Search Results (361)

Background/Objectives: Dietary patterns play a crucial role in health, yet most research examines foods individually, overlooking how they interact. This approach provides an incomplete picture of how diet influences health outcomes. Network analysis (e.g., Gaussian graphical models, mutual information networks, mixed graphical models) offers a more comprehensive way to study food co-consumption by capturing complex relationships between dietary components. However, while researchers have applied various network algorithms to explore food co-consumption, inconsistencies in methodology, incorrect application of algorithms, and varying results have made interpretation challenging. The objectives of this scoping review were to systematically map and synthesise studies that have applied network analysis to dietary data, and to establish guiding principles for future research in this area. Methods: Using PRISMA-ScR criteria, our scoping review identified 171 articles published from inception up to 7 March 2025, of which 18 studies met the inclusion criteria. Results: Gaussian graphical models were the most frequent approach, used in 61% of studies, and were often paired with regularisation techniques (e.g., graphical LASSO) to improve clarity (93%). The analysis revealed significant methodological challenges across the literature: 72% of studies employed centrality metrics without acknowledging their limitations, there was an overreliance on cross-sectional data limiting the ability to determine cause and effect, and difficulties in handling non-normal data. While most studies using GGM addressed the issue of non-normal data, either by using the nonparametric extension, Semiparametric Gaussian copula graphical model (SGCGM), or log-transforming the data, 36% did nothing to manage their non-normal data. Conclusions: To improve the reliability of network analysis in dietary research, this review proposes five guiding principles: model justification, design–question alignment, transparent estimation, cautious metric interpretation, and robust handling of non-normal data. To facilitate their adoption, a CONSORT-style checklist is introduced—the Minimal Reporting Standard for Dietary Networks (MRS-DN)—to help guide future studies. This review was preregistered on Open Science Framework. Full article

Soil electrical conductivity is a key indicator of soil salinity and sustainability, particularly in arid and semi-arid regions. Accurate estimation of EC is essential for managing soil salinity and ensuring crop productivity. Five pedotransfer functions (PTFs) were developed and evaluated for predicting electrical conductivity in a saturated paste extract using soil parameters, such as particle size analysis, pH, organic carbon, total nitrogen, cation exchange capacity, and electrical conductivity in a 1:5 soil-to-water extract, in agricultural soils of northern Tunisia. The accuracy of each PTF was systematically evaluated. PTF1 represented an R² value of 0.85, PTF2 showed an R² of 0.71 for the stepwise regression model, PTF3 achieved an R² of 0.84, PTF4, based on Lasso/Ridge regression, reached an R² of 0.89, and PTF5 reached an R² of 0.83. Our findings revealed regional variations in soil salinity, with certain areas showing elevated salinity levels that could affect agricultural sustainability. This research emphasizes the importance of developing ad hoc PTFs as a reliable tool for predicting soil salinity and, consequently, assuring sustainable soil management in northeastern Tunisia. Full article

Background: Despite chemotherapy-related toxicities being more likely in older patients, no routine prediction tool has been validated for the UK population. Previous research within the TOASTIE (tolerance of anti-cancer systemic therapy in the elderly) study found a low predictive performance of the Cancer and Aging Research Group (CARG) score for severe chemotherapy-related toxicities. Building on this, the TOASTIE study dataset was used to assess the viability of developing a predictive model with baseline variables and frailty scores for severe chemotherapy-related toxicities in older patients. Methods: All patients from the TOASTIE dataset were included, with the inclusion/exclusion criteria detailed in the TOASTIE protocol. Demographic factors, self-assessment scores, Rockwood Clinical Frailty Score and researcher’s estimated risks of toxicity were assessed for their association with severe chemotherapy-related toxicities. After data partition into 70:15:15 train/validation/test, models were built on the training dataset using logistic regression (LR), LASSO and random forest (RF). Models were optimized with a validation set with LR and LASSO; cross-validation was used with RF. Model performance was assessed with balanced accuracy, NPV and AUC. Results: Of the 322 patients included, the incidence of severe toxicities was 22% (n = 71). Ten variables were statistically significant, albeit weakly associated with severe toxicities: primarily patient-reported factors, Performance Status and high baseline neutrophil count. LR models gave the best balanced accuracies of 0.6382 (AUC 0.6950, NPV 0.8696) and 0.6469 (AUC 0.6469, NPV 0.4286) with LASSO, and 0.6294 (AUC 0.6557, NPV 0.6557) with RF. Conclusions: Models lack sufficiently robust results for clinical utility. However, a high NPV in predicting no toxicity could help identify lower-risk patients who may not require dose reductions, potentially improving overall outcomes. Full article

Osteoarthritis (OA) in the trapeziometacarpal joint (TM) is a prevalent form of hand OA, yet research on biomarkers specific to hand OA remains limited. This study aims to identify systemic plasma biomarkers at baseline in TM OA patients that are associated with patient-reported outcomes one year post-treatment. Blood samples and clinical data were collected prospectively from 143 TM OA patients undergoing conservative therapy, fat grafting, or surgery, with one-year follow-up. Supervised machine learning with Lasso regularization analyzed associations among 10 systemic biomarkers related to cartilage turnover, bone remodeling, pain, or lipid metabolism. Generalized estimating equation models evaluated baseline biomarker associations with one-year outcomes. Patients averaged 61 years, were mostly female (69%), and were primarily treated conservatively (47%). The machine learning model identified associations between outcomes and biomarkers, including PIIANP, Visfatin, adiponectin, and leptin. Adjusted analyses revealed baseline PIIANP associated with VAS, QuickDASH, and TASD improvements, while Visfatin correlated with VAS worsening. We could identify two different plasma markers that could predict the clinical outcome of TM OA treatment. Baseline PIIANP is associated with improvement, while Visfatin is associated with worsening in TM OA outcomes up to one year post-treatment. Further prospective studies are needed to confirm and solidify these findings. Full article

Background: Proteomic profiling may improve the understanding of obesity and cardiovascular risk prediction. This study explores the use of protein-predicted scores for body mass index (PPS_BMI), body fat percentage (PPS_BFP), and waist–hip ratio (PPS_WHR) to estimate risk for major adverse cardiovascular events (MACEs). Methods: We used data from the UK Biobank with proteome profiling. PPS_BMI, PPS_BFP, and PPS_WHR were derived using the LASSO algorithm. The association between these protein scores and incident MACEs was evaluated using a competing risk model. Results: Strong to moderate correlations were observed between protein-predicted obesity phenotypes and their measured counterparts (R²: BMI = 0.78, BFP = 0.85, WHR = 0.63). Each standard deviation increment of PPS_BFP and PPS_WHR, but not PPS_BMI, was associated with greater risk of MACEs (hazard ratio [HR] 1.25, 95% CI 1.14–1.38, p < 0.0001; HR 1.15, 95% CI 1.06–1.24, p = 0.001, respectively). For predicting MACEs, compared with the PREVENT equation (C statistic 0.694), the models adjusted for only age, sex, current smoking, and protein scores showed comparable performance (C statistics 0.684–0.688). Conclusion: Protein-predicted scores of obesity showed strong independent associations and predictive performance for MACEs, suggesting they may capture additional biological risk beyond anthropometry. These scores may complement existing risk models by providing a biologically informed approach to assessing obesity-related cardiovascular risk and improving risk stratification. Full article

A portable spectral detector for water quality assessment was developed, utilizing potassium nitrate and ammonium chloride standard solutions as the subjects of investigation. By preparing solutions with differing concentrations, spectral data ranging from 254 to 1275 nm was collected and subsequently preprocessed using methods such as multiple scattering correction (MSC), Savitzky–Golay filtering (SG), and standardization (SS). Estimation models were constructed employing modeling algorithms including Support Vector Machine-Multilayer Perceptron (SVM-MLP), Support Vector Regression (SVR), random forest (RF), RF-Lasso, and partial least squares regression (PLSR). The research revealed that the primary variation bands for NH₄⁺ and NO₃⁻ are concentrated within the 254–550 nm and 950–1275 nm ranges, respectively. For predicting ammonium chloride, the optimal model was found to be the SVM-MLP model, which utilized spectral data reduced to 400 feature bands after SS processing, achieving R² and RMSE of 0.8876 and 0.0883, respectively. For predicting potassium nitrate, the optimal model was the 1D Convolutional Neural Network (1DCNN) model applied to the full band of spectral data after SS processing, with R² and RMSE of 0.7758 and 0.1469, respectively. This study offers both theoretical and technical support for the practical implementation of spectral technology in rapid water quality monitoring. Full article

Abdominal fat is a key indicator of chicken meat quality. Excessive deposition not only reduces meat quality but also decreases feed conversion efficiency, making the breeding of low-abdominal-fat strains economically important. Genomic selection (GS) uses information from genome-wide association studies (GWASs) and high-throughput sequencing data. It estimates genomic breeding values (GEBVs) from genotypes, which enables early and precise selection. Given that abdominal fat is a polygenic trait controlled by numerous small-effect loci, this study combined population genetic analyses with machine learning (ML)-based feature selection. Relevant single-nucleotide polymorphisms (SNPs) were first identified using a combined GWAS and linkage disequilibrium (LD) approach, followed by a two-stage feature selection process—Lasso for dimensionality reduction and recursive feature elimination (RFE) for refinement—to generate the model input set. We evaluated multiple machine learning models for predicting genomic estimated breeding values (GEBVs). The results showed that linear models and certain nonlinear models achieved higher accuracy and were well suited as base learners for ensemble methods. Building on these findings, we developed a Dynamic Adaptive Weighted Stacking Ensemble Learning Framework (DAWSELF), which applies dynamic weighting and voting to heterogeneous base learners and integrates them layer by layer, with Ridge serving as the meta-learner. In three independent validation populations, DAWSELF consistently outperformed individual models and conventional stacking frameworks in prediction accuracy. This work establishes an efficient GEBV prediction framework for complex traits such as chicken abdominal fat and provides a reusable SNP feature selection strategy, offering practical value for enhancing the precision of poultry breeding and improving product quality. Full article

Background/Objectives: Severe acute pancreatitis (SAP) carries substantial morbidity and resource burden, and early risk stratification remains challenging with conventional scores that require serial observations. The aim of this study was to develop and compare supervised machine-learning (ML) pipelines—integrating feature selection and SHAP-based explainability—for early prediction of SAP at emergency department (ED) presentation. Methods: This retrospective, single-center cohort was conducted in a tertiary-care ED between 1 January 2022 and 1 January 2025. Adult patients with acute pancreatitis were identified from electronic records; SAP was classified per the Revised Atlanta criteria (persistent organ failure ≥ 48 h). Six feature-selection methods (univariate AUROC filter, RFE, mRMR, LASSO, elastic net, Boruta) were paired with six classifiers (kNN, elastic-net logistic regression, MARS, random forest, SVM-RBF, XGBoost) to yield 36 pipelines. Discrimination, calibration, and error metrics were estimated with bootstrapping; SHAP was used for model interpretability. Results: Of 743 patients (non-SAP 676; SAP 67), SAP prevalence was 9.0%. Compared with non-SAP, SAP patients more often had hypertension (38.8% vs. 27.1%) and malignancy (19.4% vs. 7.2%); they presented with lower GCS, higher heart and respiratory rates, lower systolic blood pressure, and more frequent peripancreatic fluid (31.3% vs. 16.9%) and pleural effusion (43.3% vs. 17.5%). Albumin was lower by 4.18 g/L, with broader renal–electrolyte and inflammatory derangements. Across the best-performing models, AUROC spanned 0.750–0.826; the top pipeline (RFE–RF features + kNN) reached 0.826, while random-forest-based pipelines showed favorable calibration. SHAP confirmed clinically plausible contributions from routinely available variables. Conclusions: In this study, integrating feature selection with ML produced accurate and interpretable early prediction of SAP using data available at ED arrival. The approach highlights actionable predictors and may support earlier triage and resource allocation; external validation is warranted. Full article

Bone and bone marrow Metastasis (BBM) are life-threatening complications of advanced malignancies, frequently requiring intensive care and associated with high short-term mortality. However, prognostic tools specifically tailored to critically ill BBM patients are limited. This multicenter cohort study aimed to develop and validate deep learning models for predicting 30-day mortality using ICU data from MIMIC-IV, eICU-CRD, and the First Affiliated Hospital of Xinjiang Medical University. After univariate screening, XGBoost-Boruta and Lasso regression identified 11 key clinical features within 24 h of ICU admission. Thirteen deep learning models were trained using five-fold cross-validation, and their performance was evaluated through AUC, average precision, calibration, and decision curves. TabNet achieved the best internal performance (AUC 0.878; AP 0.940) and maintained strong discrimination in both same-region (eICU: AUC 0.840; AP 0.932) and cross-regional (Xinjiang: AUC 0.831; Accuracy 80.5%) validation. SHAP and attention-based interpretability analyses consistently identified SOFA, serum calcium, and albumin as dominant predictors. A TabNet-based online calculator was subsequently deployed to enable bedside mortality risk estimation. In conclusion, TabNet demonstrates potential as an accurate and interpretable tool for early mortality risk stratification in critically ill BBM patients, offering support for more timely and individualized decision-making in BBM-related critical care. Full article

It is essential to balance energy supply and demand in residential buildings through accurate forecasting of energy use due to varying daily and seasonal residential building loads. This study demonstrates a data-driven Virtual Energy Replication Framework (VERF) to predict the behavior of residential buildings using weather forecast data. The framework integrates supervised machine learning models and time-ahead weather parameters to estimate photovoltaic (PV) power production, heat pump energy consumption, and indoor thermal comfort. The accuracy of prediction models is validated using TRNSYS simulations of a typical household in Saarbrucken, Germany, a temperate oceanic climate region. The XGBoost model exhibits the highest reliability, achieving a root mean square error (RMSE) of 0.003 kW for PV power generation and 0.025 kW for heat pump energy use, with R² scores of 0.94 and 0.87, respectively. XGBoost and random forest regression models perform well in predicting PV generation and HP electricity load, with mean prediction errors of 5.27–6% and 0–7.7%, respectively. In addition, the thermal comfort index (PPD) is predicted with an RMSE of 1.84 kW and an R² score of 0.80 using the XGBoost model. The mean prediction error remains between 2.4% (XGBoost regression) and −11.5% (lasso regression) throughout the forecasted data. Because the framework requires no real-time instrumentation or detailed energy modelling, it is scalable and adaptable for smart building energy systems, and has particular value for Building-Integrated Photovoltaics (BIPV) demonstration projects on account of its predictive load-matching capabilities. The research findings justify the applicability of VERF for efficient and sustainable energy management using weather-informed prediction models in residential buildings. Full article

Antimicrobial resistance has emerged as one of the most critical public health challenges of the 21st century, threatening to undermine the foundations of modern medicine. In 2019, bacterial infections accounted for 13.6% of all global deaths, with more than 7.7 million fatalities directly attributable to 33 bacterial pathogens, most prominently Staphylococcus aureus, Streptococcus pneumoniae, Escherichia coli, Klebsiella pneumoniae, and Pseudomonas aeruginosa. Resistance mechanisms are multifactorial, encompassing enzymatic degradation, target modification, efflux pump overexpression, reduced membrane permeability, and biofilm formation, often in combination, leading to multidrug-resistant, extensively drug-resistant, and pandrug-resistant phenotypes. Alarmingly, projections estimate that by 2050 AMR could result in over 10 million deaths annually. This comprehensive review synthesizes global epidemiological data, insights into bacterial resistance mechanisms, and emerging therapeutic solutions, including novel antibiotics such as lasso peptides and macrocyclic peptides (e.g., zosurabalpin), naturally derived compounds (e.g., corallopyronin, clovibactin, chlorotonil A), and targeted inhibitors (e.g., Debio 1453 for Neisseria gonorrhoeae). Addressing the AMR crisis requires coordinated international efforts, accelerated drug discovery, and the integration of innovative non-antibiotic approaches to preserve the efficacy of existing therapies and ensure preparedness against future bacterial threats. Full article

Introduction: Recurrence after pelvic exenteration remains a significant concern in patients with locally advanced rectal cancer (LARC). Therefore, there is a need for improved non-invasive predictive tools to aid in patient selection. Radiomics, which extracts quantitative imaging features, may help identify patients at greater risk of recurrence. This study aimed to develop and validate a radiomics-based nomogram using pre-treatment MRI to predict postoperative recurrence risk in LARC. Methods: The largest multicenter retrospective radiomics analysis of 191 patients with pathologically confirmed LARC treated at fourteen centres (2016–2018) was performed. All patients received neoadjuvant chemoradiotherapy followed by curative-intent exenterative surgery. Manual tumour segmentation was performed on pre-treatment T2-weighted MRI. Feature selection employed LASSO regression with 5-fold cross-validation across 1000 bootstrap samples. The most frequently selected features were used to construct a logistic regression model via stepwise backward selection. Model performance was assessed using ROC analysis, calibration plots, decision curve analysis, and internal validation with 1000 bootstraps. A nomogram was generated to enable individualized recurrence risk estimation. Results: Postoperative recurrence occurred in 51% (n = 98) of cases. Five radiomic features reflecting tumour heterogeneity, morphology, and texture were included in the final model. In multivariable analysis, all selected features were significantly associated with recurrence, with odds ratios ranging from 0.63 to 1.64. The model achieved an optimism-adjusted AUC of 0.70, indicating fair discrimination. Calibration plots showed good agreement between predicted and observed recurrence probabilities. Decision curve analysis confirmed clinical utility across relevant thresholds. A clinically interpretable nomogram was developed based on the final model. Conclusions: A radiomics-based model using preoperative MRI can predict recurrence in LARC. The derived nomogram provides a practical tool for preoperative risk assessment. Prospective validation is necessary. Full article

For the autoregressive models, classical estimation methods, including the least squares estimator or the maximum likelihood estimator are not robust to heavy-tailed distributions or outliers in the dataset, and lack sparsity, leading to potentially inaccurate estimation and poor generalization capability. Meanwhile, the existing variable selection methods can not handle the case where the influence of explanatory variables on the dependent variable gradually weakens as the lag order increases. To address these issues, we propose a novel robust adaptive lasso method for the autoregressive models. The proposed method is constructed by using partial autocorrelation coefficients as adaptive penalty weights to promote sparsity in parameter estimation, and by employing a robust autocorrelation estimator based on the $F{Q}_n$ statistic to enhance resistance to outliers. Numerical simulations and two real data analyses illustrate the promising performance of our proposed approach. The results indicate that our proposed approach exhibits good robustness and sparsity in the presence of outliers in the dataset. Full article

This study applies machine learning methods to predict the Canadian yield curve using a comprehensive set of macroeconomic variables. Lagged values of the yield curve and a wide array of Canadian and international macroeconomic variables are utilized across various machine learning models. Hyperparameters are estimated to minimize mispricing across government bonds with different maturities. The Group Lasso algorithm outperforms the other models studied, followed by Lasso. In addition, the majority of the models outperform the Random Walk benchmark. The feature importance analysis reveals that oil prices, bond-related factors, labor market conditions, banks’ balance sheets, and manufacturing-related factors significantly drive yield curve predictions. This study is one of the few that uses such a broad array of macroeconomic variables to examine Canadian macro-level outcomes. It provides valuable insights for policymakers and market participants, with its feature importance analysis highlighting key drivers of the yield curve. Full article

The karst terrain of Guangxi, China, characterized by steep slopes and thin residual soils, is highly vulnerable to rainfall-induced shallow landslides. Timely and accurate displacement forecasting is critical for early warning and risk mitigation. However, most existing systems depend on centralized computation, leading to latency and reduced responsiveness. Moreover, conventional forecasting models are often too computationally intensive for edge devices with limited processing resources. To address these constraints, we present EoML-SlideNet, a lightweight forecasting framework designed for resource-limited hardware. It decomposes displacement and triggers into trend and periodic components, then applies the Dual-Band Lasso-Enhanced Latent Variable (DBLE–LV) module to select compact, interpretable features via cross-correlation, LASSO, and VIF screening. A small autoregressive model predicts the trend, while a lightweight neural network captures periodic fluctuations. Their outputs are combined to estimate displacement. All models were evaluated on a single CPU-only workstation to ensure fair comparison. This study introduces floating-point operations (FLOPs), alongside runtime, as practical evaluation metrics for landslide displacement prediction models. A site-specific multi-sensor dataset was developed to monitor rainfall-triggered landslide behavior in the karst terrain of Guangxi. The experimental results show that EoML-SlideNet achieves 2–4 times lower MAE/RMSE than the most accurate deep learning and the lightest baseline models, while offering 3–30 times faster inference. These results demonstrate that low-complexity models can match or surpass the accuracy of deep networks while achieving latency and FLOP levels suitable for edge deployment without dependence on remote servers. Full article