Search Results (38,798)

Background: Coronary artery calcium (CAC) scores are a widely used surrogate marker for atherosclerotic burden, but they do not fully reflect plaque vulnerability or coronary inflammation. This study aimed to evaluate the relationship between CACs, coronary plaque characteristics, and perivascular inflammatory activity using advanced CCTA and CaRi-Heart^® analysis. Methods: A total of 250 patients with no prior cardiovascular disease were retrospectively evaluated and stratified by CACs into three groups: 0 (n = 28), 1–100 (n = 121), and >100 (n = 101). Coronary plaque morphology, high-risk plaque (HRP) features, CAD-RADS scores, and AI-derived fat attenuation index (FAI) centiles were assessed. Results: Significant differences across CAC categories were observed for several key parameters. The number of diseased coronary segments increased markedly (from 1.39 ± 1.10 vs. 2.97 ± 1.57 vs. 3.94 ± 2.10; p < 0.0001, one-way ANOVA). A similar upward trend was seen for segment involvement scores, HRP prevalence, and the proportions of mixed and calcified plaque components. Regression analysis demonstrated that CACs correlated significantly with segment burden (r² = 0.2520), CAD-RADS (r² = 0.1352), and the FAI score centile (r² = 0.0568). Conclusions: This study highlights the limitations of CACs as a standalone risk stratification tool. Vulnerable and inflamed plaques may already be present in patients with low or zero CACs. Integrating CCTA with perivascular FAI mapping enables earlier detection of biologically active atherosclerosis and supports more precise clinical decision-making. Full article

This study presents an expert system for assessing the stability of underground mine workings and automatically selecting rock bolt support schemes. The system integrates physically based calculations of roof compressive strength (Rc) and expected maximum displacement (Um) with rule-based decision logic grounded in engineering practice. Unlike empirical classifications and black-box AI models, the proposed approach ensures interpretable, reproducible, and context-aware engineering decisions. The architecture includes a numerical solver that computes Rc and Um based on excavation geometry, geomechanical properties, and mining conditions. The support scheme is selected using a knowledge base of formalized rules, while the specific support parameters are calculated within the solver. The system was validated across 51 underground excavations, with approximately 85% of its recommendations matching field-proven support solutions, and 12% suggesting reinforced schemes that could have prevented failures. The expert system is suitable for integration into digital mine management platforms and offers a foundation for developing digital twin solutions in geomechanically variable environments. Full article

The study of early intervention programs for at-risk children and their families is a continuously evolving field. As a result, researchers, policymakers, and practitioners focus on the effectiveness of these programs. The educational outcomes of the implementation of early intervention programs have been well studied. However, regarding the financial and societal benefit of the implementation of these programs, studies are limited. Studies conducted in the past have indicated that early intervention programs are cost-effective; early intervention programs reduce the need for costly public services in the future by supporting the child’s wellbeing and development, promoting family stability, providing early access to appropriate support services, enhancing families’ knowledge and skills, and providing them with the resources necessary to support their children. There is a great need for updated financial evaluations related to the implementation of early intervention programs for at-risk children and their families to broaden their social impact. Thus, it is important that policymakers consider financial evaluations, in combination with qualitative data, in their decision-making procedures. Policymakers, researchers, and practitioners should closely cooperate in the planning and implementation of programs that meet the needs of the children and families who are at risk. Full article

Source-based virtual reconstructions have become essential tools for communication and research in urban and architectural studies. While these reconstructions are often showcased through exhibition visualizations, the underlying knowledge is not always apparent or even documented. This raises concerns about their sustainability. Without transparent, publicly accessible documentation of the decision-making processes (known as paradata) that come with and support these digital reconstructions, there is a risk of losing both the knowledge embedded in them and their potential scientific value. To enhance transparency and allow for proper assessment and recognition of these reconstructions, thorough documentation and evaluation of the reconstruction processes are crucial. Although there are various approaches to documenting virtual reconstructions tailored to specific use cases, and while some focus on aspects like visualizing reliability, the overall process of documentation remains cumbersome and costly, making it an exception rather than the norm. Previous tools that claim to properly document virtual reconstructions either cover only part of the metadata and linked sources, are too complicated to use, or are no longer available. Currently, there is no universally accepted, straightforward, and easy-to-use workflow for this purpose. The IDOVIR project addresses this gap by offering a user-friendly, web-based platform designed specifically for documenting digital architectural reconstructions. We strive for achieving such a standardized workflow. To date, the platform has already been adopted by a large number of users, and many projects are publicly accessible. Full article

South Africa’s transition to a renewable-powered grid faces critical challenges due to the inherent variability of wind and solar generation as well as the need for economically viable and reliable dispatch strategies. This study proposes a scenario-based stochastic optimization framework that integrates machine learning forecasting and uncertainty modeling to enhance operational decision making. A hybrid Long Short-Term Memory–XGBoost model is employed to forecast wind, photovoltaic (PV) power, concentrated solar power (CSP), and electricity demand, with Monte Carlo dropout and quantile regression used for uncertainty quantification. Scenarios are generated using appropriate probability distributions and are reduced via Temporal-Aware K-Means Scenario Reduction for tractability. A two-stage stochastic program then optimizes power dispatch under uncertainty, benchmarked against Deterministic, Rule-Based, and Perfect Information models. Simulation results over 7 days using five years of real-world South African energy data show that the stochastic model strikes a favorable balance between cost and reliability. It incurs a total system cost of ZAR 1.748 billion, with 1625 MWh of load shedding and 1283 MWh of curtailment, significantly outperforming the deterministic model (ZAR 1.763 billion; 3538 MWh load shedding; 59 MWh curtailment) and the rule-based model (ZAR 1.760 billion, 1.809 MWh load shedding; 1475 MWh curtailment). The proposed stochastic framework demonstrates strong potential for improving renewable integration, reducing system penalties, and enhancing grid resilience in the face of forecast uncertainty. Full article

This paper presents a cross-layer intrusion detection framework leveraging explainable artificial intelligence (XAI) and interpretability methods to enhance transparency and robustness in attack detection within the Internet of Medical Things (IoMT) domain. By addressing the dual challenges of compromised data integrity, which span both biosensor and network-layer data, this study combines advanced techniques to enhance interpretability, accuracy, and trust. Unlike conventional flow-based intrusion detection systems that primarily rely on transport-layer statistics, the proposed framework operates directly on raw packet-level features and application-layer semantics, including MQTT message types, payload entropy, and topic structures. The key contributions of this research include the application of K-Means clustering combined with the principal component analysis (PCA) algorthim for initial categorization of attack types, the use of SHapley Additive exPlanations (SHAP) for feature prioritization to identify the most influential factors in model predictions, and the employment of Partial Dependence Plots (PDP) and Accumulated Local Effects (ALE) to elucidate feature interactions across layers. These methods enhance the system’s interpretability, making data-driven decisions more accessible to nontechnical stakeholders. Evaluation on a realistic healthcare IoMT testbed demonstrates significant improvements in detection accuracy and decision-making transparency. Furthermore, the proposed approach highlights the effectiveness of explainable and cross-layer intrusion detection for secure and trustworthy medical IoT environments that are tailored for cybersecurity analysts and healthcare stakeholders. Full article

Urban building energy retrofit (UBER) is a critical strategy for advancing the low-carbon and climate-resilience transformation of cities. The integration of machine learning (ML), data-driven clustering, and multi-objective optimization (MOO) is a key aspect of artificial intelligence (AI) that is transforming the process of retrofit decision-making. This integration enables the development of scalable, cost-effective, and robust solutions on an urban scale. This systematic review synthesizes recent advances in AI-driven MOO frameworks for UBER, focusing on how state-of-the-art methods can help to identify and prioritize retrofit targets, balance energy, cost, and environmental objectives, and develop transparent, stakeholder-oriented decision-making processes. Key advances highlighted in this review include the following: (1) the application of ML-based surrogate models for efficient evaluation of retrofit design alternatives; (2) data-driven clustering and classification to identify high-impact interventions across complex urban fabrics; (3) MOO algorithms that support trade-off analysis under real-world constraints; and (4) the emerging integration of explainable AI (XAI) for enhanced transparency and stakeholder engagement in retrofit planning. Representative case studies demonstrate the practical impact of these approaches in optimizing envelope upgrades, active system retrofits, and prioritization schemes. Notwithstanding these advancements, considerable challenges persist, encompassing data heterogeneity, the transferability of models across disparate urban contexts, fragmented digital toolchains, and the paucity of real-world validation of AI-based solutions. The subsequent discussion encompasses prospective research directions, with particular emphasis on the potential of deep learning (DL), spatiotemporal forecasting, generative models, and digital twins to further advance scalable and adaptive urban retrofit. Full article

Background: Solar urticaria is a rare and disabling photodermatosis. Due to its low prevalence, most available data regarding treatment are derived from observational studies and case series, and a systematic evaluation of treatment efficacy is lacking. This systematic review and meta-analysis aims to assess therapeutic outcomes across treatment modalities in order to guide clinical care. Methods: We conducted a systematic literature search across PubMed, ScienceDirect, the Cochrane Library, and ClinicalTrials.gov. Studies reporting treatment outcomes in patients with solar urticaria were included. Pooled response rates were calculated for each treatment modality. Results: Out of 508 studies initially identified, 38 met the inclusion criteria. Antihistamines were evaluated in 21 studies (376 patients), with a pooled response rate (partial or complete) of 83.0% (95% CI, 70.4–91.1%) and a complete response rate of 7.7% (95% CI, 1.7–28.3%). Phototherapy was assessed in 11 studies (145 patients), showing a similar overall response (89.8%; 95% CI, 77.9–95.3%) but a higher complete response rate (39.8%; 95% CI, 18.3–66.1%). Omalizumab, evaluated in nine studies (76 patients), demonstrated the highest efficacy, with 93.2% (95% CI, 73.8–98.5%) achieving response and 68.4% (95% CI, 48.5–83.2%) complete remission. Limited data on IVIG, cyclosporine, and plasmapheresis suggested partial efficacy in selected refractory cases. Conclusions: This meta-analysis may support clinical decision-making by clinicians. A stepwise approach is suggested: high-dose H₁ antihistamines as first-line therapy, phototherapy as an alternative option in patients with access to treatment centers, and omalizumab for those with insufficient response. In refractory cases, additional options might be considered. Full article

Recent advances in vision–language models (VLMs) have transformed the field of robotics. Researchers are combining the reasoning capabilities of large language models (LLMs) with the visual information processing capabilities of VLMs in various domains. However, most efforts have focused on terrestrial robots and are limited in their applicability to volatile environments such as ocean surfaces and underwater environments, where real-time judgment is required. We propose a system integrating the cognition, decision making, path planning, and control of autonomous marine surface vehicles in the ROS2–Gazebo simulation environment using a multimodal vision–LLM system with zero-shot prompting for real-time adaptability. In 30 experiments, adding the path plan mode feature increased the success rate from 23% to 73%. The average distance increased from 39 m to 45 m, and the time required to complete the task increased from 483 s to 672 s. These results demonstrate the trade-off between improved reliability and reduced efficiency. Experiments were conducted to verify the effectiveness of the proposed system and evaluate its performance with and without adding a path-planning step. The final algorithm with the path-planning sub-process yields a higher success rate, and better average path length and time. We achieve real-time environmental adaptability and performance improvement through prompt engineering and the addition of a path-planning sub-process in a limited structure, where the LLM state is initialized with every application programming interface call (zero-shot prompting). Additionally, the developed system is independent of the vision–LLM archetype, making it scalable and adaptable to future models. Full article

Neuroendocrine neoplasms (NENs) of the lung are a biologically and clinically diverse group of tumors that includes well-differentiated typical and atypical carcinoids (LNETs), as well as poorly differentiated large-cell neuroendocrine carcinoma and small-cell lung cancer. Despite their relative rarity, the incidence of LNETs is increasing, primarily due to advancements in diagnostic techniques and heightened clinical awareness. While the current World Health Organization (WHO) classification offers a morphological basis for diagnosis and prognosis, particularly for extrapulmonary neuroendocrine neoplasms (ep-NENs), it has limitations in predicting the clinical behavior of pulmonary carcinoids. Recent evidence highlights the inadequacy of traditional criteria in fully capturing the biological complexity and clinical heterogeneity of these tumors. This review explores the evolving landscape of LNETs, focusing on well-differentiated forms and analyzing current classification systems, clinicopathological features, and the emerging role of novel prognostic and predictive biomarkers. Advances in histopathology and molecular profiling have begun to elucidate distinct molecular subsets within carcinoids, offering potential avenues for improved risk stratification and therapeutic decision-making. Although there are limited treatment options for advanced disease, new insights into tumor biology could facilitate the development of personalized therapeutic strategies and pave the way for future innovations in LNET management. Full article

Background/Objectives: Accurate prediction of pediatric appendicitis diagnosis, management, and severity is critical for clinical decision-making. We aimed to evaluate the predictive performance of a wide range of machine learning models, combined with various feature selection techniques, on a pediatric appendicitis dataset. A particular focus was placed on the role of ultrasound (US) image-descriptive features in model performance and explainability. Methods: We conducted a retrospective cohort study on a dataset of 781 pediatric patients aged 0–18 presenting to Children’s Hospital St. Hedwig in Regensburg, Germany, between January 2016 and February 2023. We developed and validated predictive models; machine learning algorithms included the random forest, logistic regression, stochastic gradient descent, and the light gradient boosting machine (LGBM). These were paired exhaustively with feature selection methods spanning filter-based (association and prediction), embedded (LGBM and linear), and a novel redundancy-aware step-up wrapper approach. We employed a machine learning benchmarking study design where AI models were trained to predict diagnosis, management, and severity outcomes, both with and without US image-descriptive features, and evaluated on held-out testing samples. Model performance was assessed using overall accuracy and area under the receiver operating characteristic curve (AUROC). A deep learner optimized for tabular data, GANDALF, was also evaluated in these applications. Results: US features significantly improved diagnostic accuracy, supporting their use in reducing model bias. However, they were not essential for maximizing accuracy in predicting management or severity. In summary, our best-performing models were, for diagnosis, the random forest with embedded LGBM feature selection (98.1% accuracy, AUROC: 0.993), for management, the random forest without feature selection (93.9% accuracy, AUROC: 0.980), and for severity, the LGBM with filter-based association feature selection (90.1% accuracy, AUROC: 0.931). Conclusions: Our results demonstrate that high-performing, interpretable machine learning models can predict key clinical outcomes in pediatric appendicitis. US image features improve diagnostic accuracy but are not critical for predicting management or severity. Full article

Advanced computer vision (CV) and deep learning (DL) are essential for sustainable agriculture via automated vegetation management. This paper methodically reviews advancements in these technologies for agricultural settings, analyzing their fundamental principles, designs, system integration, and practical applications. The amalgamation of transformer topologies with convolutional neural networks (CNNs) in models such as YOLO (You Only Look Once) and Mask R-CNN (Region-Based Convolutional Neural Network) markedly enhances target recognition and semantic segmentation. The integration of LiDAR (Light Detection and Ranging) with multispectral imagery significantly improves recognition accuracy in intricate situations. Moreover, the integration of deep learning models with control systems, which include laser modules, robotic arms, and precision spray nozzles, facilitates the development of intelligent robotic mowing systems that significantly diminish chemical herbicide consumption and enhance operational efficiency relative to conventional approaches. Significant obstacles persist, including restricted environmental adaptability, real-time processing limitations, and inadequate model generalization. Future directions entail the integration of varied data sources, the development of streamlined models, and the enhancement of intelligent decision-making systems, establishing a framework for the advancement of sustainable agricultural technology. Full article

In disaster relief operations, integrating disaster reconnaissance, material delivery, and effect evaluation into a temporal task chain can significantly reduce emergency response cycles and improve rescue efficiency. However, since multiple types of heterogeneous UAVs need to be coordinated during the rescue temporal task chains assignment process, this places higher demands on the real-time dynamic decision-making and system fault tolerance of its task assignment algorithm. This study addresses the sequential dependencies among disaster reconnaissance, material delivery, and effect evaluation stages. A task allocation model for heterogeneous UAV swarm targeting temporal task chains is formulated, with objectives to minimize task completion time and energy consumption. A dynamic coalition formation algorithm based on temporary leader election and multi-round negotiation mechanisms is proposed to enhance continuous decision-making capabilities in complex disaster environments. A simulation scenario involving twenty heterogeneous UAVs and seven temporal rescue task chains is constructed. The results show that the proposed algorithm reduces average task completion time by 15.2–23.7% and average fuel consumption by 18.3–26.4% compared with cooperative network protocols and distributed auctions, with up to a 43% reduction in fuel consumption fluctuations. Full article

With the continuous advancement of artificial intelligence (AI) technology, AI algorithms have demonstrated exceptional aircraft control capabilities in highly dynamic and complex scenarios such as aerial combat. However, the inherent lack of explainability in AI algorithms poses a significant challenge to gaining sufficient trust, presenting potential safety risks that could lead to aircraft loss of control. This limitation hinders the widespread adoption of AI in practical applications. To enhance human–AI trust, improve system stability and safety, and advance the deployment of AI algorithms in practical settings, this study proposes an approach to describe and explain AI decision-making behaviors using natural language. Natural language is a straightforward medium for expressing information, which avoids the need for additional decoding or interpretation, particularly in rapidly changing battlefield environments, enabling pilots to quickly comprehend the intentions of AI algorithms and thereby fostering trust in AI systems. This study constructs a dataset of AI decision behavior description and interpretation based on adversarial temporal data in an aerial combat scenario and introduces an encoder–decoder framework that integrates an attentional mechanism. Findings from the experiments suggest that this approach effectively delineates and elucidates the AI decision-making behaviors, thereby facilitating mutual trust between humans and AI. Full article

Food product labels serve as a critical source of information, providing details about nutritional content, ingredients, and health implications. These labels enable Food and Drug Authorities (FDA) to ensure compliance and take necessary health-related and logistics actions. Additionally, product labels are essential for online grocery stores to offer reliable nutrition facts and empower customers to make informed dietary decisions. Unfortunately, product labels are typically available in image formats, requiring organizations and online stores to manually transcribe them—a process that is not only time-consuming but also highly prone to human error, especially with multilingual labels that add complexity to the task. Our study investigates the challenges and effectiveness of leveraging large language models (LLMs) to extract nutritional elements and values from multilingual food product labels, with a specific focus on Arabic and English. A comprehensive empirical analysis was conducted using a manually curated dataset of 294 food product labels, comprising 588 transcribed nutritional elements and values in both languages, which served as the ground truth for evaluation. The findings reveal that while LLMs performed better in extracting English elements and values compared to Arabic, our post-processing techniques significantly enhanced their accuracy, with GPT-4o outperforming GPT-4V and Gemini. Full article