Search Results (978)

Accurate river discharge estimation is fundamental for water resource management under increasingly variable hydrological conditions. While conventional in situ techniques remain hydrometric reference standards, their operational deployment is constrained by cost, accessibility, and limited spatial coverage. Advances in remote sensing and artificial intelligence (AI) have introduced non-contact discharge estimation frameworks based on image-derived observations. This systematic review, conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 reporting guidelines, examines the evolution of river discharge measurement methods between 2004 and 2024 through a structured two-stage design. An initial search in Web of Science and Scopus identified 2809 records, of which 249 were retained for first-stage synthesis. A focused second-stage screening isolated seven studies that directly integrate image-based data with machine learning or deep learning architectures for discharge estimation. The analysis reveals a methodological transition from instrument-based hydrometry toward computationally assisted, image-driven approaches. The retained studies employ close-range and satellite imagery combined with Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), and related models. Although reported validation metrics indicate strong predictive capability under specific conditions, performance remains dependent on site-specific calibration and reference discharge records. Broader operational deployment requires improved transferability, uncertainty integration, and cross-basin validation. Full article

Background: Stenotrophomonas maltophilia is a multidrug-resistant pathogen with limited therapeutic options that predominantly affects critically ill and immunocompromised patients. Trimethoprim–sulfamethoxazole (TMP/SMX) remains the conventional first-line therapy; however, emerging resistance and toxicity concerns necessitate alternative regimens. This study represents, to our knowledge, the first network meta-analysis (NMA) comparing the efficacy and safety of clearly defined monotherapy and combination antibiotic regimens for S. maltophilia infections. Materials and methods: A systematic search of PubMed, Cochrane Library, Web of Science, and ClinicalTrials.gov (inception to January 2026) identified eligible randomized-controlled studies and retrospective studies. Data were analyzed using a frequentist random-effects NMA with TMP/SMX as the reference. Evaluated regimens included TMP/SMX, fluoroquinolone (FQ), minocycline (MIN), TMP/SMX + FQ, TMP/SMX + MIN, FQ + MIN and FQ + other. Primary and secondary outcomes were all-cause mortality, clinical cure, and adverse effects. Results: Thirteen retrospective studies encompassing 2980 patients were included. Using TMP/SMX as the reference, network meta-analysis demonstrated heterogeneity in all-cause mortality across antimicrobial regimens. FQ and MIN monotherapies were associated with lower odds of mortality (effect sizes: 0.65, 95% CI: 0.49–0.85 and 0.50, 95% CI: 0.28–0.90), whereas combination therapy with TMP/SMX plus FQ was associated with higher mortality (effect size: 2.93, 95% CI: 1.18–7.31). Treatment ranking based on effect sizes suggested more favorable mortality profiles for MIN and FQ regimsens. No significant differences were observed in clinical cure, while FQ was associated with a lower incidence of adverse effects compared with TMP/SMX. Conclusions: This network meta-analysis suggests that FQ and MIN monotherapies may be associated with more favorable survival and tolerability compared with TMP/SMX monotherapy. No clear differences were observed for combination therapy relative to other active monotherapy options. Prospective randomized studies are required to validate these observations and to better inform the management of S. maltophilia infections. Full article

Though deep learning has brought transformative advances to the field of modulation recognition, conventional approaches typically rely on a large amount of labeled data, which is often difficult to obtain in real-world communication scenarios. Few-shot modulation recognition (FSMR), which aims to identify modulation formats with extremely limited training samples, serves as a key enabler for next-generation cognitive radio, intelligent spectrum management, and non-cooperative communications. However, existing neural network models are not inherently designed for few-shot learning (FSL) and cannot be directly applied to FSMR tasks. To address this gap, this paper proposes a spatio-temporal prototypical network (STPN) trained within a meta-learning framework. Through a lightweight multi-module design that sequentially captures spatial patterns and temporal dependencies, STPN effectively integrates hybrid feature extraction with prototype-based classification. In contrast to existing approaches, STPN features a streamlined architecture free from intricate operations that could compromise generalization. This advantage is especially crucial when the model is trained on numerous meta-tasks with only a few samples. Comprehensive experiments on public benchmarks show that STPN achieves superior classification accuracy over several baseline models, while also offering advantages in parameter efficiency and computational cost. Further analysis investigates the key parameters influencing model performance, and ablation studies confirm the individual contribution of each module. This work not only deepens the theoretical understanding of prototype-based FSL techniques but also establishes a practical framework applicable to other signal processing tasks that demand robust performance under limited labeled data. Full article

Background: Deep convolutional neural networks (DCNNs) are increasingly used in computer-aided dental diagnostics. However, the relative diagnostic performance of commonly applied architectures, particularly Faster R-CNN and Mask R-CNN, has not been systematically synthesized across imaging modalities. This systematic review and meta-analysis compared the diagnostic accuracy of Faster R-CNN and Mask R-CNN for dental caries detection using radiographic and photographic images. Methods: PubMed (MEDLINE), EMBASE, Web of Science, and Scopus were systematically searched for studies published up to 15 June 2025. Studies applying Faster R-CNN and/or Mask R-CNN to dental caries detection were included. Binary diagnostic data were extracted, and pooled sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were estimated using a bivariate random-effects model. Study quality was assessed with QUADAS-AI, and radiomics-based radiographic studies were additionally evaluated using the Radiomics Quality Score (RQS). The protocol was registered in PROSPERO (CRD420251074443). Results: Seventeen studies met the inclusion criteria. Across all imaging modalities, Mask R-CNN showed significantly higher pooled sensitivity (85.6% vs. 71.7%, p = 0.0244), specificity (94.2% vs. 81.4%, p = 0.00089), and AUC (0.95 vs. 0.84, p = 0.0053) than Faster R-CNN. In radiographic images, Mask R-CNN consistently outperformed Faster R-CNN in sensitivity (86.3% vs. 67.2%, p = 0.0497), specificity (96.5% vs. 85.0%, p = 0.00105), and AUC (0.97 vs. 0.86, p = 0.0067). In photographic images, Mask R-CNN achieved a higher AUC (0.91 vs. 0.83, p = 0.048), whereas differences in pooled sensitivity (83.5% vs. 77.3%, p = 0.435) and specificity (86.0% vs. 75.1%, p = 0.156) were not statistically significant. Conclusions: Faster R-CNN and Mask R-CNN both show potential for dental caries detection, but current evidence is limited by substantial heterogeneity, predominantly retrospective designs, and variability in imaging and labeling. Across the included studies, Mask R-CNN showed higher pooled performance estimates than Faster R-CNN, with the clearest differences in radiographic applications; however, this comparison is indirect and should be considered suggestive rather than definitive given study-level heterogeneity and uncertainty in the reference standard in a sizable proportion of studies. Prospective, multi-center studies with standardized imaging protocols, rigorous annotation, and independent external validation are required to support reliable clinical implementation. Full article

As network communication technologies rapidly advance, ransomware has emerged as a significant cybersecurity threat that organizations cannot ignore. Static analysis enables rapid identification of ransomware by examining file structure and code characteristics before execution. However, existing classifiers are predominantly designed under the closed-set assumption, causing them to misclassify novel variants into known families. Furthermore, ransomware datasets typically exhibit long-tailed distributions with emerging families having very few available samples, making it difficult for models to learn discriminative features. To address these challenges, we propose Few-Shot Open-Set Ransomware Detection through Meta-learning and Energy-based Modeling (MEM), a unified open-set recognition framework based on static analysis of Portable Executable features. By integrating Model-agnostic Meta-learning (MAML), the model rapidly adapts to new families with limited samples. The Energy Function quantifies the confidence of predictions in distinguishing between known samples and unknown ones, while Focal Loss dynamically adjusts sample weights to reduce bias introduced by imbalanced distributions. The experimental results demonstrate that MEM achieves higher classification accuracy and better rejection performance of unknown samples than existing open-set recognition methods. Full article

Background/Objectives: This network meta-analysis aimed to evaluate and compare the risks of lower eyelid complications—ectropion, entropion, scleral show, and postoperative scarring—associated with four surgical approaches (subciliary, subtarsal, infraorbital, and transconjunctival) for orbital and zygomaticomaxillary fracture repair. Methods: A systematic search of PubMed, Embase, and Cochrane databases identified relevant studies published between 1 January 1990 and 10 January 2026. Twenty-seven eligible studies involving 2790 patients were included. Direct pairwise meta-analyses and network meta-analyses were conducted to compare complication risks among the approaches. Sensitivity analyses were performed to assess the influence of individual studies, and inconsistency tests were applied to evaluate model robustness. Results: The subciliary approach was associated with the highest risk of ectropion and scleral show. The transconjunctival approach had the lowest risk of ectropion and scarring but the highest risk of entropion. The subtarsal approach had the lowest risk of scleral show, while the infraorbital approach had the highest risk of postoperative scarring. Sensitivity analyses confirmed consistent rankings, and no significant inconsistency was detected. Conclusions: This study provides updated, comprehensive evidence to guide the choice of surgical approach for orbital and zygomaticomaxillary fracture repair. Surgeons should balance operative exposure, cosmetic outcomes, and complication risk, and communicate these trade-offs clearly with patients to optimize decision-making. Full article

The Background: monoclonal antibody therapies represent high-efficacy treatment options for relapsing forms of multiple sclerosis (MS). However, the absence of direct head-to-head randomized trials and the use of heterogeneous comparators across pivotal studies complicate comparative effectiveness assessments. While network meta-analysis (NMA) offers a framework to integrate evidence, the fragmented structure of the available evidence base precludes a conventional NMA with global indirect comparisons and treatment ranking. Methods: A systematic review with qualitative assessment of treatment effects of randomized controlled trials evaluating monoclonal antibody therapies in relapsing forms of multiple sclerosis was conducted. Annualized relapse rate (ARR) was analyzed as the primary outcome, and six-month confirmed disability progression (CDP) as the key secondary outcome. Network geometry and connectivity were explicitly assessed for each outcome prior to quantitative synthesis. Analyses were restricted to comparator-defined connected components of the evidence base, and indirect comparisons across disconnected components were not performed. Sensitivity analyses, including descriptive analyses in progressive multiple sclerosis, were conducted where appropriate. Results: nine randomized controlled trials involving 6762 patients were included. For ARR, the evidence network was fragmented into three disconnected components defined by placebo-, interferon beta-1a-, and teriflunomide-controlled trials. Within connected sub-networks, monoclonal antibody therapies consistently demonstrated substantial reductions in ARR relative to their respective comparators, with overlapping confidence intervals suggesting broadly comparable relapse suppression among high-efficacy agents. For CDP, network connectivity was more limited, and treatment effects were more heterogeneous. Significant reductions in disability progression were observed for some agents within comparator-specific networks, while uncertainty remained for others. Due to network disconnection, no global treatment ranking was performed. Conclusions: this study provides a transparent synthesis of randomized evidence on monoclonal antibody therapies in relapsing MS. By explicitly accounting for network connectivity and comparator heterogeneity, the analysis avoids unsupported indirect comparisons and global treatment hierarchies. The findings support robust relapse suppression across monoclonal antibody therapies within comparable trial frameworks, while highlighting heterogeneity in disability outcomes. These results illustrate the importance of contextual interpretation in comparative effectiveness research in MS. Full article

Reliability is a fundamental aspect of modern structural engineering due to the inherent randomness of materials, loads, and environmental conditions. However, as system complexity increases, a substantial computational cost is typically required to evaluate the failure probability, often involving 10⁵–10⁶ limit state function evaluations in a conventional Monte Carlo simulation. To address this challenge, this study presents an active-learning-driven deep neural network (ALDNN) meta model algorithm to improve both efficiency and accuracy in reliability analysis. To substantially reduce the computational costs, a multi-phase active learning framework incorporating weighted sampling and adaptive threshold-based candidate filtering is implemented by iteratively selecting more important points and adaptively training deep neural networks. Thresholds for candidate sample points and training datasets are gradually adjusted based on feedback from estimated responses. The proposed method reduces the number of true limit state evaluations to the order of 10² in the benchmark problems considered, while maintaining high accuracy. Its performance is assessed using widely referenced benchmark problems, and finite-element-method-based implicit examples for frame structures are further employed to verify applicability. The results demonstrate the high efficiency, accuracy, and scalability of the ALDNN meta model as system complexity increases. Full article

This systematic review summarizes the application of artificial intelligence (AI) in classifying upper-limb motion using Electroencephalogram (EEG) and Electromyogram (EMG) signals, focusing on the field’s progression from Traditional Machine Learning (TML) to Deep Learning (DL) architectures. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a search of PubMed, IEEEXplore, and Web of Science yielded 301 eligible studies published up to June 2025. The results indicate a change from classical classifiers like Linear Discriminant Analysis (LDA) and Support Vector Machines (SVMs) toward DL approaches. While Convolutional Neural Networks (CNNs) remain the most frequently implemented, emerging architectures, including Long Short-Term Memory (LSTM) networks and Transformers, have demonstrated remarkable performance. Despite the rise of DL, classical models remain highly relevant due to their robustness and efficiency. This review also identifies a heavy reliance on EEG-only modalities (60%), with only 7% of studies utilizing hybrid EEG-EMG systems, representing a potential missed opportunity for signal fusion. Full article

Hydrogen is a potential energy carrier for the decarbonization of the heating sector; however, its long-term role remains highly debated. This meta-analysis (2024–early 2025) assesses hydrogen’s potential for domestic heating regarding consumption, costs, and environmental impacts. Current scientific evidence distinguishes between hydrogen use for direct residential heating and its role in integrated energy systems. For residential decarbonization, the literature does not support hydrogen as a primary solution: electrification, especially through heat pumps, remains the most efficient and cost-effective long-term pathway. Direct hydrogen heating faces major thermodynamic and economic barriers, including low conversion efficiency, high Levelized Costs of Energy (LCOE), infrastructure limitations, and challenges in achieving broad social acceptance. Hydrogen’s more strategic value emerges at the system level. Hybrid configurations that combine heat pumps with hydrogen storage show strong potential by using heat pumps to efficiently meet thermal demand while reserving hydrogen for flexible backup and storage. In particular, hydrogen is well suited for long-term seasonal energy storage and grid balancing, enhancing system flexibility and reliability. Its main contribution therefore lies not in direct end-use heating, but in strengthening grid resilience and supporting energy autarky in net-zero scenarios. Hydrogen blending into existing gas networks is widely viewed as a transitional measure to stimulate the hydrogen economy and deliver limited short-term emission reductions, rather than a definitive net-zero solution. Overall, hydrogen’s residential role remains niche, requiring targeted research, development, and large-scale pilot projects to validate competitive applications. Full article

High-density lipoprotein-binding protein (HDLBP), also called Vigilin, is a multifunctional RNA-binding protein with established roles in RNA transport and regulation, chromosome segregation, lipid homeostasis, and translational regulation. Frequently detected to be perturbed in phosphoproteome analysis, phosphorylation is indicated as a major mechanism in the regulation of HDLBP functions; however, its phosphorylation landscape remains unexplored. We performed a meta-phosphoproteome analysis of HDLBP to map site-specific functional and regulatory roles of its two most frequently detected phosphosites, S31 and S944. Co-occurrence analysis across multiple datasets indicated that they can be phosphorylated together, suggesting potential co-ordinated regulation. Site-specific co-regulation analysis revealed distinct phospho-regulatory networks, with upstream kinases identified exclusively for S944. Functional enrichment of co-regulated protein phosphosites (CPPs) highlighted its role in RNA metabolism, chromosome organization, and nucleoplasmic transport, while functional annotation of site-specific phosphorylation of CPPs indicates its involvement in cell cycle regulation, apoptosis, and carcinogenesis. Additionally, the potential role of CPPs in the lipid homeostasis network was explored. Furthermore, the differential expression of HDLBP phosphosites across multiple cancers was observed using UALCAN, suggesting a potential role for phospho-regulation of HDLBP in tumor-associated pathways. Together, these findings provide the first integrated view of HDLBP phosphorylation and could serve as a valuable framework for future targeted studies to elucidate the mechanistic roles of site-specific HDLBP phosphorylation in cellular and pathophysiological processes. Full article

Background and Objectives: Palmoplantar pustulosis (PPPust) and palmoplantar psoriasis (PPso) are distinct palm/sole dermatoses that have historically shared the abbreviation “PPP”. Though the two—since the advent of advanced biotechnology—are now deemed separate diagnoses, each still falls under the ‘palmoplantar spectrum’. It is important to note that PPso and PPPust are each distinct from generalized pustular psoriasis (GPP), a condition that is outside the scope of our study. We quantified the relative efficacy of biologic and small-molecule monotherapies on the palmoplantar spectrum using Bayesian network meta-analyses (NMAs). Materials and Methods: On 6 November 2025, we searched PubMed, Scopus, ClinicalTrials.gov, and citations (i.e., citation mining) for randomized trials of monotherapy reporting PPP Area and Severity Index (PPPASI) outcomes at 12 or 16 weeks; we secondarily investigated fresh pustule-related outcomes at 4 weeks. We ran Bayesian NMAs with uniform priors; nodes were defined by dose and timepoint. Interventions’ Surface Under the Cumulative Ranking Curve (SUCRA) values were computed; pairwise effects with 95% credible intervals were also estimated. Sensitivity analyses adjusted for diagnosis (pustulosis vs. psoriasis) via network meta-regression. Results: Twenty trials (n = 2030) with 23 active comparators provided data for 10 endpoints (fresh pustules at 4 weeks; PPPASI-50/75 and mean percentage and absolute PPPASI change at 12 and 16 weeks). Conclusions: The NMA indicates efficacy of ixekizumab and brodalumab (IL-17 inhibitors), guselkumab (IL-23 inhibitor), and spesolimab (IL-36 inhibitor) in managing palmoplantar pustulosis. Full article

The accuracy of forest canopy height estimation is crucial for forest resource management and ecosystem carbon sequestration. However, existing approaches often face limitations in effectively integrating multisource remote sensing data, feature representation, and model learning strategies. To enhance the prediction performance of the model in complex terrain and multisource data environments, this study comprehensively used ICESat-2/ATLAS photon point clouds, Sentinel-2/MSI multispectral imagery, and SRTM-DEM to construct a remote sensing-driven multisource feature system, which eliminated redundant interference using permutation feature importance analysis. Additionally, a self-attention (SA) mechanism was introduced to strengthen high-dimensional feature representation. Three heterogeneous models, incorporating deep neural network (DNN), extreme gradient boosting (XGBoost), and residual network (ResNet), were independently applied for forest canopy height estimation and were further used as base learners, with a random forest as the meta-learner, and an SA-Blending heterogeneous ensemble model that combines a blending technique with an SA mechanism was proposed to enhance the accuracy of forest canopy height estimation. To evaluate the SA optimization strategy and the role of multisource fusion, this study used the original features, SA-optimized features, and multisource fusion features (i.e., the concatenation and fusion of original features and self-attention mechanism features) as inputs to comprehensively compare the performance of each single model and the integrated model. The results show that: (1) The self-attention mechanism significantly improves the prediction performance of heterogeneous models. Compared with original features inputs, the R² of DNN (SA-Only) and XGBoost (SA-Only) increased to 0.706 and 0.708, respectively, and the RMSE decreased to 1.691 m and 1.613 m. Although the R² for ResNet (SA-Only) decreased slightly to 0.699 and the RMSE increased to 1.712 m, the overall impact was not significant. (2) Under the condition of multisource fusion feature input, DNN+SA, XGBoost+SA, and ResNet+SA all demonstrated higher fitting accuracy and stability, verifying the enhancing effect of the SA mechanism on the association expression of multisource information. (3) The SA-Blending model achieved the best overall performance, with R² of 0.766 and RMSE of 1.510 m. It outperformed individual models and the SA-optimized model in terms of overall accuracy, stability, and robustness. The results can provide technical support for high-precision forest canopy height mapping and are of great significance for ecological monitoring applications. Full article

Background: There are multiple effective treatment options for patients diagnosed with chronic lymphocytic leukemia and small lymphocytic lymphoma (hereafter, simply CLL). In 2025, two phase 3 randomized clinical trials of pirtobrutinib, a non-covalent BTK inhibitor, were reported, demonstrating improved outcomes versus comparator therapies in the treatment-naïve setting (NCT05254743 and NCT05023980). Methods: A systematic literature review was conducted to identify RCTs in the first-line setting for CLL. A Bayesian NMA was performed to compare overall response rate (ORR) and progression-free survival (PFS) of pirtobrutinib versus treatments recommended by the National Comprehensive Cancer Network in the first-line setting, with a focus on BTKi monotherapy. Results: Eight unique trials were identified for comparison versus pirtobrutinib. Eligible RCTs formed two disconnected networks (pirtobrutinib, ibrutinib and zanubrutinib were in Network 1; acalabrutinib was in Network 2). Results from Network 1 for ORR showed an odds ratio (OR) = 0.56 (95% credible interval [CrI], 0.28, 1.12) for ibrutinib versus pirtobrutinib and OR = 0.50 (95% CrI, 0.20, 1.27) for zanubrutinib versus pirtobrutinib. The PFS of ibrutinib was inferior to pirtobrutinib (hazard ratio (HR) = 1.89, 95% CrI, 1.13, 3.19); the PFS HR comparing zanubrutinib with pirtobrutinib was 1.51 (95% CrI, 0.84, 2.72). Conclusions: This NMA shows that pirtobrutinib has better PFS outcomes than ibrutinib. While PFS outcomes suggest that pirtobrutinib is comparable to second-generation covalent BTKi monotherapies, uncertainty exists in the interpretation of the treatment effect, as evidenced by wide credible intervals. These findings suggest the value of pirtobrutinib as a future treatment option for patients in the first-line setting. Full article

Intermodal transportation (IMT) has long been recognized as a key strategy for decarbonizing freight transportation (FT), which is one of the most polluting sectors worldwide. While IMT has been extensively examined using operations research (OR) methods, the integration of decarbonization objectives has only recently gained momentum. Despite this growing interest, to the best of our knowledge, no prior comprehensive review has systematically synthesized OR methodologies specifically addressing IMT decarbonization. To address this gap, we conduct a systematic literature review of OR studies on IMT decarbonization and organize the survey into two complementary parts. Part I focuses on methodological foundations of OR applications in IMT decarbonization. We classify studies by problem type and OR technique, analyzing modeling characteristics, solution approaches, and uncertainty treatment. Our analysis reveals that exact methods dominate the literature (41% of studies), while meta-heuristics show rapid recent growth with 50% of studies published recently. Approximately 20% of studies incorporate uncertainty, and they are predominantly demand-focused. We identify critical research gaps including limited multistage stochastic frameworks to capture cascading uncertainties, insufficient attention to terminal operations and network reliability, and the underutilization of emerging technologies such as reinforcement learning and digital twins. This systematic synthesis establishes the current state of OR methodologies in IMT decarbonization and provides a foundation for future innovations in sustainable freight systems. Full article