Search Results (64)

Background: Large language models (LLMs) are increasingly considered as adjuncts for differential diagnostic reasoning, yet their sensitivity to gender-attributed cues in the persona prompt—particularly for neglected tropical diseases (NTDs) and in non-English clinical settings—remains poorly characterised. Objective: The objective of this study was to compare the diagnostic accuracy of one proprietary and three open-weight LLMs for Chagas disease (CD) and visceral leishmaniasis (VL) under paired persona-prompt conditions in which the only manipulated variable was the linguistic gender of the simulated medical persona. Methods: This experimental, paired study evaluated ChatGPT-4o, LLaMA 3 70B, Meditron-70B, and Mixtral 8x7B across 12 cases per disease (n = 24) from real records at a Brazilian teaching hospital. The primary outcome was top-five diagnostic accuracy. A committee of five infectious-disease specialists assessed the biological plausibility of all differentials. Paired comparisons used Wilcoxon signed-rank tests; 95% confidence intervals were calculated using the Wilson-score method. Results: ChatGPT-4o achieved the highest accuracy (CD: 100% under both prompts; VL: 83.3–91.7%). LLaMA 3 70B and Mixtral 8x7B showed moderate performance (41.7–83.3%); the medically fine-tuned Meditron-70B exhibited paradoxically poor accuracy (16.7–25.0%) and the lowest committee-rated plausibility scores. A consistent small numerical trend favoured the female prompt across most model–disease combinations (differences of 0–16.7 percentage points), but no comparison reached statistical significance (all p > 0.05). Conclusions: Gender-attributed persona-prompt variation did not produce a systematic effect on LLM diagnostic accuracy for CD or VL. ChatGPT-4o outperformed the three evaluated open-weight alternatives, and medical-domain fine-tuning did not confer the expected advantage. Expert-validated assessment of hypothesis plausibility should complement target-disease accuracy in clinical LLM evaluation studies, particularly for NTDs. Full article

Hidden disaster-causing factor investigation is a fundamental task for safety production in mines. Water hazards in karst metal underground mines are characterized by complex disaster-forming mechanisms, strong suddenness, and high risk, while traditional assessment methods are prone to expert subjective bias and cannot meet the demand for precise prevention and control. This study proposes an improved fuzzy comprehensive evaluation model by integrating the analytic hierarchy process (AHP) and normal distribution-based expert confidence weighting. A three-level assessment index system consisting of 3 first-level indicators and 11 s-level indicators is established for karst metal mine water hazard risk. The normal distribution function is used to quantify expert confidence weights so as to reduce subjective deviation. A three-level fuzzy comprehensive evaluation is performed to achieve quantitative risk grading, and the model robustness is verified through sensitivity analysis. Furthermore, three-dimensional geological modeling and seepage–stress coupling numerical simulation are conducted using COMSOL 6.0 software to validate the reliability of assessment results. The Mao’erling Gold Mine in Hunan Province is taken as a case study. The evaluation yields a comprehensive membership vector of (0.103, 0.130, 0.184, 0.351, 0.232), which is strongly consistent with numerical simulation results and field water inrush records. The results demonstrate that the improved model features strong objectivity and favorable robustness, and can provide a scientific basis for water hazard investigation, risk assessment, and prevention engineering in karst metal underground mines. Full article

The rapid expansion of the new energy vehicle (NEV) market underscores a critical gap in the absence of a scientific health evaluation method for official inspections and annual checks. To address this, our study develops a comprehensive and quantitative health calibration system tailored for four specific application scenarios: annual inspection, battery health assessment, maintenance, and used car evaluation. Utilizing the Delphi method and Fuzzy Analytic Hierarchy Process (FAHP), we propose a construction method for a hierarchical and quantitative evaluation system. For each scenario, an independent quantitative evaluation table is established, identifying key indicators through a combination of specific operational contexts and expert opinions. The FAHP is then applied to determine the precise weights of these selected indicators, yielding a clear weighting structure for health metrics across different scenarios. This work culminates in a quantitative evaluation methodology for the health degree of in-use NEVs. By extending vehicle service life, reducing premature battery degradation, and enhancing safety, the proposed system directly supports the sustainable development of the NEV industry. It contributes to resource conservation, lower environmental impact, and greater consumer trust in green transportation. The proposed system is significant for fostering the healthy development of the NEV industry, enhancing vehicle safety and reliability, promoting technological progress, and strengthening consumer purchase confidence. Full article

Abandoned mine methane (AMM) emissions represent a significant public safety and environmental hazard in post-industrial urban areas. Uncontrolled subsurface gas migration may lead to explosive accumulations in confined spaces, human exposure, infrastructure damage, and additional greenhouse gas emissions. This study develops an integrated risk assessment framework for AMM in urban environments, combining quantitative analysis of field monitoring data with semi-quantitative probability–consequence risk matrices and multi-factor evaluation. Methane concentrations were measured at 41 monitoring points during three campaigns (August–September 2024). A total of 42 influencing factors were identified and classified into seven categories (geological, mining, hydrogeological, meteorological, anthropogenic, biological, and special phenomena). Exceedance probabilities of critical thresholds were estimated with 95% confidence intervals. Consequence weights were derived using the Analytic Hierarchy Process (AHP) based on a five-expert panel (CR = 0.043). The framework was applied to the urban area of Lupeni, Romania, where methane concentrations of up to 54% vol. were measured during borehole screening measurements (subsurface probe points). Elevated concentrations were detected four days after commissioning of a new gas pipeline. Gas chromatographic analysis excluded pipeline leakage and confirmed a mining-related source. Results indicate a localized critical risk (R = 25 on a 1–25 scale) in hotspot P2, with a 95% confidence interval for the probability of exceeding the 3% vol. alert threshold of [0.885–1.00], justifying immediate mitigation through controlled drainage. Post-intervention monitoring showed a reduction to instrumentally undetectable levels by February 2025. The study demonstrates that administrative mine closure does not eliminate residual methane risk and proposes a complete decision-support algorithm (URBAN-MINE-RISK) for similar urban settings. The applicability of structural reliability methods (e.g., FORM) is discussed as a future research direction. The methodology is transferable to other post-mining regions in Central and Eastern Europe. Full article

Background/Objectives: MRI is a non-invasive tool which can be used to assess baseline gonadal anatomy, including changes during puberty. Volumetric characterization offers valuable insights about the reproductive system and gonads, but annotation is cumbersome, and no AI tool is currently available. This study aimed to develop two open-source AI models to segment bilateral gonads at MRI scans in healthy subjects. Materials and Methods: This study uses a longitudinal dataset consisting of 182 MRIs from 22 healthy girls (median age 13) and 266 MRIs from 44 healthy boys (median age 13) from a single institute. MRI acquisition included T2-weighted (T2W) sequence, along with fat-saturated (FS) T2W when indicated. An expert radiologist segmented gonadal anatomy, including ovarian cysts (>3 cm). Three-dimensional nnUnet models were trained for ovary, cyst, and testicle segmentation, respectively. The ovary–cyst segmentation model was applied to an external dataset with 30 adult subjects. Model performance was evaluated on the test set using the Dice similarity coefficient for ovary (DSCOV), cyst (DSCCY), and testicles (DSCTS). Subject-level total volumes for ovaries (TOV), cysts (TCV), and testicles (TTV) were computed. Results: Ovary, cyst, and testicle segmentation models achieved DSCOV of 0.86, DSCCY of 0.69, and DSCTS of 0.90 in the in-house test set, respectively. Average mean difference with 95% confidence intervals for TOV, TCV, and TTV were 0.87 (−5.78, 7.5), −0.41 (−3.3, 2.5), and 0.19 (−1.5, 1.9) cm³, respectively. Conclusions: The developed models show promising and reliable performance in volumetric and morphologic evaluation of gonads during puberty. Full article

The Low-Strain Pile Integrity Test (LSPIT), standardized in ASTM D5882, is widely used as a rapid and economical non-destructive technique for assessing pile continuity in deep foundation systems. However, interpretation of LSPIT reflectograms remains strongly dependent on expert judgment and is influenced by soil–pile interaction effects such as damping and radiation losses, which can alter waveform morphology and confound automated defect screening. This study proposes a soil-aware deep learning framework that combines image-based reflectogram features with categorical geotechnical context describing the dominant soil regime at the measurement site. Reflectogram images are processed with a pretrained ConvNeXt-Large backbone, while soil information derived from Unified Soil Classification System (USCS) logs is represented as a categorical auxiliary input and mapped to a learnable embedding. The resulting multimodal design conditions waveform interpretation based on site context rather than relying on signal morphology alone. The framework is examined on an assembled benchmark of 510 expert-labeled reflectograms (404 intact and 106 defective), including a nine-site subset of 182 field records with explicit soil annotations. On the assembled benchmark, the model yields 99.41% accuracy and a weighted F1-score of 0.9941; on the nine-site subset, the observed accuracy is 99.45% with zero missed defective cases. Balanced accuracy, specificity, missed-detection rate, false-alarm rate, and confidence intervals are additionally reported to better align the evaluation with engineering screening practice. The study also states the current limits of the evidence base, including partial soil annotation, dominant-soil simplification, restricted soil coverage, and the absence of leave-site-out and interpretability-focused validation. Overall, the results support soil-aware multimodal learning as a promising proof-of-concept direction for more context-aware automated LSPIT interpretation, while also identifying the validation steps still required for broad field deployment. Full article

Public opinion on online platforms now plays an important role in agricultural markets, which have always been unpredictable. Although sentiment analysis has been widely applied to agricultural texts, most existing studies typically focus only on classification accuracy without connecting results to actual market intelligence systems, especially in multilingual contexts. This paper introduces a reliability-aware transformer-based framework for analyzing sentiment in agricultural market intelligence across multiple languages. The framework leverages weakly supervised multilingual transformers to extract sentiment signals from large-scale unlabeled Thai and English texts about major agricultural commodities found online. To enhance robustness under weak supervision, the framework incorporates reliability-aware mechanisms, including confidence-based pseudo-label filtering, cross-source consistency refinement, and expert-guided calibration to reduce noise and account for bias between different data sources. Sentiment predictions are further aligned with market intelligence objectives through reliability-weighted aggregation, yielding interpretable sentiment indices that enable cross-lingual and cross-source comparability. We tested the framework extensively using a multilingual agricultural corpus derived from social media and news coverage of agriculture. The results show consistent improvements over both classical machine learning approaches and standard multilingual transformer baselines. Additional ablation studies and sensitivity analyses confirmed that reliability-aware mechanisms, particularly confidence thresholding, play a crucial role in getting the right balance between label quality and data coverage. Overall, the results indicate that reliability-aware multilingual sentiment analytics provide robust and actionable insights for agricultural market monitoring and policy analysis. Full article

Risk management is critical to maintain consistency between estimated and actual costs in construction investment projects, especially those that incorporate tourism and heritage components. This study aims to quantify the impact of risk factors on construction investment costs and to estimate an updated maximum project budget at a defined confidence level using an integrated expert-based and probabilistic approach. The approach combines a Frequency–Impact matrix, weighted scaling, and PERT/Monte Carlo simulation, thereby transforming expert judgments into comparable numerical parameters suitable for predictive modeling. The methodology is applied to the rehabilitation of the Esmeralda Hotel project in Cuba, a heritage asset characterized by high cultural value and technical complexity. The results quantify the effects of prioritized risk factors, compute their impact coefficients, and re-estimate the project’s upper budget limit at a 95% confidence level. The findings show that risk drivers associated with higher-complexity construction processes concentrate the main vulnerabilities and explain most of the increase in total cost. In addition, the analysis indicates that contingency margins established by regulation are insufficient to absorb the project’s observed variability. The proposed model supports proactive budget control by anticipating cost deviations, improving resource allocation, and strengthening decision-making under high uncertainty. Its flexible structure enables adaptation to different project types and serves as a practical decision-support tool for investors, designers, and project managers seeking greater financial accuracy and reduced risk of cost overruns. Full article

Background/Objectives: Federated learning has emerged as a promising paradigm for enabling collaborative artificial intelligence in healthcare while preserving data privacy. However, most existing frameworks focus on isolated tasks and lack integrated pipelines that combine classification, segmentation, explainability, and automated clinical reporting. Methods: This study proposes FedIHRAS, a privacy-preserving federated learning framework designed for multi-institutional radiological analysis. The system integrates multi-task deep learning modules, including pathology classification using a modified ResNet-50 backbone, anatomical segmentation, explainability through Grad-CAM, and automated report generation supported by semantic aggregation using SNOMED CT. The framework employs confidence-weighted aggregation, differential privacy mechanisms, and secure aggregation protocols to ensure privacy and robustness across heterogeneous institutional datasets. Results: Experimental evaluation was conducted across four large-scale chest X-ray datasets representing simulated institutional nodes, totaling approximately 874,000 images. FedIHRAS achieved high diagnostic performance with strong cross-institutional generalization and demonstrated improved robustness under non-IID data distributions. Additional experiments showed favorable communication efficiency, effective privacy–utility trade-offs, and strong agreement with expert radiologist assessments. Conclusion: The proposed FedIHRAS framework demonstrates that federated learning can support scalable, privacy-preserving, and clinically meaningful radiological AI systems. By integrating multi-task learning, explainability, and automated reporting within a unified federated architecture, the framework addresses key limitations of existing approaches and contributes to the development of collaborative AI in healthcare. Full article

Background: We tested whether a contrast-free protocol can reproduce contrast-enhanced VI-RADS scoring and whether reader expertise influences results. Methods: In this retrospective single-center study (January–December 2024), 65 patients (69 lesions) underwent bladder multiparametric MRI. Two blinded radiologists assigned VI-RADS scores using only T2-weighted and diffusion-weighted imaging (biparametric, non-contrast MRI): an expert (>15 years in urogenital radiology) in genitourinary MRI and a non-expert (5 years of experience in genitorurinary radiology). Two complementary reference standards were used. For reproducibility analysis, the reference standard was the VI-RADS score from the original clinical report based on the full multiparametric examination including contrast-enhanced imaging. For diagnostic accuracy analysis, histopathology was used as the reference standard for muscle-invasive versus non-muscle-invasive disease. Agreement was evaluated with confusion matrices, overall agreement, and weighted Cohen’s kappa. Discrimination for high likelihood of muscle invasion (VI-RADS ≥ 4) was assessed with receiver operating characteristic analysis. Results: Reference scores were VI-RADS 2 (34.8%), 3 (14.5%), 4 (20.3%), and 5 (30.4%). Agreement was higher for the expert than the non-expert (73.9% vs. 56.5%; weighted kappa 0.74 [95% confidence interval 0.56–0.89] vs. 0.58 [0.37–0.75]). The area under the curve for VI-RADS ≥ 4 was 0.87 (0.78–0.95) for the expert and 0.81 (0.69–0.91) for the non-expert. Sensitivity at a biparametric threshold of VI-RADS ≥ 4 was 88.6% for both readers; specificity was 85.3% vs. 73.5%. Post-resection cases showed more discrepancies, mainly overstaging. Conclusions: Contrast-free biparametric MRI may approximate multiparametric VI-RADS scoring only in treatment-naïve pre-TURBT cases with clearly low-risk, non-equivocal imaging features, but performance is reader-dependent and less reliable in equivocal, higher-risk, and post-resection examinations. Contrast-enhanced multiparametric MRI remains preferred for staging. Full article

Soil moisture prediction is essential for precision irrigation in water-limited agricultural systems. This study presents a deep learning-driven irrigation framework for winter wheat, integrating a novel Informer–UNet model with a Comprehensive Irrigation Index for adaptive water management. The Informer–UNet combines ProbSparse self-attention mechanisms with UNet’s multi-scale feature fusion, enabling simultaneous prediction of soil moisture at 27 monitoring points across three depths, 10, 30, and 50 cm, while quantifying prediction uncertainty through Monte Carlo Dropout. A Comprehensive Irrigation Index incorporating moisture deviation, spatial variance, and confidence interval width was developed, with weights optimized via genetic algorithm. Field experiments were conducted in Chengdu, China, over two winter wheat growing seasons. The Informer–UNet achieved superior prediction accuracy, R² greater than 0.98, RMSE less than 0.65, compared to LSTM, Transformer, and standard Informer models, with the fastest convergence and lowest validation loss. The proposed DeepIndexIrr strategy maintained soil moisture within the target range, 55% to 75%, for over 81% of the irrigation period, reducing water consumption by 38.2% compared to fixed-threshold control and 19.2% compared to expert manual scheduling. These results demonstrate that integrating spatially distributed deep learning predictions with uncertainty-informed decision rules offers a promising approach for sustainable precision irrigation. Full article

The paper proposes a completely new geometric interpretation of intuitionistic fuzzy sets for confidence-aware decision making. Instead of directly using ordered pairs of membership and non-membership degrees, we reinterpret the intuitionistic fuzzy triangle as a structured coordinate framework that simultaneously represents the evaluation outcomes and the evaluators’ expertise in the following manner: experts’ confidence levels are modelled with line segments parallel to the hypotenuse, while evaluation scores are represented by line segments radiating from the origin of the coordinate system toward the hypotenuse. Their intersections form a finite lattice of points whose total number depends on the chosen confidence and assessment scales. The proposed construction preserves the semantic foundations of intuitionistic fuzziness: points closer to the origin reflect higher uncertainty in the evaluator’s confidence, while points onto the hypotenuse represent determinate judgments (with varying degrees of positivity or negativity) based on the complete evaluator’s confidence. The geometric distances between intersections provide a formal explanation of varying discriminative power: assessments from highly confident reviewers are more distinguishable than those from less confident ones. In addition, a colour-based visualization further supports the intuitive interpretation of confidence-weighted evaluations. The proposed framework offers an alternative yet fully consistent way to model expertise-dependent decision processes within the intuitionistic fuzzy setting, bridging geometric insight and practical evaluation scenarios via a structured system of parallels and meridians. Full article

Thailand’s goal of becoming carbon-neutral by 2050 and producing no emissions by 2065 requires their reliable renewable energy means to be expanded upon quickly. Biomass is an important resource for this. Even though there are many biomass power plants in Thailand, the further expansion of biomass energy is being held back by several problems, such as unclear rules and feedstock instability, which is worsening because of climate change. This study formulates an investor-focused Analytic Hierarchy Process (AHP) framework to rank the policy instruments that bolstered investor confidence in 2024–2025. Expert opinions were gathered through a Delphi-validated process and examined via eigenvector-based weighting and consistency checks. The findings indicate that law and regulatory policy is the most successful intervention (0.31), followed by economic incentives (0.24) and R&D support (0.18). Sub-criteria analysis reveals that regulatory clarity and the stability of feedstock supply—aggravated by climate-induced yield risks—are the predominant factors influencing investment decisions. Sensitivity analysis substantiates this ranking, indicating that fundamental regulatory reform is necessary to realize the full efficacy of financial or technological incentives. These results provide policymakers with a clear method to make decisions about how to align biomass roadmaps with the needs of the private sector. This will help emerging economies make a smooth and long-lasting transition to clean energy. Full article

Multi-level models are core artifacts of Model-Based Systems Engineering (MBSE) for cross-disciplinary collaboration and staged evolution, yet assessing their maturity in the conceptual design phase remains difficult. This paper proposes a systematic, model-centric maturity assessment method for instrumentation conceptual design. By tailoring ISO/IEC 25010 to instrumentation characteristics, we establish a seven-dimensional quality attribute framework (functional suitability, performance efficiency, interaction capability, reliability, maintainability, flexibility, and structural completeness) and an L0–L4 maturity scale for multi-level MBSE models. The indicators are structured using a Quality Attribute Utility Tree. CRITIC derives the objective weights by jointly considering the score dispersion and inter-indicator correlation, and Dempster–Shafer evidence theory is used to map the indicator values and expert ratings onto basic belief assignments and fuses the multi-source evidence to the output maturity levels with explicit confidence and uncertainty. A case study of an automatic dosing instrument for solid foam drainage agents at a high-pressure gas wellhead yields an overall maturity of $L_1$ (Structured), with $BetP\left(L_1\right)= 0$.424, and an overall unknown mass of 0.186. The results highlight reliability and performance efficiency as the main bottlenecks and support targeted model refinement and resource allocation in early-stage design. Full article

Background/Objectives: Diabetes is major metabolic disorder and rapidly increasing public health problem globally. The greatest way to reduce diabetic complications is adequate knowledge about the condition. Hence, the primary objectives of this study were to evaluate the psychometric properties of the Simplified Diabetes Knowledge Test—Arabic version (SDKT-A) among Iraqi insulin-dependent diabetic patients. Additionally, the secondary objectives were to assess the associated independent variables and the risk of atherosclerosis and cardiovascular risk event by using atherogenic indices and lipid ratios with the SDKT-A. Methods: A cross-sectional, descriptive study was conducted in primary healthcare clinics. The SDKT was translated into Arabic using forward–backward translation, reconciliation, and pilot testing. Thereafter, psychometric properties of the SDKT-A were evaluated depending on different criteria. Atherogenic indices of Castelli risk indices I and II (CRI-I and II), triglyceride/HDL ratio, non-HDL-C ratio, atherogenic coefficient (AC), and triglyceride–total cholesterol–body weight index (TCBI) were calculated using specific formulas. Results: The SDKT-A questionnaire showed acceptable readability and validity. Cronbach’s alpha test (95% confidence interval) was 0.662 (0.59–0.73). The Pearson correlation coefficient of reliability for test–retest was found to be 0.659. The item difficulty index for most items was between 0.237 and 0.877. The point biserial correlation values ranged from 0.028 to 0.535 with Ferguson’s sigma value equal to 0.962. The content validation results showed a significant content validity ratio (CVR) value for most of the questions, ranging from 0.8 to 1. The content validity index (CVI) value for SDKT-A was found to be 0.98, which showed good agreement between experts. In addition, the exploratory factor analysis with promax rotation identified four domains for the final 20 items of the SDKT-A that explained 41.83% of the scale total variance. The mean score of the SDKT-A was 11.09 ± 3.40. The total score of the SDKT-A was positively and significantly correlated with education level (r = 0.322, p < 0.01). In addition, the total scores of the SDKT-A were negatively and significantly correlated with glycemic control, age, CRI-I, CRI-II, triglyceride/HDL ratio, AC, non-HDL-C ratio, and TCBI. Furthermore, the glycemic control (HbA1c) was positively and significantly correlated with the preventive measures factor (r = 0.175, p < 0.05), and were negatively and significantly correlated with the lifestyle and modification factor (r = −0.169, p < 0.05), diet and monitoring factor (r = −0.158, p < 0.05), and awareness factor (r = −0.149, p < 0.05). Conclusions: This study showed acceptable psychometric properties for the SDKT-A, with low levels of knowledge of diabetic disease in the sample population. Finally, comprehensive and interactive educational programs regarding lifestyle and modification, diet, and monitoring and awareness in primary healthcare centers in Iraq are warranted. Full article