Search Results (84)

Background/Objectives: As the primary cause of cancer-related death globally, lung cancer highlights the critical need for early identification, precise staging, and individualized treatment planning. By enabling automated diagnosis, staging, and prognostic evaluation, recent developments in artificial intelligence (AI) and machine learning (ML) have completely changed the treatment of lung cancer. The goal of this narrative review is to compile the most recent data on uses of AI and ML throughout the lung cancer care continuum. Methods: A comprehensive literature search was conducted across major scientific databases to identify peer-reviewed studies focused on AI-based imaging, detection, and prognostic modeling in lung cancer. Studies were categorized into three thematic domains: (1) detection and screening, (2) staging and diagnosis, and (3) risk prediction and prognosis. Results: Convolutional neural networks (CNNs), in particular, have shown significant sensitivity and specificity in nodule recognition, segmentation, and false-positive reduction. Radiomics-based models and other multimodal frameworks combining imaging and clinical data have great promise for forecasting treatment outcomes and survival rates. The accuracy of non-small-cell lung cancer (NSCLC) staging, lymph node evaluation, and malignancy classification were regularly improved by AI algorithms, frequently matching or exceeding radiologist performance. Conclusions: There are still issues with data heterogeneity, interpretability, repeatability, and clinical acceptability despite significant advancements. Standardized datasets, ethical AI implementation, and transparent model evaluation should be the top priorities for future initiatives. AI and ML have revolutionary potential for intelligent, personalized, and real-time lung cancer treatment by connecting computational innovation with precision oncology. Full article

Rainfall simulators are crucial devices in erosion research, enabling the controlled reproduction of precipitation characteristics for both laboratory and field investigations. This study presents a comprehensive characterization of a rainfall simulator originally designed to assess the erosive effects of precipitation on heritage surfaces. The simulator, installed at the University of León, was evaluated using volumetric methods and disdrometric techniques, employing a Parsivel² optical disdrometer. Simulations were conducted with a falling height of 10 m and high-intensity rainfalls. Spatial uniformity was assessed through thematic mapping and the Christiansen Uniformity (CU) coefficient, revealing limited uniformity across the full wetted area, but an improved performance within the central zone (CU up to 80%). Disdrometric data provided detailed insights into drop size and velocity distributions, enabling the estimation of rainfall intensity, kinetic energy, and momentum, as well as the spatial uniformity of the energetic parameters. Empirical models to estimate the raindrop’s fall velocity were tested against disdrometric measurements, confirming the simulator’s ability to generate rainfall with velocity characteristics comparable to those of natural precipitation. Moreover, the findings underscore the importance of integrating multiple measurement approaches to enhance the reliability and accuracy of rainfall simulator characterization. Full article

The integration of optical sensors and deep learning technologies in smart agriculture represents a critical intersection between technological innovation and agricultural economic sustainability, yet comprehensive assessments of their economic impact remain limited. This study applies a scientometric approach to 135 documents indexed in Scopus and Web of Science between January 2017 and June 2025, using Bibliometrix Bibliometrix (R package version 4.5.2), VOSviewer version 1.6.20, and Voyant Tools to examine publication trends, leading contributors, collaboration patterns, thematic structures, and reported economic outcomes. The analysis shows a strong upward trajectory with an estimated 66.48% annual increase in publications, identifying Xiukang Wang and Shaowen Wang as leading contributors among 791 authors from diverse institutions. Thematic analysis reveals three interconnected clusters: (i) precision agriculture and remote sensing as the sensing backbone; (ii) prediction and soil analysis as data-driven decision-support mechanisms; and (iii) vegetation indexes and productivity as measurement tools linking spectral information to yield and input use. Economic evidence includes high disease-detection accuracy (up to 95%), notable pesticide-use reductions (around 40%), improved autonomous-navigation precision (<6 cm error), and crop-detection performance exceeding 99%. However, adoption challenges persist, including technological heterogeneity, high implementation costs, limited model transferability, and varying levels of digital readiness across regions. Overall, the findings indicate that optical sensors and deep learning are transitioning from experimental applications to technologies with measurable economic impact, offering guidance for researchers, policymakers, technology developers, and agricultural producers seeking economically viable precision-agriculture solutions. Full article

The Caucasus Mountains are recognized as a global center of biodiversity but currently face significant risks of degradation due to intensified economic development and the effects of climate change. Forest inventory and mapping are essential for biodiversity conservation in the Caucasus region. Geospatial modeling is a common method of thematic mapping, but its reliability depends heavily on the initial classification of reference data used for model training. Modern vegetation science features various classification approaches, most of which were developed independently of digital mapping practices and are rarely assessed for their suitability in geospatial modeling. To fill this gap, we classified the same dataset of vegetation relevés from mixed and broadleaf forests in the northwestern Caucasus using two approaches, based on floristic and dominant concepts, and compared the predictive performance of geospatial models trained on these datasets. We considered multiple types of geospatial variables, including optical satellite imagery, a digital elevation model (DEM), and bioclimatic and soil features, to evaluate their informativeness for spatial differentiation of the resulting forest types and to identify optimal variable combinations for modeling via multistage feature selection. We trained several models using different variable sets and machine learning methods for both classifications and evaluated their accuracy via nested cross-validation. The forest types produced by the two approaches scarcely matched, and the selected variable sets for model training differed accordingly. Unexpectedly, bioclimatic and soil variables were more effective than DEM- and satellite-derived variables, despite their coarser spatial resolution. Floristic-based geospatial models outperformed dominant-based models in terms of forest-type separability and predictive accuracy. Therefore, a floristic classification approach may be preferable for forests with complex species composition, both ecologically and in terms of the reliability of geospatial modeling and the derived mapping results. Full article

Background: Artificial Intelligence (AI) is a transformative innovation designed to enable machines to perform tasks typically requiring human intelligence. Among various medical fields, cardiology—and particularly electrophysiology—has seen rapid integration of AI technologies. The ability of AI to analyze large and complex datasets is reshaping diagnostic and therapeutic approaches. Objectives: This review aims to provide a comprehensive overview of AI models and their applications in cardiac electrophysiology. The focus is on understanding how AI contributes to clinical practice through ECG interpretation, arrhythmia detection, atrial mapping, and catheter ablation, while also exploring its limitations and future potential. Methods: The review discusses various AI approaches, including Machine Learning (ML) and Deep Learning (DL), and highlights relevant literature illustrating their implementation in electrophysiological settings. Key clinical applications are examined thematically, with a narrative synthesis of current capabilities, technologies, and outcomes. Results: AI-based tools have demonstrated effectiveness in identifying supraventricular arrhythmias like atrial fibrillation (AF) and atrial flutter (AFL), as well as complex conditions such as ventricular tachycardias (VTs) and long QT syndrome (LQTS). In procedural contexts, AI enhances electro-anatomical mapping, reduces operative time, and supports tailored post-ablation management. Discussion: While AI offers clear advantages in diagnostic accuracy and procedural efficiency, challenges remain regarding data security, ethical transparency, and clinical adoption. Addressing these limitations will be crucial for integrating AI into routine electrophysiology and maximizing its potential in future cardiology practice. Full article

Hydrogel microneedles (HMNs) act as non-invasive devices that can effortlessly merge with the human body for drug delivery and diagnostic purposes. Nonetheless, their improvement is limited by intricate and repetitive issues related to material composition, structural geometry, manufacturing accuracy, and performance enhancement. At present, there are only a limited number of studies accessible since artificial intelligence and machine learning (AI/ML) for HMN are just starting to emerge and are in the initial phase. Data is distributed across separate research efforts, spanning different fields. This review aims to tackle the disjointed and narrowly concentrated aspects of current research on AI/ML applications in HMN technologies by offering a cohesive, comprehensive synthesis of interdisciplinary insights, categorized into five thematic areas: (1) material and microneedle design, (2) diagnostics and therapy, (3) drug delivery, (4) drug development, and (5) health and agricultural sensing. For each domain, we detail typical AI methods, integration approaches, proven advantages, and ongoing difficulties. We suggest a systematic five-stage developmental pathway covering material discovery, structural design, manufacturing, biomedical performance, and advanced AI integration, intended to expedite the transition of HMNs from research ideas to clinically and commercially practical systems. The findings of this review indicate that AI/ML can significantly enhance HMN development by addressing design and fabrication constraints via predictive modeling, adaptive control, and process optimization. By synchronizing these abilities with clinical and commercial translation requirements, AI/ML can act as key facilitators in converting HMNs from research ideas into scalable, practical biomedical solutions. Full article

Background: Functional lumbar segmental instability (FLSI) is a clinically significant subtype of nonspecific low back pain, characterized by impaired motor control during mid-range spinal motion. Despite its prevalence, diagnostic approaches remain fragmented, and no single clinical test reliably captures its complexity. This scoping review aims to synthesize current evidence on the reliability, validity, subclassification, and predictive value of manual tests used in the evaluation of FLSI, and to identify conceptual and methodological gaps in the literature. Methods: A structured search was conducted across five databases (PubMed, Scopus, Web of Science, CINAHL, Embase) between May and August 2025. Twenty-four empirical studies and eleven foundational conceptual sources were included. Data were charted into five thematic domains: conceptual frameworks, diagnostic accuracy, reliability, subclassification models, and predictive value. Methodological appraisal was performed using QUADAS and QAREL tools. Results: The Passive Lumbar Extension Test (PLET) demonstrated the most consistent reliability and clinical utility. The Prone Instability Test (PIT) and Posterior Shear Test (PST) showed variable performance depending on protocol standardization. Subclassification models distinguishing functional, structural, and combined instability achieved high inter-rater agreement. Screening tools for sub-threshold lumbar instability (STLI) showed preliminary feasibility. Predictive validity of manual tests for rehabilitation outcomes was inconsistent, suggesting the need for multivariate models. Conclusions: Manual tests can support the clinical evaluation of FLSI when interpreted within structured diagnostic frameworks. Subclassification models and composite test batteries enhance diagnostic precision, but standardization and longitudinal validation remain necessary. Future research should prioritize protocol harmonization, integration of sensor-based technologies, and stratified outcome studies to guide individualized rehabilitation planning. Full article

This paper presents an approach integrating Large Language Models (LLMs), specifically GPT-4 and the open-source DeepSeek-R1, into Geographic Information System (GIS) workflows to enhance the accessibility, flexibility, and efficiency of spatial analysis tasks. We designed and implemented a system capable of interpreting natural language instructions provided by users and translating them into automated GIS workflows through dynamically generated Python scripts. An interactive graphical user interface (GUI), built using CustomTkinter, was developed to enable intuitive user interaction with GIS data and processes, reducing the need for advanced programming or technical expertise. We conducted an empirical evaluation of this approach through a comparative case study involving typical GIS tasks such as spatial data validation, data merging, buffer analysis, and thematic mapping using urban datasets from Pesaro, Italy. The performance of our automated system was directly compared against traditional manual workflows executed by 10 experienced GIS analysts. The results from this evaluation indicate a substantial reduction in task completion time, decreasing from approximately 1 h and 45 min in the manual approach to roughly 27 min using our LLM-driven automation, without compromising analytical quality or accuracy. Furthermore, we systematically evaluated the system’s factual reliability using a diverse set of geospatial queries, confirming robust performance for practical GIS tasks. Additionally, qualitative feedback emphasized improved usability and accessibility, particularly for users without specialized GIS training. These findings highlight the significant potential of integrating LLMs into GISs, demonstrating clear advantages in workflow automation, user-friendliness, and broader adoption of advanced spatial analysis methodologies. Full article

Insider threats remain a persistent challenge in cybersecurity, as malicious or negligent insiders exploit legitimate access to compromise systems and data. This study presents a bibliometric review of 325 peer-reviewed publications from 2015 to 2025 to examine how machine learning (ML) and deep learning (DL) techniques for insider threat detection have evolved. The analysis investigates temporal publication trends, influential authors, international collaboration networks, thematic shifts, and algorithmic preferences. Results show a steady rise in research output and a transition from traditional ML models, such as decision trees and random forests, toward advanced DL methods, including long short-term memory (LSTM) networks, autoencoders, and hybrid ML–DL frameworks. Co-authorship mapping highlights China, India, and the United States as leading contributors, while keyword analysis underscores the increasing focus on behavior-based and eXplainable AI models. Symmetry emerges as a central theme, reflected in balancing detection accuracy with computational efficiency, and minimizing false positives while avoiding false negatives. The study recommends adaptive hybrid architectures, particularly Bidirectional LSTM–Variational Auto-Encoder (BiLSTM-VAE) models with eXplainable AI, as promising solutions that restore symmetry between detection accuracy and transparency, strengthening both technical performance and organizational trust. Full article

Background/Objectives: Evidence from transcriptomic and histopathologic studies has revealed that peri-implantitis lesions are characterized by deeper inflammatory infiltration, increased immune cell accumulation, and distinctive molecular signatures. This systematic review aimed to evaluate the diagnostic and pathophysiological potential of transcriptomic, metagenomic, and bioinformatic biomarkers in peri-implantitis by integrating findings from bioinformatics and machine learning-based studies. The dual objective was to identify biologically relevant markers and assess the accuracy of predictive models, addressing diagnostic gaps in peri-implant disease management. Methods: Eligible designs included cross-sectional, case–control, and cohort studies. Literature searches were conducted across PubMed, EMBASE, Scielo, and Scopus, with independent screening, data extraction, and quality assessment. Functional meta-synthesis was used to thematically organize biomarkers and pathways, while diagnostic meta-analysis pooled ROC-AUC values to assess model performance. Results: Eleven studies met the inclusion criteria. Functional synthesis revealed five recurring biomarker themes: innate and adaptive immune responses, immune cell infiltration, fibroblast activation, and ceRNA regulation. A meta-analysis of six studies reported a pooled AUC of 0.91 (95% CI: 0.88–0.93) with I² = 0%, indicating no heterogeneity, supporting the reliability of ML-based models in distinguishing peri-implantitis from healthy conditions. Sources of variation included differences in validation strategies and data preprocessing. Conclusions: Integrating transcriptomic, metagenomic, and bioinformatic biomarkers with machine learning may enable earlier and more accurate diagnosis of peri-implantitis. The identified biomarkers highlight molecular and microbial pathways linked to inflammation and tissue remodeling, underscoring their potential as diagnostic indicators and therapeutic targets with translational relevance. Full article

Spatial heterogeneity in soil deposition poses a significant challenge to accurate geotechnical characterization, which is essential for sustainable infrastructure development. This study presents an advanced geotechnical data-driven mapping framework, based on a monotonized and augmented formulation of Shepard’s inverse distance weighting (IDW) algorithm, implemented through the Google Earth Engine (GEE) platform. The approach is rigorously evaluated through a comparative analysis against the classical IDW and Kriging techniques using standard key performance indices (KPIs). Comprehensive field and laboratory data repositories were developed in accordance with international geotechnical standards (e.g., ASTM). Key geotechnical parameters, i.e., standard penetration test (SPT-N) values, shear wave velocity (Vs), soil classification, and plasticity index (PI), were used to generate high-resolution geospatial models for a previously unmapped region, thereby providing essential baseline data for building infrastructure design. The results indicate that the augmented IDW approach exhibits the best spatial gradient conservation and local anomaly detection performance, in alignment with Tobler’s First Law of Geography, and outperforms Kriging and classical IDW in terms of predictive accuracy and geologic plausibility. Compared to classical IDW and Kriging, the augmented IDW algorithm achieved up to a 44% average reduction in the RMSE and MAE, along with an approximately 30% improvement in NSE and PC. The difference in spatial areal coverage was found to be up to 20%, demonstrating an improved capacity to model spatial subsurface heterogeneity. Thematic design maps of the load intensity (LI), safe bearing capacity (SBC), and optimum foundation depth (OD) were constructed for ready application in practical design. This work not only establishes the inadequacy of conventional geostatistical methods in highly heterogeneous soil environments but also provides a scalable framework for geotechnical mapping with accuracy in data-poor environments. Full article

Background: Breast cancer is still the most common type of cancer worldwide. Advances and the global use of artificial intelligence (AI) have opened up new opportunities to improve diagnostic accuracy and optimize breast cancer screening. This review summarizes the findings from systematic reviews to assess the current situation of AI integration in mammography. Methods: A total of 28 systematic reviews were included and analyzed using a standardized narrative checklist to assess the impact of AI on mammography imaging. Bibliometric analysis and thematic synthesis were used to assess trends, evaluate the performance of AI in different modalities and identify challenges and opportunities for clinical implementation. Results and Discussion: AI technologies show an overall performance comparable to radiologists in terms of sensitivity and specificity, especially when integrated with human interpretation to detect breast cancer in mammography. However, most studies are retrospective, which raises concerns about their generalizability to real-world clinical settings. Key limitations include potential dataset bias—often stemming from the over-representation of specific imaging equipment or clinical environments—limited ethnic and demographic diversity, the lack of model explainability that hinders clinical trust, and an unclear or evolving legal and regulatory framework that complicates integration into standard practice. Conclusions: AI has the potential to transform mammography screening, but its integration into the real world requires prospective validation, ethical safeguards and robust regulatory oversight. Coordinated international efforts are essential to ensure that AI is used safely, fairly and effectively in breast cancer diagnostics. Full article

Sustainable shell structures are thin, curved systems such as domes, vaults, and cylindrical shells that achieve strength and stability primarily through membrane action, allowing significant material savings. Their sustainability lies in minimizing embodied energy and CO₂ emissions by using less material, integrating recycled or bio-based components, and applying optimization strategies to extend service life and enable reuse or recycling, all while maintaining structural performance and architectural quality. This review critically examines the state-of-the-art in sustainable shell structures, focusing on their buckling behavior and material-efficient design strategies. Integrating bibliometric analysis with thematic synthesis, the study identifies key research trends, theoretical advancements, and optimization tools that support structural efficiency. Emphasis is placed on recent developments in composite and bio-based materials, imperfection-sensitive buckling models, and performance-based design approaches. Advanced computational methods, including finite element analysis, machine learning, and digital twins, are highlighted as critical in enhancing predictive accuracy and sustainability outcomes. The findings underscore the dual challenge of achieving both structural stability and environmental responsibility, while outlining research gaps and future directions toward resilient, low-impact shell construction. Full article

Agriculture is the backbone of Punjab’s economy, and with much of India’s population dependent on agriculture, the requirement for accurate and timely monitoring of land has become even more crucial. Blending remote sensing with state-of-the-art machine learning algorithms enables the detailed classification of agricultural lands through thematic mapping, which is critical for crop monitoring, land management, and sustainable development. Here, a Hyper-tuned Deep Neural Network (Hy-DNN) model was created and used for land use and land cover (LULC) classification into four classes: agricultural land, vegetation, water bodies, and built-up areas. The technique made use of multispectral data from Sentinel-2 and Landsat-8, processed on the Google Earth Engine (GEE) platform. To measure classification performance, Hy-DNN was contrasted with traditional classifiers—Convolutional Neural Network (CNN), Random Forest (RF), Classification and Regression Tree (CART), Minimum Distance Classifier (MDC), and Naive Bayes (NB)—using performance metrics including producer’s and consumer’s accuracy, Kappa coefficient, and overall accuracy. Hy-DNN performed the best, with overall accuracy being 97.60% using Sentinel-2 and 91.10% using Landsat-8, outperforming all base models. These results further highlight the superiority of the optimised Hy-DNN in agricultural land mapping and its potential use in crop health monitoring, disease diagnosis, and strategic agricultural planning. Full article

This research investigates topic-based sentiment classification in Greek educational-related data using transformer-based language models. A comparative evaluation is conducted on GreekBERT, XLM-r-Greek, mBERT, and Palobert using three original sentiment-annotated datasets representing parents of students with functional diversity, school directors, and teachers, each capturing diverse educational perspectives. The analysis examines both overall sentiment performance and topic-specific evaluations across four thematic classes: (i) Material and Technical Conditions, (ii) Educational Dimension, (iii) Psychological/Emotional Dimension, and (iv) Learning Difficulties and Emergency Remote Teaching. Results indicate that GreekBERT consistently outperforms other models, achieving the highest overall F1 score (0.91), particularly excelling in negative sentiment detection (F1 = 0.95) and showing robust performance for positive sentiment classification. The Psychological/Emotional Dimension emerged as the most reliably classified category, with GreekBERT and mBERT demonstrating notably high accuracy and F1 scores. Conversely, Learning Difficulties and Emergency Remote Teaching presented significant classification challenges, especially for Palobert. This study contributes significantly to the field of sentiment analysis with Greek-language data by introducing original annotated datasets, pioneering the application of topic-based sentiment analysis within the Greek educational context, and offering a comparative evaluation of transformer models. Additionally, it highlights the superior performance of Greek-pretrained models in capturing emotional detail, and provides empirical evidence of the negative emotional responses toward Emergency Remote Teaching. Full article