Search Results (205)

With the rapid development of Industrial Internet-oriented smart energy systems, hydro-turbine generator units are increasingly monitored through networked sensors, industrial communication infrastructures, and edge/cloud-based condition-monitoring platforms. These Internet-connected monitoring environments provide abundant vibration data for intelligent operation and maintenance (O&M) but also introduce a challenging unsupervised cross-scenario diagnosis problem. Specifically, diagnostic models trained on labeled historical data may suffer severe performance degradation when deployed to unlabeled online data collected under different hydraulic conditions, rotational speeds, or operating conditions. Furthermore, existing domain adaptation methods, in their pursuit of distribution alignment, frequently overlook a critical bottleneck that limits generalization performance: inter-class entanglement. Specifically, under intense hydraulic background noise and cross-condition distribution shifts, features belonging to distinct fault types are highly susceptible to aliasing within the feature space. To overcome these issues, this paper proposes a Conditional Wasserstein Adversarial Network with Bi-level Prototype Disentanglement Regularization (CWAN-BPDR). First, a Conditional Wasserstein Adversarial Network (CWAN) is constructed by combining the smooth-gradient property of Wasserstein distance with conditional adversarial alignment, thereby achieving stable and fine-grained category-level domain adaptation. Furthermore, to alleviate the inter-class entanglement problem that may arise during cross-domain alignment, a Bi-level Prototype Disentanglement Regularization (BPDR) term is designed. By jointly implementing source–target prototype alignment and prototype–feature bidirectional alignment, BPDR explicitly suppresses inter-class confusion and enhances intra-class compactness and inter-class separability in the feature space. Experimental results on the JNU and NEFU datasets demonstrate that CWAN-BPDR achieves average diagnostic accuracies of 97.82% and 98.99%, respectively, while significantly mitigating label entanglement in challenging cross-operating-condition tasks. These results indicate that the proposed method can effectively transfer diagnostic knowledge acquired from labeled historical operating conditions to unlabeled online monitoring data. It can therefore serve as an offline-trained diagnostic module for Industrial Internet of Things-based condition-monitoring platforms in hydropower systems. Full article

Under the Yellow River Basin’s strategic imperative of ecological protection and high-quality development, the critical question is whether rapid urbanization’s population agglomeration and land expansion are genuinely aligned with-or increasingly decoupled from-underlying economic vitality. To address this, we construct a unified analytical framework that synchronously captures coupling coordination, decoupling trajectories, and land-use efficiency, operationalized through multi-source county-level panel data for the Jinan Metropolitan Area in lower Yellow River Basin across 2000, 2010, and 2020. Unlike conventional two-dimensional assessments, the framework distinguishes system coordination, evolutionary direction, and input–output performance while using harmonized nighttime light data to capture the spatial intensity of economic vitality. The results show that: (1) the mean county-level coordination grade increased from 4.76 to 5.32, although strong core–periphery disparities persisted; (2) the decoupling structure shifted from relative homogeneity to pronounced differentiation, and strongly decoupled counties accounted for 48% of all units by 2020; and (3) average efficiency rose from 0.25 to 0.39, but most counties remained below the efficiency frontier, producing a pattern of central agglomeration and peripheral dispersion. Cross-classification further identifies coordinated but inefficient, efficient but dysfunctional, and low-coordination–low-efficiency trajectories that cannot be detected using a single model. The framework therefore provides a transferable diagnostic tool for differentiated territorial planning in metropolitan regions undergoing rapid structural transformation. Full article

Overview: SeptiCyte RAPID is an FDA-cleared gene expression test that quantifies host immune response to aid in the diagnosis of sepsis. The test yields a score (the SeptiScore) ranging from 0–15, distributed across four bands (1–4) based on increased likelihood of sepsis. Each band can be characterized by average positive and negative likelihood ratios (LR+ and LR−, respectively) for the discrimination of sepsis versus the non-infectious systemic inflammatory response syndrome (SIRS). Methods: A retrospective analysis of prospectively collected data from a combined cohort of critically ill patients suspected of sepsis (n = 889), recruited across 19 hospitals in the USA and Europe. The analysis quantified the LR+ and LR− parameters as a function of SeptiScore, for discrimination of sepsis vs. SIRS in patients admitted to ICU. Hypotheses: (1) The likelihood ratio (LR) framework provides a clinically useful interpretive approach that complements the previously used SeptiScore banding scheme; (2) Low Band 1 SeptiScores are associated with sufficiently small LR− to support the use of SeptiCyte RAPID as a rule-out test for sepsis; (3) High Band 4 SeptiScores are associated with sufficiently large LR+ to support the use of SeptiCyte RAPID as a rule-in test for sepsis; and (4) SeptiScore-derived LR+ and LR− values can be combined with estimates of pre-test probability (derived from patient characteristics and/or other diagnostic tests) to generate individualized, patient-specific post-test probabilities of sepsis. Results: The SeptiCyte RAPID test demonstrates strong diagnostic performance in distinguishing sepsis from SIRS. The likelihood ratios across different score bands provide clear clinical utility: the median LR+ was 3.26 (range 2.57–4.24) for Band 3, and 6.97 (range 4.35–15.57) for Band 4, providing evidence toward ruling in sepsis at high SeptiScores. Conversely, the median LR− was 0.16 (range 0.14–0.20) for Band 2 and 0.085 (range 0.014–0.16) for Band 1, providing evidence toward ruling out sepsis at low SeptiScores. A higher-resolution analysis of SeptiCyte RAPID performance confirmed these trends by evaluating LR+ and LR− at specific values within each band. The sepsis group was further stratified according to whether patients were classified as blood culture positive (BC+) or blood culture negative (BC−), and the detailed LR+ and LR− analyses were repeated. A monotonic increase in likelihood ratio with increasing SeptiScore was consistently observed, independent of whether sepsis patients were culture-positive, culture-negative, or unstratified with respect to blood culture status. Conclusions: High SeptiScores have correspondingly high LR+ values, and low SeptiScores have correspondingly low LR− values, both of which may have clinical utility. High likelihood ratios for Band 4 SeptiScores, which precede traditional microbiology results, may provide clinicians with early confidence of a sepsis diagnosis and microbiology diagnostic stewardship. Low likelihood ratios for Band 1 SeptiScores may prompt clinicians to consider an alternate diagnosis to sepsis. These are diagnostic-performance-based observations; whether they translate into fewer missed diagnoses or more efficient use of hospital resources has not been directly assessed in this study and will require dedicated clinical outcome studies. Full article

Mpox remains an important public health threat in several African countries, with recurrent outbreaks highlighting the need for decentralized and scalable diagnostic systems. During the 2024–2025 Mpox outbreak in Burundi, reliance on a single National Reference Laboratory limited timely diagnosis, reduced surveillance efficiency, and delayed outbreak response activities. This study describes and evaluates the implementation of a national strategy for decentralizing and expanding Mpox diagnostic capacity across Burundi. A descriptive implementation study was conducted between August 2024 and July 2025. Burundi implemented a four-phase diagnostic scale-up strategy that expanded Mpox testing services from one centralized laboratory to 56 decentralized GeneXpert-equipped laboratories, including mobile laboratory units. The implementation phases comprised strategic planning and risk mapping, pilot deployment at the national level, regional expansion, and extension to peripheral district laboratories. Key interventions included healthcare workforce training, strengthening laboratory supply chains, deployment of mobile diagnostic units, and integration of laboratory information into the national surveillance system. Program performance was assessed using indicators of laboratory network expansion, testing coverage, diagnostic turnaround time, and confirmed case detection. Following implementation, the number of operational Mpox diagnostic sites increased from 1 to 56, representing a 5500% expansion in testing capacity. National testing coverage approached 100%, substantially improving geographical access to diagnostic services. Weekly confirmed Mpox case detection increased by 496%, reflecting enhanced surveillance sensitivity and improved case identification. Diagnostic turnaround time decreased from 24–72 h under the centralized model to 2–4 h following decentralization. The expanded diagnostic network facilitated earlier case confirmation, more rapid isolation of infected individuals, strengthened surveillance activities, and accelerated implementation of outbreak control measures. The phased decentralization of Mpox diagnostics using existing GeneXpert infrastructure and mobile laboratories substantially improved testing access, reduced diagnostic delays, and strengthened outbreak response capacity in Burundi. This approach demonstrates a practical, scalable, and cost-effective model for enhancing epidemic preparedness and building resilient diagnostic systems in resource-constrained settings. Similar strategies could support improved detection and control of Mpox and other emerging infectious diseases across Africa and comparable low-resource environments. Full article

Various methodologies have been developed over the years to assess model predictive control (MPC) performance. However, few have been applied in industry, and they remain limited in terms of providing a rapid indication of the root causes of deteriorated control performance. This article aims to review the existing methodologies in the literature that address these challenges. Additionally, it implements a structure in which MPC performance assessment is integrated within a fault detection and diagnosis (FDD) framework. The integrated approach employs cascaded modules of machine learning (ML) binary classifiers arranged in a sequence that mimics the decision-making logic of an operator. To illustrate the integrated strategy both conceptually and operationally, a van de Vusse reactor, controlled by a nonlinear model predictive controller (NMPC), is used as a case study. The ML models evaluated include XGBoost, Random Forest, Multilayer Perceptron, Long Short-Term Memory, and Gated Recurrent Unit. The results show that these models can correctly distinguish the cause of abnormalities, even in the presence of measurement noise, with a detection accuracy of 99% and an abnormality classification accuracy above 85% for the best-performing models. Different ML models performed best for distinct diagnostic tasks, highlighting the flexibility of arranging models according to their most suitable application. The investigation indicates that the proposed ML-based FDD framework, which embeds control performance assessment, is competitive for control-aware diagnosis of MPC-controlled processes. Full article

Rapid and accurate identification of various faults occurring in transmission lines is essential for restoring normal line operation. However, existing transmission line fault diagnosis methods still face challenges in terms of noise immunity and diagnostic accuracy. To address these issues, this paper proposes a deep learning method based on recurrence plots and a convolutional neural network–bidirectional gated recurrent unit–attention mechanism model. The voltage and current signals of transmission lines are transformed into recurrence plots in both the time and frequency domains. Parallel convolutional neural networks are then employed to extract local features from the two domains, while bidirectional gated recurrent units are used to capture temporal dependencies. Furthermore, multi-head self-attention and cross-attention mechanisms are introduced to enhance key features within each domain and achieve adaptive fusion of inter-domain feature information. A transmission line model is established in Simulink to collect data under various fault conditions and influencing factors, thereby verifying the effectiveness and adaptability of the proposed method. Experimental results show that the proposed method achieves fault recognition accuracies of 99.63%, 96.68%, and 75.38% under NL1, NL2, and NL3 Gaussian-noise conditions, respectively, and maintains accuracies of 99.02%, 95.93%, and 72.43% under mixed-noise conditions. Compared with other deep learning models, the proposed method demonstrates higher diagnostic accuracy and stronger robustness. Full article

Rapid surrogate models are attractive for iterative computational fluid dynamics (CFD) design loops, though defining their operating envelope remains crucial. This study proposes RenaNet, a Reynolds-aware convolutional gated recurrent unit (ConvGRU) surrogate, for predicting two-dimensional laminar and transitional flows past cylinder and square obstacles. Using two initial flow snapshots and a Reynolds-number map, the model predicts spatiotemporal flow states up to 2000 time steps into the future, with Lattice Boltzmann Method (LBM) simulations serving as ground truth. Trained on Reynolds numbers of $1\le \mathrm{Re}\le 500$ (cylinder) and $1\le \mathrm{Re}\le 250$ (square), RenaNet achieves a minimum validation mean squared error (MSE) of $1.47\times {10}^{-5}$. A Reynolds-number ablation shows that removing the conditioning channel increases the validation MSE to $1.17\times {10}^{-3}$, while a ConvLSTM baseline gives $9.94\times {10}^{-4}$ with 24% more parameters. RenaNet also uses a direct long-horizon prediction interface for distant target frames. Auxiliary physics diagnostics confirm that predictions trained via MSE maintain acceptable continuity residuals across fitting, interpolation, and extrapolation cases. The average inference time for a 1000-step prediction horizon is approximately 1.25 s, delivering a 500-fold speedup over the reference LBM solver. Interpolation errors range from ${10}^{-4}$ to ${10}^{-2}$ depending on Reynolds number and geometry, while extrapolation beyond the training regime increases errors to the order of ${10}^{-2}$. These results establish RenaNet as a robust, parameter-efficient surrogate for laminar and transitional flows, with a clearly characterized operational boundary that informs future extensions into turbulent regimes. Full article

Background: Abdominal pain in hematological patients, particularly during chemotherapy-induced neutropenia, represents a significant diagnostic challenge due to the broad spectrum of potentially life-threatening conditions, including neutropenic enterocolitis (NEC). Computed tomography (CT) is considered the reference imaging modality; however, its use is limited by radiation exposure, and the need for patient transport. Bedside ultrasound (BS-US) may offer a rapid, non-invasive, and repeatable alternative. Methods: This prospective study compared BS-US and CT in 65 hematological patients presenting with acute abdominal pain. Concordance between the two modalities was evaluated in terms of intestinal site localization, bowel wall thickness (BWT), and final diagnosis. Diagnostic agreement was assessed using Cohen’s kappa coefficient, and additional diagnostic accuracy metrics—including sensitivity, specificity, positive predictive value, and negative predictive value—were calculated. BWT measurements were analyzed using Bland–Altman methods. Results: A high level of agreement was observed between BS-US and CT in both intestinal localization and final diagnosis. Agreement for intestinal site localization was good (Cohen’s κ = 0.964), as was diagnostic concordance (Cohen’s κ = 0.962), and using CT as the reference standard, BS-US showed uniformly good diagnostic performance across all evaluated conditions, with sensitivity, specificity, PPV, and NPV consistently reaching 1.00 and confirming strong agreement between BS-US and CT. These findings were consistent across different clinical settings (hematology unit and Intensive Care Unit) and independent of body mass index. In NEC cases, BWT measurements showed strong concordance between CT and BS-US, with only 4.6% of values outside the limits of agreement in Bland–Altman analysis. Conclusions: BS-US demonstrated a good agreement with CT and proved to be a reliable, safe diagnostic tool in hematological patients with acute abdominal pain. These findings indicate that bedside ultrasound represents a valuable and safe diagnostic tool in neutropenic hematological patients with acute abdominal pain, providing crucial information in a clinically fragile population that may not always be suitable for CT due to their unstable condition. While our study is hypothesis-generating, the role of BS-US in this setting emerges as a reasonable, evidence-supported hypothesis that warrants further prospective evaluation. Full article

Background: The rehabilitation of patients who have undergone extensive maxillectomy for neoplastic lesions is a significant clinical challenge. The resulting anatomical and functional defects severely impact quality of life, and traditional removable prostheses often lack stability. Zygomatic implants offer a viable solution by providing stable anchorage in the zygomatic bone, bypassing the need for bone reconstruction. Methods: This case report details the rehabilitation of a 62-year-old female patient with a history of recurrent oral squamous cell carcinoma. A fully digital workflow, including CBCT and CAD/CAM technology, was used for meticulous surgical and prosthetic planning. The surgical procedure involved a guided maxillectomy, a free forearm flap reconstruction, and the simultaneous placement of two zygomatic implants and one conventional implant. The procedure was done with EZGOMA guided surgery, which, starting from the EZPLAN software design of zygomatic and traditional implants, allowed us to determine the implant’s position in the three-dimensional axes and also the position of the internal hexagon. This allowed us to design the implant beneath the diagnostic wax-up in the three axes, and also to calculate the degrees of inclination of the multi-unit abutment. Results: All implants achieved primary stability with a torque exceeding 45 Ncm. The patient received an immediate provisional prosthesis, which allowed for the rapid restoration of phonetic and esthetic function. The post-operative course was uneventful, with no complications. Follow-up imaging confirmed the successful integration of the implants and the absence of any prosthetic or surgical issues at 24-month successful follow-up. Conclusions: This case suggests that implant-supported rehabilitation with zygomatic implants can be a highly effective treatment for patients with severe maxillary defects following cancer surgery. By using an integrated surgical and prosthetic strategy, along with advanced digital technology, we can achieve fast, safe, and predictable results. This approach successfully restores both function and esthetics, even in challenging anatomical situations. The auxilium of guided plates is a helpful aid for both implant placement and managing bone resection during cancer surgery. Full article

Rapid urbanization and the aging of large-scale building stocks have created a critical disconnection between strategic urban planning and physical structural realities. This study introduces a multi-dimensional resilience framework to evaluate the structural integrity and socio-economic exposure of Riga’s urban fabric at the parcel level. By integrating high-resolution wear-out data with a normalized Economic Priority Index (EPI), the study analyzes the distribution of 2405 buildings identified in the terminal wear-out phase of the Bathtub Curve reliability model. The results reveal that 92.7% of critically vulnerable buildings fall outside the scope of the city’s RTIAN 2030 strategic intervention framework, including the majority of high-risk structures supporting 13,416 business units and 646,033 residents. Spatial intersection analysis further demonstrates that contemporary modernization initiatives, including digital pilot zones, effectively bypass 98% of these critical structural hotspots. Predictive scenario analysis confirms that without a strategic reorientation toward a proactive, reliability-based monitoring framework, these excluded corridors face an exponential escalation of structural risk. Specifically, this study examines the urban spatial resilience of Riga’s building stock through the integrated PLE-Bathtub Curve framework, evaluates the spatial alignment of RTIAN 2030 with identified vulnerability zones, and assesses how effectively Smart City pilot initiatives target structurally vulnerable clusters defined by the Economic Priority Index (EPI). This research provides a replicable diagnostic framework, calibrated for post-socialist urban contexts, to support municipal authorities in realigning investment priorities with empirical physical vulnerabilities, ensuring long-term metropolitan continuity. Full article

Serratia marcescens has emerged as an important opportunistic pathogen in intensive care units (ICUs), where critically ill patients, invasive devices, antimicrobial exposure, and complex environmental reservoirs create favorable conditions for colonization, infection, and recurrent outbreaks. This narrative review synthesizes evidence from the past decade regarding the clinical and molecular epidemiology, environmental persistence, device-associated transmission, biofilm-mediated resistance, and infection-control strategies of S. marcescens in ICU settings. The literature was reviewed using an integrative approach informed by Ferrari’s narrative review framework, with thematic synthesis across clinical, microbiological, environmental, and genomic domains. Recent evidence indicates that ICU-associated S. marcescens infections frequently involve respiratory tract colonization, ventilator-associated pneumonia, bloodstream infection, urinary tract infection, and device-related transmission. Hospital water systems, sink drains, wet surfaces, ventilator circuits, reusable equipment, and contaminated antiseptic or liquid products may serve as persistent reservoirs, particularly when biofilm formation supports long-term survival and recurrent dissemination. At the molecular level, S. marcescens demonstrates substantial genomic diversity, intrinsic and acquired antimicrobial resistance, inducible AmpC β-lactamase activity, efflux-mediated tolerance, and plasmid-associated resistance gene transfer. This review particularly emphasizes the molecular determinants that enable S. marcescens to persist in ICU ecosystems, including AmpC-mediated β-lactam resistance, efflux-associated tolerance, quorum-sensing-regulated biofilm formation, plasmid-mediated horizontal gene transfer, and WGS-defined clonal transmission. Whole-genome sequencing, rapid molecular diagnostics, active surveillance, environmental sampling, and integrated infection-control bundles have become increasingly important for distinguishing clonal outbreaks from endemic transmission and guiding timely interventions. Emerging perspectives emphasize the need to combine antimicrobial stewardship, environmental engineering, respiratory-care auditing, anti-biofilm strategies, and AI-assisted real-time surveillance into adaptive ICU infection-control frameworks. Overall, S. marcescens should be regarded not merely as an episodic outbreak organism, but as a highly adaptable ICU-associated pathogen requiring multidisciplinary prevention strategies. Full article

The global rise in multidrug-resistant (MDR) fungal pathogens has positioned Candida auris and Candida glabrata as major threats to public health. In recent years, these pathogens have increasingly been reported beyond traditional hospital settings, including neonatal intensive care units, long-term care facilities, oncology wards, and post-pandemic critical care environments. International surveillance bodies, including the Centers for Disease Control and Prevention (CDC), European Centre for Disease Prevention and Control (ECDC), World Health Organization (WHO), and regional monitoring networks, have documented escalating antifungal resistance, complex outbreak dynamics, and persistent gaps in infection control implementation. C. auris has emerged as a major etiological agent of healthcare-associated outbreaks, particularly in intensive care and neonatal units. Surveillance data indicate that a high proportion of C. auris isolates exhibit resistance to azoles, often exceeding 80% in some regions, while echinocandin resistance remains variable. Resistance patterns have evolved from predominantly azole resistance to broader multidrug-resistant phenotypes, including treatment-emergent echinocandin resistance. Six genetically distinct clades (I–VI) have been identified, with Clades I, III, and IV associated with large-scale outbreaks, whereas available data suggests that Clades II, V, and VI are more geographically restricted, although evidence for the recently described clades remains limited. C. glabrata is increasingly recognized as a major cause of invasive candidiasis, with rising resistance reported across multiple regions. While reduced azole susceptibility was historically predominant, emerging evidence highlights rising dual azole–echinocandin resistance, adaptive microevolution during antifungal therapy, and biofilm-associated tolerance mechanisms. Despite these advances, significant gaps persist in global resistance surveillance and in the mechanistic understanding of virulence and antifungal adaptation. Current mitigation strategies include antifungal stewardship programs, expanded resistance testing, and strengthened surveillance systems. Advances in rapid diagnostic technologies such as matrix-assisted laser desorption ionization–time of flight (MALDI-TOF) mass spectrometry, polymerase chain reaction (PCR)-based assays, and genomic surveillance have improved pathogen identification and outbreak detection, although accessibility remains limited in resource-constrained settings. This review examines emerging epidemiological, genomic, and antifungal resistance trends in C. auris and C. glabrata and highlights key priorities for improving diagnosis, surveillance, stewardship, and management of multidrug-resistant Candida infections. Full article

Pediatric respiratory infections remain among the leading causes of emergency department visits, hospitalization and pediatric intensive care unit (PICU) admission. Although most acute respiratory infections in children are viral, clinical manifestations overlap substantially among viral, bacterial and atypical pathogens, creating diagnostic uncertainty and promoting empirical antimicrobial use. Rapid antigen tests, nucleic acid amplification tests, multiplex respiratory panels and metagenomic sequencing have expanded the ability to detect pathogens within clinically actionable timeframes. However, evidence from pediatric emergency trials indicates that rapid pathogen detection alone does not necessarily reduce antibiotic prescribing or healthcare costs. These findings suggest that the value of rapid diagnostics depends less on analytical breadth than on whether testing is applied to the right child, in the right clinical scenario and within a predefined decision pathway. This narrative review reorganizes the evidence around a scenario-driven top-pathogen framework. Top pathogens are defined as organisms that, in a specific age group, syndrome, season or care setting, have high prevalence, severe disease potential, transmissibility, treatment implications, antimicrobial resistance relevance or infection-control value. We discuss how top-pathogen testing should differ across emergency triage, inpatient ward management, severe pneumonia, PICU care, hospital-acquired pneumonia, ventilator-associated pneumonia and outbreak settings. We further examine the economic mechanisms through which rapid testing may generate value, including reduced unnecessary antibiotics, timely antiviral therapy, optimized isolation, shorter length of stay, reduced repeated testing and prevention of healthcare-associated transmission. Finally, we propose implementation principles centered on diagnostic stewardship, antimicrobial stewardship, local epidemiology and real-world cost-effectiveness evaluation. A scenario-driven top-pathogen strategy may provide a practical bridge between broad syndromic testing and precision infectious disease management in children. Full article

The diagnosis of enteric fever has become difficult due to the nonspecific and overlapping clinical syndrome of typhoid and paratyphoid infections with other febrile illnesses. Moreover, the rapid emergence of fluoroquinolone-resistant typhoidal Salmonella and the lack of robust diagnostic methods highlight the urgent need for highly sensitive molecular techniques. Here, we evaluated the performance of a rapid, reliable, and cost-effective molecular diagnostic approach for detecting Salmonella Typhi, including the globally dominant haplotype H58 lineage (H58), and Salmonella Paratyphi A. An in-house-built conventional polymerase chain reaction (PCR) was performed on a collection of blood-culture-positive strains, and the sensitivity and specificity were compared with those of the standard blood culture results. H58 and non-H58 Typhi lineages with distinct resistance patterns were confirmed from the previously reported sequencing data. Our PCR result showed that target genes SSPA2308, STY2513, and STY0307 demonstrated 100% sensitivity and specificity for Salmonella Paratyphi A, Salmonella Typhi, and H58 Salmonella Typhi, respectively. The PCR assay reliably detected bacterial DNA at 5.2 × 10⁴ colony-forming units (CFUs), with consistent amplification observed up to 10⁻¹ dilution. This single-nucleotide polymorphism (SNP)-based diagnostic approach has added a new dimension to designing unique markers for multidrug-resistant (MDR)-associated H58 lineage detection and has the potential to inform local treatment algorithms. Full article

This study proposes and validates a framework that integrates Grey Wolf Optimization (GWO) with Extreme Gradient Boosting (XGBoost) for estimating the Poisson’s ratio of auxetic structures. First, for 320 models derived from Computer-Aided Design-based (CAD-based) unit-cell designs, a systematic sweep of diameter and cellular dimensions was conducted to obtain porosity coverage in the 45–85% range. Subsequently, elastic modulus and Poisson’s ratio were computed via finite element analysis (FEA) at three mesh resolutions (0.20/0.25/0.30 mm), and relationships between design variables and outputs were examined using correlation heatmaps and Locally Weighted Scatterplot Smoothing (LOWESS) curves. GWO optimized the XGBoost hyperparameters through a multi-band narrowed search strategy; performance was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Coefficient of Determination ($R^2$) metrics, as well as residual diagnostics and Ground Truth–Prediction alignments for Poisson’s ratio. Across all configurations, $R^2\ge 0.994$ and absolute errors are on the order of ∼${10}^{-3}$; the 0.25 mm mesh stands out in terms of overall balance with the lowest squared-error profile and the highest $R^2$, the 0.30 mm mesh is practically equivalent in terms of MAE, and the 0.20 mm mesh is comparatively weaker. Residual diagnostics—comprising a pattern-free cloud around zero, slight right-skewness, and limited heteroskedasticity—indicate low bias and no substantive model-specification issues. The findings align with physical insight, confirming that Poisson’s ratio shifts toward more negative values as porosity increases and toward less negative values as diameter increases. The proposed GWO–XGBoost framework provides a reliable pre-screening tool for rapid design exploration and Poisson’s-ratio-targeted optimization, with the potential to reduce the need for additional FEA simulations and experimental iterations during early-stage design. Full article