic patterns and recent observations, allowing effective prediction under both regular and abnormal traffic scenarios. In addition, direction-aware encoding is incorporated to suppress interference from opposite-direction lanes, which is essential for directional highway traffic systems. Extensive experiments on multiple benchmark datasets, including PeMS and PEMSF, demonstrate the effectiveness and robustness of AMSGCN. In particular, on the I-24 MOTION dataset, AMSGCN achieves an RMSE reduction of 11.0% compared to ASTGCN and 17.4% relative to the strongest STGCN baseline. Ablation studies further confirm that dynamic and multi-scale spatial attention provides the primary performance gains, while temporal gating and direction-aware modeling offer complementary improvements. These results indicate that AMSGCN is a robust and effective solution for highway traffic flow prediction. Full article

Developing vehicle classification remains a fundamental challenge for intelligent traffic management in the Indian urban environment, where traffic exhibits high heterogeneity, density and unpredictability. In the Indian subcontinent, vehicle movement is erratic, congestion is high, and vehicle types vary significantly. Conventional global benchmarks often fail to capture these complexities, highlighting the need for a region-specific dataset. To address this gap, the present study introduced the EAHVSD dataset, a novel real-world image collection comprising 10,864 vehicle images from four distinct classes, acquired from roadside surveillance cameras at multiple viewpoints and under varying conditions. This dataset is designed to support the development of an automatic traffic counter and classifier (ATCC) system. A comprehensive evaluation of eleven state-of-the-art deep learning models, namely VGG16, VGG19, MobileNetV2, Xception, AlexNet, ResNet50, ResNet152, DenseNet121, DenseNet201, InceptionV3, and NASNetMobile, was carried out. Among these, the highest accuracy result has been achieved by VGG-16, MobileNetV2, InceptionV3, DenseNet-121, and DenseNet-201. We developed a stacking-based meta-ensemble framework to leverage the complementary strengths of its components and overcome their individual limitations. In this approach, a meta-learner classifier integrates the predictions of the best-performing models, thereby improving robustness, scalability, and real-world adaptability. The proposed ensemble model achieved an overall classification accuracy of 96.04%, a Cohen’s Kappa of 0.93, and an AUC of 0.99, consistently outperforming the individual models and existing baselines. A comparative analysis with prior studies further validates the efficacy and reliability of the stacking-based meta-ensemble method. These findings position the proposed frameworks as a robust and scalable solution for efficient vehicle classification under practical surveillance constraints, with potential applications in intelligent transportation systems and traffic management. Full article

Accurate multivariate traffic flow forecasting is critical for intelligent transportation systems yet remains challenging due to the complex interplay of temporal dynamics and spatial interactions. While Transformer-based models have shown promise in capturing long-range temporal dependencies, most existing approaches compress multidimensional observations into flattened sequences—thereby neglecting explicit modeling of cross-dimensional (i.e., spatial or inter-variable) relationships, which are essential for capturing traffic propagation, network-wide congestion, and node-specific behaviors. To address this limitation, we propose TSAformer, a novel Transformer architecture that explicitly preserves and jointly models time and dimension as dual structural axes. TSAformer begins with a multimodal input embedding layer that encodes raw traffic values alongside temporal context (time-of-day and day-of-week) and node-specific positional features, ensuring rich semantic representation. The core of TSAformer is the Two-Stage Attention (TSA) module, which first models intra-dimensional temporal evolution via time-axis self-attention then captures inter-dimensional spatial interactions through a lightweight routing mechanism—avoiding quadratic complexity while enabling all-to-all cross-node communication. Built upon TSA, a hierarchical encoder–decoder (HED) structure further enhances forecasting by modeling traffic patterns across multiple temporal scales, from fine-grained fluctuations to macroscopic trends, and fusing predictions via cross-scale attention. Extensive experiments on three real-world traffic datasets—including urban road networks and highway systems—demonstrate that TSAformer consistently outperforms state-of-the-art baselines across short-term and long-term forecasting horizons. Notably, it achieves top-ranked performance in 36 out of 58 critical evaluation scenarios, including peak-hour and event-driven congestion prediction. By explicitly modeling both temporal and dimensional dependencies without structural compromise, TSAformer provides a scalable, interpretable, and high-performance solution for spatiotemporal traffic forecasting. Full article

Flooding in Bengaluru areas such as Kodigehalli, Hebbal, and Nagavara has led to severe disruptions, including traffic congestion, infrastructure damage, and health risks. To address this issue, we have proposed a smart flood alert and communication system, integrating Internet of things (IoT), artificial intelligence (AI), and smart infrastructure solutions. The system helps by giving information about real-time water level sensors, AI-driven flood prediction models, automated emergency coordination, and a mobile-based citizen reporting platform. Through cloud-based data processing, predictive analytics, and smart drainage management, this solution aims to enhance early warnings, reduce emergency response time, and improve urban flood resilience. It yields up to an 80% reduction in alert delays, a 50% faster emergency response, and improved community safety. This project seeks collaboration with government agencies, technology firms, and community stakeholders to implement a pilot plan, ensuring a scalable and sustainable flood mitigation strategy for Bengaluru. Full article

Background: Iron deficiency (ID) is prevalent in congestive heart failure (CHF), worsening outcomes. While European guidelines recommend screening using ferritin and transferrin-saturation (TSAT), inconsistent diagnostic criteria, especially regarding functional deficiency (ferritin 100–299 μg/L + TSAT < 20%) and hyperferritinemia, limit prognostic accuracy. This study evaluated iron status definitions, including guideline criteria and a combined Ferritin-TSAT model, for predicting 365-day mortality in hospitalised CHF patients. Methods: This retrospective analysis used MIMIC-IV data from 1839 CHF patients. Iron status within 24 h of admission was categorised using: (1) Guideline ID vs. non-ID; (2) Ferritin categories; (3) TSAT categories; (4) Combined Ferritin-TSAT model (Low: guideline ID; Intermediate: ferritin 100–299 + TSAT ≥ 20%; High: ferritin ≥ 300 μg/L). Adjusted Cox models assessed mortality associations. Results: Guidelines-defined iron deficiency (33.66% prevalence) independently associated with higher 1-year mortality (56.1% vs. 29.4%; adjusted HR 4.36, 95% CI 3.35–5.34). The combined Ferritin-TSAT model showed significant prognostic value, differentiating true iron deficiency (reference) from hyperferritinemia (adjusted HR 0.50 vs. iron deficiency) and intermediate group (adjusted HR 0.36 vs. ID), indicating varying risk relative to the most deficient group. This combined model better distinguished hyperferritinemic and iron-replete subgroups than the binary guideline definition. Conclusions: Iron status, including deficiency and hyperferritinemia, independently predicts 1-year mortality in CHF. While guideline iron deficiency is a strong predictor, a combined Ferritin-TSAT classification offers finer risk stratification by identifying distinct phenotypes (true deficiency, hyperferritinemia, intermediate). Nuanced iron status assessment could improve prognostic evaluation and guide personalised therapies (e.g., IV iron for deficiency, investigation for hyperferritinemia) to enhance CHF outcomes. Full article