Search Results (25,191)

Background/Objectives: The increasing use of electronic devices is reshaping lifestyle by offering new avenues for health behavior change. These tools provide to monitor health, fitness, and nutrition, promoting healthier lifestyles to prevent non-communicable diseases (NCDs). This umbrella review (conducted according to PRISMA 2020 guidelines, registered on PROSPERO CRD42024511141) assesses the effectiveness of wearable devices and mobile applications in improving healthy lifestyle behaviors to mitigate the risk of NCDs. Methods: Systematic reviews and meta-analyses (n = 27) focusing on digital tools for health behavior change were analyzed, with emphasis on their integration into daily life and their impact on health outcomes, including body weight, metabolic and anthropometric parameters, and dietary quality. Results and Conclusions: Interventions leveraging gamification, social interaction, and goal-setting (6/27) have shown greater efficacy in improving body-nutrition profile. The integration of eHealth technologies holds transformative potential for preventive healthcare and positive biology. These tools can contribute to healthier lifestyles, extended life expectancy, and reduced healthcare costs, although current limitations exist, including data accuracy, privacy concerns, and sustaining user engagement over time. Full article

Background/Objectives: Endometriosis is a chronic inflammatory condition that often requires laparoscopic examination for definitive diagnosis. Automated analysis of laparoscopic images using Deep Learning (DL) may support clinicians by improving diagnostic consistency and efficiency. This study aimed to develop and evaluate explainable DL models for the binary classification of endometriosis using laparoscopic images from the publicly available GLENDA (Gynecologic Laparoscopic ENdometriosis DAtaset). Methods: Four representative architectures—ResNet50, EfficientNet-B2, EdgeNeXt_Small, and Vision Transformer (ViT-Small/16)—were systematically compared under class-imbalanced conditions using five-fold cross-validation. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP) were applied for visual explanation, and their quantitative alignment with expert-annotated lesion masks was assessed using Intersection over Union (IoU), Dice coefficient, and Recall. Results: Among the evaluated models, EdgeNeXt_Small achieved the best trade-off between classification performance and computational efficiency. Grad-CAM produced spatially coherent visualizations that corresponded well with clinically relevant lesion regions. Conclusions: The study shows that lightweight convolutional neural network (CNN)–Transformer architectures, combined with quantitative explainability assessment, can identify endometriosis in laparoscopic images with reasonable accuracy and interpretability. These findings indicate that explainable AI methods may help improve diagnostic consistency by offering transparent visual cues that align with clinically relevant regions. Further validation in broader clinical settings is warranted to confirm their practical utility. Full article

Introduction: Evaluating cardiovascular function is crucial in the care of critically ill patients. Recent advancements in continuous cardiac output (CO) monitoring have led to the emergence of several arterial pulse contour devices. To effectively compare the accuracy of these devices, a comprehensive assessment is necessary. However, no experimental studies were found that have evaluated these devices in a controlled setting. Methods: In this innovative bench study, we used a Donovan mock circulatory system in conjunction with a total artificial heart (TAH-t) to simultaneously generate several comparable arterial waveforms and compared CO estimates from three different pulse contour devices: FloTrac™ (Vigileo™, v1.8 4th generation, Edwards LifeSciences, Irvine, CA, USA), proAQT™ (PulsioFlex™, Pulsion Medical Systems, Munich, Germany), and LiDCO™ Plus (LiDCO™, LidCO Ltd., Cambridge, UK). These devices underwent several hemodynamic challenges (HCs), including decreased preload, decreased afterload, and increased heart rate. To evaluate the degree of agreement between the devices, we performed a Bland–Altman analysis for the paired devices. The interclass comparison, error percentage, and variation coefficient for each device were also assessed. Results: The present study first tested the comparability between the three additional arterial line waveforms, and the arterial control line was simultaneously generated with the hemodynamic simulation bench. Comparing the reference values of the dP/dt and sAUC pulse pressure, we found no clinically significant difference between the simultaneously generated arterial waveforms. The different pulse contour devices were then each connected to the arterial lines, with the performance of HCs. HC1 with a decreased preload revealed that CO estimates significantly decreased compared to the baseline values: 3.2 ± 0.06 L.min⁻¹, 4.7 ± 0.05, 4.3 ± 0.07, and 4.0 ± 0.05 for reference methods FloTrac™, PulsioFlex™, and LiDCO™, respectively. HC2 with an increased heart rate revealed CO estimates with FloTrac™, PulsioFlex™, and LiDCO™—6.0 ± 0.03, 6.6 ± 0.06, and 6.0 ± 0.05 L.min⁻¹, respectively—when the CO estimate was 5.6 ± 0.2. HC3 with a decreased afterload that significantly increased CO estimates compared to the baseline with FloTrac™, PulsioFlex™, and LiDCO™—7.0 ± 0.18, 6.6 ± 0.15, and 7.1 ± 0.30 L.min⁻¹, respectively—when the CO estimate with the reference method did not change significantly (from 5.90 ± 0.13 to 5.94 ± 0.11 p = 0.26). The devices’ degree of agreement was estimated with Bland–Altman analysis. Conclusions: The Donovan Mock Circulatory System with SynCardia TAH-t can be used as an innovative experimental hemodynamic simulation bench. It was proven to be stable, accurate, and reliable in generating several controlled pulse pressure waveforms, while many parameters could be changed, such as the preload, heart rate, or afterload. This enables a simultaneous evaluation of different pulse contour devices submitted to several HCs. This is of interest for clinicians to better understand the underlying principles and realistically compare the performance and potentially inherent limitations of pulse contour devices experimentally in a controlled simulated environment. Full article

Background: Stress is a critical determinant of mental health, yet conventional monitoring approaches often rely on subjective self-reports or physiological signals that lack real-time responsiveness. Recent advances in large language models (LLMs) offer opportunities for speech-driven, adaptive stress detection, but existing systems are limited to retrospective text analysis, monolingual settings, or detection-only outputs. Methods: We developed a real-time, speech-driven stress detection framework that integrates audio recording, speech-to-text conversion, and linguistic analysis using transformer-based LLMs. The system provides multimodal outputs, delivering recommendations in both text and synthesized speech. Nine LLM variants were evaluated on five benchmark datasets under zero-shot and few-shot learning conditions. Performance was assessed using accuracy, precision, recall, F1-score, and misclassification trends (false-negatives and false-positives). Real-time feasibility was analyzed through latency modeling, and user-centered validation was conducted across cross-domains. Results: Few-shot fine-tuning improved model performance across all datasets, with Large Language Model Meta AI (LLaMA) and Robustly Optimized BERT Pretraining Approach (RoBERTa) achieving the highest F1-scores and reduced false-negatives, particularly for suicide risk detection. Latency analysis revealed a trade-off between responsiveness and accuracy, with delays ranging from ~2 s for smaller models to ~7.6 s for LLaMA-7B on 30 s audio inputs. Multilingual input support and multimodal output enhanced inclusivity. User feedback confirmed strong usability, accessibility, and adoption potential in real-world settings. Conclusions: This study demonstrates that real-time, LLM-powered stress detection is both technically robust and practically feasible. By combining speech-based input, multimodal feedback, and user-centered validation, the framework advances beyond traditional detection only models toward scalable, inclusive, and deployment-ready digital mental health solutions. Full article

Objectives: We aimed to develop and validate a per-cycle prediction model for in vitro fertilization (IVF) success using only preprocedural clinical variables available at the first consultation. Methods: We retrospectively analysed 1243 IVF/ICSI cycles (University of Szeged, 21 January 2022–12 December 2023). An Extreme Gradient Boosting (XGBoost version 1.7.7.1) classifier was trained on 14 baseline predictors (e.g., female age, AMH, BMI, FSH, LH, sperm concentration/motility, and infertility duration). A parsimonious 9-variable model was derived by feature importance. Model performance was assessed on the untouched test set and, as a final step, on an independent same-centre external validation cohort (n = 92) without re-fitting or recalibration. Results: The 9-variable model achieved an AUC of 0.876 on the internal test set, with an accuracy of 81.70% (95% CI 76.30–86.30%), sensitivity of 75.60%, specificity of 84.40%, PPV of 68.60%, and NPV of 88.50%. In external validation, the model maintained strong performance with an accuracy of 78.30%, confirming consistent discrimination on an independent same-centre cohort. Female age was the dominant high-impact feature, while AMH and BMI acted as “workhorse” predictors, and male factors added incremental value. Conclusions: IVF outcome can be predicted at the first visit using routinely collected preprocedural data. The model showed consistent discrimination internally and in external validation, supporting its potential utility for early, individualized counselling and treatment planning. Full article

This study develops an interpretable and calibrated XGBoost framework for probabilistic slope stability assessment using a 627-case database of circular-mode failures. Six predictors, namely, unit weight (γ), cohesion (c), friction angle (φ), slope angle (β), slope height (H), and pore-pressure ratio (rᵤ), were used to train a gradient-boosted tree model optimized through Bayesian hyperparameter search with five-fold stratified cross-validation. Physically based monotone constraints ensured that failure probability (P_f) decreases as c and φ increase and increases with β, H, and rᵤ. The final model achieved strong performance (AUC = 0.88, Accuracy = 0.80, MCC = 0.61) and reliable calibration, confirmed by a Brier score of 0.14 and ECE/MCE of 0.10/0.19. A 1000-iteration bootstrap quantified both epistemic and aleatoric uncertainties, providing 95% confidence bands for P_f-feature curves. SHAP analysis validated physically consistent influence rankings (φ > H ≈ c > β > γ > rᵤ). Predicted probabilities were classified into Low (P_f < 0.01), Medium (0.01 ≤ P_f ≤ 0.10), and High (P_f > 0.10) risk levels according to geotechnical reliability practices. The proposed framework integrates calibration, uncertainty quantification, and interpretability into a comprehensive, auditable workflow, supporting transparent and risk-informed slope management for infrastructure, mining, and renewable energy projects. Full article

Accurate estimation of peak water demand remains a challenge in institutional settings with floating populations, particularly in regions where design standards may require revision and validation to accommodate evolving consumption patterns. This pilot study assesses the potential of a probabilistic adaptation of Hunter’s method, calibrated through high-resolution flow and pressure monitoring, for peak flow estimation in five academic buildings in Loja, Ecuador. Over 62 days, usage parameters, duration (t), frequency (i), and peak period (h), were disaggregated from 1 min interval data to derive building-specific binomial probability distributions. The adapted model was compared against three benchmarks: the Neyman–Scott Rectangular Pulse Model (NSRPM), the Water Demand Calculator (WDC), and Ecuador’s Hydro-Sanitary Standard (NHE 2011). Results indicate the proposed approach estimates peak flows within −11.6% to +20.0% of observed values, outperforming WDC (systematic underestimation up to −81.5%) and NHE 2011 (average underestimation of −31.3%), though NSRPM achieved high accuracy for one site (−1.1%) with high inter-building variability (average −38.4%). While limited to a small sample in a single climatic context, this pilot demonstrates that temporal disaggregation of stochastic demand enables a context-sensitive recalibration of Hunter’s method, offering a methodologically sound basis for future validation across diverse institutional settings in the Global South. Full article

The high cost of wind turbine maintenance has intensified the need for reliable fault detection and condition monitoring methods. While Supervisory Control and Data Acquisition (SCADA) systems provide valuable operational data, the raw signals often contain noise, outliers, and missing or redundant entries, which can compromise analysis accuracy. This study presents a novel cluster-based outlier removal approach for SCADA data preprocessing, featuring a unique flexibility to include or exclude negative power values—a factor rarely investigated but potentially critical for fault detection performance. The method applies the K-Means++ unsupervised clustering algorithm to group data points along the wind speed–power curve. The number of clusters is determined heuristically using the elbow method, while outliers are identified through Mahalanobis distance with thresholds derived from Chebyshev’s inequality theorem. The approach was validated using SCADA data from a wind farm in Portugal and further assessed with a CUSUM test-based structural change detection method to study how preprocessing choices—outlier thresholds (5% vs. 1%) and inclusion/exclusion of negative power values—affect early fault identification. Results demonstrate reliable fault detection up to 14 days before failure, retaining over 99% of the original dataset. This work provides key insights into preprocessing impacts on model reliability and offers an open-source Python implementation for reproducibility. Full article

Background/objectives: Strangulated small bowel obstruction (SSBO) is a life-threatening condition that often requires emergency surgery. Identifying preoperative computed tomography (CT) findings indicative of bowel resection may improve diagnostic accuracy and inform surgical decision-making. Methods: We retrospectively analyzed patients diagnosed with SSBO who underwent contrast-enhanced abdominal CT and emergency surgery between January 2022 and April 2024. Patients were divided into two groups according to the surgical outcomes: those who underwent bowel resection and those who did not. CT images were independently reviewed by a radiologist blinded to surgical outcomes, and CT findings were compared between the resection and non-resection groups. Variables significant in the between-group comparisons (p < 0.05) were entered into a multivariable logistic regression to identify indicators for bowel resection. Results: Fifty-two patients were identified, sixteen (30.8%) of whom required bowel resection. The most reliable indicator was absent bowel wall enhancement on contrast-enhanced CT, with a sensitivity of 75.0% and specificity of 86.1%. It was also independently associated with bowel resection [odds ratio (OR) 19.7; 95% confidence interval: 3.43–113.4]. In contrast, ascites, beak sign, and mesenteric edema were commonly observed in both groups and lacked specificity. Of note, bowel resection was avoided in 5 of 17 patients with absent bowel wall enhancement based on intraoperative assessment using indocyanine green (ICG) fluorescence imaging. Conclusions: Absent bowel wall enhancement on contrast-enhanced CT is an independent preoperative indicator for bowel resection in SSBO. Full article

Background: Myxofibrosarcomas are notoriously highly infiltrative soft-tissue sarcomas, making negative surgical margins difficult to obtain. Recently, vacuum-assisted closure (VAC) is used to delay wound closure until a negative margin has been achieved; however, this can delay care and increase costs. Our institution has historically performed single-stage resections with intraoperative frozen margin analysis and reconstruction in these patients. The purpose of this study is to report the outcomes of this technique. Methods: We reviewed 112 patients (62 males, mean age 70 ± 14 years) with superficial myxofibrosarcoma. Eighty-eight patients received preoperative radiation. All patients underwent surgical resection with intraoperative frozen margin analysis, and the planned reconstruction was performed in a single anesthetic. Results: The 10-year local recurrence-free survival was 90%; positive intraoperative frozen section (HR 7.44, p = 0.004) and final permanent margins (HR 8.53, p = 0.007) were associated with local recurrence. Intraoperative margins were negative in 103 (92%) of patients, 1 of which was positive on final permanent section. There were nine cases of microscopically positive margins, of which seven underwent immediate re-excision to a negative margin. The accuracy of frozen margin assessment for myxofibrosarcoma was between 92.92 and 98.23%. All patients underwent reconstruction at the time of resection, with 19% needing an additional procedure, most commonly due to a wound complication (12%). Conclusions: Multidisciplinary single-stage excision with intraoperative frozen margin assessment and soft-tissue reconstruction yields low rates of local recurrence in patients with superficial myxofibrosarcoma. Full article

Rice cultivation accounts for roughly 10% of worldwide anthropogenic greenhouse gas emissions, making it a significant source of methane (CH₄) Despite modest observational constraints, estimates of worldwide CH₄ emissions from rice agriculture range from 18–115 Tg CH₄ yr⁻¹. CH₄ is a potent greenhouse gas, and its oxidation produces tropospheric ozone (O₃), which is harmful to public health and crop production when combined with nitrogen oxides (NOx) and sunlight. Elevated O₃ levels reduce air quality, crop productivity, and human respiratory health. This study presents an AI-driven framework that combines ensemble learning, hyperparameter optimisation (HPs), and SHAP-based explainability to enhance CH₄ emission predictions from rice paddies in India, Bangladesh, and Vietnam. The model consists of two stages: (1) a classification stage to distinguish between zero and non-zero CH₄ emissions, and (2) a regression stage to estimate emission magnitudes for non-zero situations. The framework also incorporates O₃ and asthma incidence data to assess the downstream impacts of CH₄-driven ozone formation on air quality and health outcomes. Understanding the factors that drive optimal model performance and the relative importance of features affecting model outputs is still an ongoing field of research. To address these issues, we present an integrated approach that utilises recent improvements in model optimisation and employs SHapley Additive ExPlanations (SHAP) to find the most relevant variables affecting methane (CH₄) emission forecasts. In addition, we developed a web-based artificial intelligence platform to help policymakers and stakeholders with climate strategy and sustainable agriculture by visualising methane fluxes from 2018 to 2020, ensuring practical applicability. Our findings show that ensemble learning considerably improves the accuracy of CH₄ emission prediction, minimises uncertainty, and shows the wider benefits of methane reduction for climate stability, air quality, and public health. Full article

Background/Objectives: To investigate the role of hepatobiliary phase (HBP) signal intensity (SI) on Gadoxetic acid (GA)-enhanced liver magnetic resonance imaging (MRI) in improving the diagnostic accuracy of the histological grade of fibrosis in patients with chronic hepatitis B (CHB). Methods: This retrospective study enrolled patients with CHB who underwent biopsies from the highest and lowest intensity areas identified on HBP images obtained from GA-enhanced MRI. The patients were divided into two groups based on segmental SIs: Group 1 (maximum SI) and Group 2 (minimum SI). An ultrasound-guided tru-cut biopsy was performed in these two segments. Forty patients undergoing histopathological examination were included in the study. Group comparisons were examined using Chi-square and independent-sample t-tests, and receiver operating characteristic curve analysis (ROC) was performed to determine the cutoff values of the SI for modified histologic activity index (mHAI) and fibrosis grading. Results: There were no histopathological differences between the groups (p > 0.05), but significant inflammation and fibrosis were observed in hepatic segments with an SI value of <617 (p < 0.001). The ROC results showed that the predictive cutoff value of SI for mHAI and fibrosis grading were 606 (AUC: 0.83, 95% CI 0.737–0.921, p < 0.001) and 599 (AUC: 0.85, 95% CI 0.766–0.935, p < 0.001), respectively. Conclusions: In patients with CHB, performing a biopsy from the liver segment with the lowest SI on GA-enhanced MRI increases the diagnostic accuracy for assessing the histological severity of hepatic inflammation and fibrosis. Full article

Cover crop mixes play an important role in enhancing soil health, nutrient turnover, and ecosystem resilience; yet, maintaining even seed dispersion and planting uniformity is difficult due to significant variances in seed physical and aerodynamic properties. These discrepancies produce non-uniform seeding and species separation in drill hoppers, which has an impact on stand establishment and biomass stability. The thousand-grain weight is an important measure for determining cover crop seed quality and yield since it represents the weight of 1000 seeds in grams. Accurate seed counting is thus a key factor in calculating thousand-grain weight. Accurate mixed-seed identification is also helpful in breeding, phenotypic assessment, and the detection of moldy or damaged grains. However, in real-world conditions, the overlap and thickness of adhesion of mixed seeds make precise counting difficult, necessitating current research into powerful seed detection. This study addresses these issues by integrating deep learning-based computer vision algorithms for multi-seed detection and counting in cover crop mixes. The Canon LP-E6N R6 5D Mark IV camera was used to capture high-resolution photos of flax, hairy vetch, red clover, radish, and rye seeds. The dataset was annotated, augmented, and preprocessed on RoboFlow, split into train, validation, and test splits. Two top models, YOLOv5 and YOLOv7, were tested for multi-seed detection accuracy. The results showed that YOLOv7 outperformed YOLOv5 with 98.5% accuracy, 98.7% recall, and a mean Average Precision (mAP 0–95) of 76.0%. The results show that deep learning-based models can accurately recognize and count mixed seeds using automated methods, which has practical applications in seed drill calibration, thousand-grain weight estimation, and fair cover crop establishment. Full article

Traditional cotton field plastic film residue monitoring relies on manual sampling, with low efficiency and limited accuracy; therefore, large-scale nondestructive monitoring is difficult to achieve. A UAV-based prediction method for shallow plastic film residue pollution in cotton fields that uses RDT-Net and machine learning is proposed in this study. This study focuses on the weight of residual plastic film in shallow layers of cotton fields and UAV-captured surface film images, establishing a technical pathway for drone image segmentation and weight prediction. First, the images of residual plastic film in cotton fields captured by the UAV are processed via the RDT-Net semantic segmentation model. A comparative analysis of multiple classic semantic segmentation models reveals that RDT-Net achieves optimal performance. The local feature extraction process in ResNet50 is combined with the global context modeling advantages of the Transformer and the Dice-CE Loss function for precise residue segmentation. The mPa, F1 score, and mIoU of RDT-Net reached 95.88%, 88.33%, and 86.48%, respectively. Second, a correlation analysis was conducted between the coverage rate of superficial residual membranes and the weight of superficial residual membranes across 300 sample sets. The results revealed a significant positive correlation, with R² = 0.79635 and PCC = 0.89239. Last, multiple machine learning prediction models were constructed on the basis of plastic film coverage. The ridge regression model achieved optimal performance, with a prediction R² of 0.853 and an RMSE of 0.1009, increasing accuracy in both the segmentation stage and prediction stage. Compared with traditional manual sampling, this method substantially reduces the monitoring time per cotton field, significantly decreases monitoring costs, and prevents soil structure disruption. These findings address shortcomings in existing monitoring methods for assessing surface plastic film content, providing an effective technical solution for large-scale, high-precision, nondestructive monitoring of plastic film pollution on farmland surfaces and in the plow layer. It also offers data support for the precise management of plastic film pollution in cotton fields. Full article

Bankruptcy prediction in Slovakia’s industrial manufacturing sector is vital due to its significant role in the national economy. This study aims to develop a predictive model for forecasting corporate bankruptcy within the industrial manufacturing sector in Slovakia. The novelty of this study lies in developing a model tailored to crisis conditions, validated using COVID-19 data, and adapted to the Central European context for greater accuracy and relevance. The model is constructed using financial data extracted from the Orbis database, based on company financial statements from 2020 and 2021, and encompasses firms of various sizes. Employing backwards binary logistic regression, five statistically significant predictors were identified, enabling the model to forecast impending bankruptcy with a one-year lead time. The model was trained on a sample of 1305 companies and achieves an overall prediction accuracy of 83.78%, with an AUC (Area Under the Curve) value of 91.7%, indicating strong discriminative power. The resulting model demonstrates robust predictive capability and may serve as a practical decision-support tool for managers, investors, creditors, and other stakeholders assessing the financial health of firms. Full article