The addition of powders from waste construction materials as partial cement substitute in concrete represents a significant step toward green concrete construction. High temperatures have a substantial influence on concrete strength, resulting in a reduction in mechanical properties. The prediction of the impacts of waste powders on concrete strength is an important topic in sustainable construction. Such models are needed to understand the complex interactions between waste materials’ powders and concrete strength. In this study, three machine learning approaches, extreme gradient boosting (XGBoost), random forest (RF), and M5P, were used for constructing the prediction model for the impact of elevated temperatures on the compressive strength of concrete modified by marble and granite construction waste powders as partial cement replacements in concrete. Dataset of 324 tested cubic specimens with four input variables, waste granite powder dose (GWP), waste marble powder (MWP), temperature (T), and duration (D) were chosen for developing the prediction models. The output was the concrete compressive strength (CS). MWP and GWP ranged between 0 and 9%, temperatures were ranged between 25 °C and 800 °C, and duration up to 2 h. Hyperparameters in the RF and XGB models were optimized using grid search. K-fold cross-validation and several statistical measures, including R2MAPE, RMSE, and MAE, were utilized to validate and check the accuracy of the proposed models. The developed models were evaluated against experimental data and previously established models. The XGB model demonstrated the highest R2 of 0.9989, alongside the lowest prediction errors: MAE of 0.1351 MPa, RMSE of 0.1842 MPa, and MAPE of 0.48%. The results showed that the XGB prediction model for the concrete compressive strength outperformed the other proposed models. The SHAP analysis, Individual Conditional Expectation (ICE), and Partial Dependence Plots (PDP) revealed that GWP and MWP positively influence the compressive strength, while the temperature exerts the most negative influence on predicting the compressive strength. Finally, a graphical user interface (GUI) for the compressive strength of concrete containing GWP and MWP subjected to elevated temperatures has been created, which may be of considerable assistance, guidance, and efficiency in research and construction industry contexts.

ABSTRACT This study employs machine learning approaches to predict the final exam scores of vocational undergraduate students and analyse critical factors influencing their academic performance. Using a multidimensional feature dataset, Ridge Regression was set as a baseline model, while four mainstream machine learning models – Random Forest, XGBoost, Support Vector Machine and Neural Network – were utilised for predictive modelling, with Random Forest achieving the best performance. SHapley Additive exPlanations (SHAP) was applied to interpret global and local feature contributions, indicating monthly exam scores, admission scores and self-study time as the most influential predictors, whereas demographic features were comparatively less significant. Furthermore, Partial Dependence Plots (PDP) and Kernel Density Estimation (KDE) analyses were conducted to explore feature interactions and differences between high- and low-achieving students, offering practical insights for vocational institutions to implement precise interventions focusing on key predictive factors.

Objective: Tumor progression is regulated by systemic immune status, nutritional metabolism, and the inflammatory microenvironment. This study aims to investigate inflammatory-nutritional biomarkers associated with metachronous liver metastasis (MLM) in colorectal cancer (CRC) and develop a machine learning model for accurate prediction. Methods: This study enrolled 680 patients with CRC who underwent curative resection, randomly allocated into a training set (n = 477) and a validation set (n = 203) in a 7:3 ratio. Feature selection was performed using Boruta and Lasso algorithms, identifying nine core prognostic factors through variable intersection. Seven machine learning (ML) models were constructed using the training set, with the optimal predictive model selected based on comprehensive evaluation metrics. An interactive visualization tool was developed to interpret the dynamic impact of key features on individual predictions. The partial dependence plots (PDPs) revealed a potential dose-response relationship between inflammatory-nutritional markers and MLM risk. Results: Among 680 patients with CRC, the cumulative incidence of MLM at 6 months postoperatively was 39.1%. Multimodal feature selection identified nine key predictors, including the N stage, vascular invasion, carcinoembryonic antigen (CEA), systemic immune-inflammation index (SII), albumin-bilirubin index (ALBI), differentiation grade, prognostic nutritional index (PNI), fatty liver, and T stage. The gradient boosting machine (GBM) demonstrated the best overall performance (AUROC: 0.916, sensitivity: 0.772, specificity: 0.871). The generalized additive model (GAM)-fitted SHAP analysis established, for the first time, risk thresholds for four continuous variables (CEA > 8.14 μg/L, PNI < 44.46, SII > 856.36, ALBI > -2.67), confirming their significant association with MLM development. Conclusions: This study developed a GBM model incorporating inflammatory-nutritional biomarkers and clinical features to accurately predict MLM in colorectal cancer. Integrated with dynamic visualization tools, the model enables real-time risk stratification via a freely accessible web calculator, guiding individualized surveillance planning and optimizing clinical decision-making for precision postoperative care.

BackgroundChronic obstructive pulmonary disease (COPD) is a leading cause of morbidity and mortality worldwide, with limited early detection strategies. While previous studies have examined the relationship between per- and polyfluoroalkyl substances (PFAS) and COPD, limited research has applied interpretable machine learning (ML) techniques to this association.MethodsWe investigated the association between PFAS exposure and COPD risk in 4,450 National Health and Nutrition Examination Survey (NHANES) participants from 2013 to 2018. After excluding missing covariates and extreme PFAS values and applying K-nearest neighbors (KNN) imputation, nine ML models, including CatBoost, were built and evaluated using metrics like accuracy, area under the curve (AUC), sensitivity, and specificity. The best-performing model was further analyzed using partial dependence plots (PDP) and SHapley additive exPlanations (SHAP) analysis. To enhance clinical applicability, the final model was deployed as a publicly accessible web-based risk calculator.ResultsCatBoost emerged as the best model, achieving an accuracy of 84%, AUC of 0.89, sensitivity of 81%, and specificity of 84%. PDP revealed that higher perfluorooctane sulfonic acid (PFOS) and perfluoroundecanoic acid (PFUA) levels were associated with reduced COPD risk, whereas perfluorooctanoic acid (PFOA) and 2-(N-Methyl-perfluorooctane sulfonamido) acetic acid (MPAH) showed positive associations with COPD. perfluorononanoic acid (PFNA), perfluorodecanoic acid (PFDE), and perfluorohexane sulfonic acid (PFHxS) demonstrated mixed or non-linear effects. SHAP analysis provided insights into individual predictions and overall variable contributions, clarifying the complex PFAS-COPD relationship. The deployed web-based calculator enables interactive prediction and risk interpretation, supporting potential public health applications.ConclusionCatBoost identified PFOS and PFUA as protective factors against COPD, while PFOA and MPAH increased risk of COPD. These findings emphasize the need for stricter PFAS regulation and highlight the potential of machine learning in guiding prevention strategies.

Rapid urbanization worldwide has led to ecological challenges, undermining eco-environmental resilience (EER). Understanding the coupling coordination between new-type urbanization (NTU) and EER is critical for achieving sustainable urban development. This study investigates the Chengdu–Chongqing Economic Circle using the coupling coordination degree (CCD) model to evaluate NTU-EER coordination levels and their spatiotemporal evolution. A random forest (RF) model, interpreted with Shapley Additive exPlanations (SHAP) and Partial Dependence Plot (PDP) algorithms, explores nonlinear driving mechanisms, while Geographically and Temporally Weighted Regression (GTWR) assesses drivers’ spatiotemporal heterogeneity. The results reveal the following: (1) NTU and EER levels steadily improved from 2004 to 2022, although coordination between cities still requires enhancement; (2) CCD exhibited a temporal pattern of “progressive escalation and continuous optimization,” and a spatial pattern of “dual-core leadership and regional diffusion,” with most cities shifting from NTU-lagged to synchronized development; (3) environmental regulations (MAR) and fixed asset investment (FIX) emerged as the most influential CCD drivers, and significant nonlinear interactions were observed, particularly those involving population size (HUM); (4) CCD drivers exhibited complex spatiotemporal heterogeneity, characterized by “stage dominance—marginal variation—spatial mismatch.” These findings enrich existing research and offer policy insights to enhance coordinated development in the Chengdu–Chongqing Economic Circle.

The drilling and blasting method is commonly employed for the rapid demolition of outdated buildings by destroying key structural components and inducing progressive collapse. The residual bearing capacity of these components is governed by the deformation morphology of the longitudinal reinforcement, characterized by bending deflection and exposed height. This study develops and validates a finite element (FE) model of a reinforced concrete (RC) column subjected to demolition blasting. By varying concrete compressive strength, the yield strength of longitudinal reinforcement, the longitudinal reinforcement ratio, and the shear reinforcement ratio, 45 FE models are established to simulate the post-blast morphology of longitudinal reinforcement. Two databases are created: one containing 45 original simulation cases, and an augmented version with 225 cases generated through data augmentation. To predict bending deflection and the exposed height of longitudinal reinforcement, artificial neural network (ANN) and random forest (RF) models are optimized using the hunter–prey optimization (HPO) algorithm. Results show that the HPO-optimized RF model trained on the augmented database achieves the best performance, with MSE, MAE, and R2 values of 0.004, 0.041, and 0.931 on the training set, and 0.007, 0.057, and 0.865 on the testing set, respectively. Sensitivity analysis reveals that the yield strength of longitudinal reinforcement has the most significant impact, while the shear reinforcement ratio has the least influence on both output variables. The partial dependence plot (PDP) analysis indicates that the ratio of shear reinforcement has the most significant impact on the deformation of longitudinal reinforcement.

ABSTRACT This study presents machine learning (ML) models for predicting average seismic site amplification, a key factor in seismic hazard assessment. Utilizing data from Japan’s KiK-Net strong-motion network, several algorithms were developed, including Gaussian Process Regression (GPR), Least Median Square Regression (LMSR), Sequential Minimal Optimization Regression (SMOR), K-star (K*), M5 Rules, Alternative Modeling Trees (AMT), and Regression Tree Ensemble (RTE). Input features included shear wave velocity profiles, peak ground acceleration at the rock, and ground motion duration. Models were optimized using Bayesian tuning and k-fold cross-validation. Among all models, the RTE model exhibited superior performance, achieving the lowest Root Relative Square Error (RRSE) values of 0.125 and 0.568, and Mean Squared Logarithmic Error (MSLE) values of 0.005 and 0.058 in the training and testing sets, respectively. It also showed MSLE reductions of 83.4% and 60% compared to LMSR and traditional 1D equivalent linear analysis. Shapley Additive explanations and partial dependence plots were used to interpret model behavior, revealing key variable impacts and increasing model transparency. The results highlight the capability of ML—particularly RTE—in improving the accuracy and efficiency of seismic site response predictions, demonstrating strong potential for advancing geotechnical engineering applications.

Evaluation of invasion depth is essential for the treatment strategy of esophageal squamous cell carcinoma (ESCC). However, the application of the Japanese Endoscopic Society classification system, based on the patterns of intravascular papillary cell layer (IPCL) and avascular area (AVA), requires a long-term training for endoscopists. We aimed to develop explainable semi-supervised models for predicting ESCC invasion depth based on the IPCL/AVA patterns. A total of 2,643 images of magnifying endoscopy with narrow-band imaging in the upstream task, self-supervised contrastive learning (n = 2,175), and the downstream task, fine-tuning (n = 468), were from Suzhou. In the fine-tuning, two approaches were adopted: the traditional blackbox or the explainable AI. Lastly, the models were evaluated in an external test dataset (Jintan, n = 60), in comparison with two endoscopists. The primary outcome was 3-way classification of ESCC invasion depth. The metrics included accuracy, Matthew correlation coefficient, and Cohen’s kappa. Furthermore, Grad-CAM was for visualized explanation of images; local interpretation, feature importance, and partial dependence plots were conducted for classifiers; and t-SNE was for visualization of feature vectors. A Xception-backboned explainable model (accuracy 0.817) had exhibited better performance than other models and a junior endoscopist (0.733), even though it underperformed a senior (0.883) by 0.066 on accuracy. However, the endoscopists’ performance was improved by AI assistance (junior 0.833 and senior 0.917). The explainable semi-supervised framework empowers AI models to achieve improved transparentness and performance, facing the opacity of traditional supervised learning and limited amounts of labelled endoscopic images.

The rapid expansion of online education has intensified the need to investigate the multifactorial determinants of university students’ satisfaction with digital learning platforms. While prior studies have often examined technical or pedagogical components in isolation, limited attention has been paid to their interaction with students’ psychological well-being, particularly through nonlinear mechanisms. To address this gap, this study employs a Random Forest–based framework to model satisfaction using a multidimensional dataset from 782 university students. Measured variables included platform usability, content quality, emotional experience, and self-regulation. Data were standardized via Z-scores, and class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE). Model performance was evaluated using accuracy, F1-score, and area under the ROC curve (AUC). Results identified platform stability and content update frequency as the most influential predictors, with AUC values exceeding 0.95 across most satisfaction levels. Psychological factors—especially perceived enjoyment and emotional stability—also contributed significantly. Partial dependence plots revealed threshold and saturation effects, highlighting complex nonlinear patterns missed by traditional linear models. However, performance declined in predicting low-satisfaction cases (AUC = 0.70), likely due to subgroup underrepresentation. This study contributes theoretically by integrating cognitive-affective dimensions, methodologically by demonstrating the utility of machine learning in modeling nonlinear interactions, and practically by providing actionable insights for platform optimization. Future research should incorporate additional psychological constructs, such as cognitive load and resilience, and apply the model across more diverse learner populations to enhance generalizability and support inclusive, user-centered digital education.

Development and validation of an interpretable machine learning model for predicting hyperuricemia risk: Based on environmental chemical exposure.

Arsenic and nitrate contamination of groundwater have been major causes of concern to both the environment and the health of the people, which are significant risks to drinking water quality. In this study, machine learning (ML) and deep learning (DL) models are applied to predict groundwater contamination trends in different parts of India. Mapping a five-year time series historical dataset (2016–2021) of important physicochemical parameters such as conductivity, pH, BOD, fluoride, arsenic, and nitrate, this paper compares some machine learning and deep learning models. Feature importance revealed BOD, total dissolved solids (TDS), and conductivity to be important predictors of arsenic contamination, while agricultural and industrial activities dictate nitrate contamination. Temporal analysis for the variability of arsenic levels revealed decreasing values post-year 2019, which may be due to dilution effects and regulatory measures, while nitrate contamination fluctuated region-wise. After hyperparameter tuning, XGBoost was the most predictive (R² = 0.70), outperforming traditional regression analysis. Partial Dependence Plots (PDP) also caught detailed non-linear relationships among water quality parameters. The findings indicate the potential of predictive models based on AI in groundwater monitoring in real-time to enable better mitigation of contamination. This study contributes to the offering of reliable AI-based systems of monitoring the groundwater in real-life cases and sustainable resource management planning.

The critical mean water velocity for sediment incipient motion (Vc) is a key factor in regulating sediment transport. In this study, a Genetic Expression Programming (GEP) model was developed using 261 experimental datasets, incorporating dimensionless input parameters, including riverbed slope (S), grain size to water depth ratio (d50/h), dimensionless critical shear stress (θc), and dimensionless particle diameter (D*) as input parameters. The predictive performance of the model was assessed by comparing it with five empirical equations and two artificial intelligence models, namely, random forest (RF) and K-nearest neighbors. Model evaluation was conducted using coefficient of determination (R2), root mean square error, and mean absolute error. The results indicate that the GEP model (R2 = 0.9317) and RF model (R2 = 0.9069) exhibit superior predictive accuracy. The sensitivity analysis results demonstrate that in the GEP model, the critical mean water velocity for sediment incipient motion Vc exhibits an approximately linear increase with the dimensionless particle diameter D*, a linear decrease with increasing riverbed slope S, a linearly increases with increasing dimensionless critical shear stress θc, and a U-shaped variation as the grain size to water depth ratio d50/h increases. Partial dependence plots further elucidate the intricate interdependencies among the input variables, while SHapley Additive exPlanations analysis substantiates the dominant influence of d50/h in model predictions, followed by D*, S, and θc.

Optimizing Cu2 + adsorption prediction in Undaria pinnatifida using machine learning and isotherm models.

Optimizing swine manure composting parameters with integrated CatBoost and XGBoost models: nitrogen loss mitigation and mechanism.

Predictive modeling and interpretability analysis of bioconcentration factors for organic chemicals in fish using machine learning.

Machine learning models are increasingly used for streamflow prediction due to their promising performance. However, their data-driven nature makes interpretation challenging. This study explores the interpretability of a Random Forest model trained on high streamflow events from a hydrological perspective, comparing methods for assessing feature influence. The results show that the mean decrease accuracy, mean decrease impurity, Shapley additive explanations, and Tornado methods identify similar key features, though Tornado presents the most notable discrepancies. Despite the model being trained with events of considerable temporal variability, the last observed streamflow is the most relevant feature accounting for over 20% of importance. Moreover, the results suggest that the model identifies a catchment region with a runoff that significantly affects the outlet flow. Accumulated local effects and partial dependence plots may represent first infiltration losses and soil saturation before precipitation sharply impacts streamflow. However, only accumulated local effects depict the influence of the scarce highest accumulated precipitation on the streamflow. Shapley additive explanations are simpler to apply than the local interpretable model-agnostic explanations, which require a tuning process, though both offer similar insights. They show that short-period accumulated precipitation is crucial during the steep rising limb of the hydrograph, reaching 72% of importance on average among the top features. As the peak approaches, previous streamflow values become the most influential feature, continuing into the falling limb. When the hydrograph goes down, the model confers a moderate influence on the accumulated precipitation of several hours back of distant regions, suggesting that the runoff from these areas is arriving. Machine learning models may interpret the catchment system reasonably and provide useful insights about hydrological characteristics.

Automated external defibrillator resources (AEDRs) are the crux of out-of-hospital cardiac arrest (OHCA) responses, enhancing safe and sustainable urban environments. However, existing studies failed to consider the nexus between built environment (BE) features and AEDRs. Can explainable machine-learning (ML) methods reveal the BE-AEDR nexus? This study applied an Optuna-based extreme gradient boosting (OP_XGBoost) decision tree model with SHapely Additive exPlanations (SHAP) and partial dependence plots (PDPs) aiming to scrutinize the spatial effects, relative importance, and non-linear impact of BE features on AEDR intensity across grid and block urban patterns in Tianjin Downtown, China. The results indicated, that (1) marginally, the AEDR intensity was most influenced by the service coverage (SC) at grid scale and nearby public service facility density (NPSF_D) at block scale, while synergistically, it was shaped by comprehensive accessibility and land-use interactions with the prioritized block pattern; (2) block-level granularity and (3) non-linear interdependencies between BE features and AEDR intensity existed as game-changers. The findings suggested an effective and generalizable approach to capture the complex interplay of the BE-AEDR and boost the AED deployment by setting health at the heart of the urban development framework.

ABSTRACT This study introduces a novel methodology for measuring a monthly FinTech index to address the timeliness challenges in systemic financial risk prediction using FinTech data. By employing machine learning models, the SHAP algorithm, and partial dependence plots, we assess the role of FinTech of different technical types as drivers of systemic financial risk. We simultaneously conduct comparative analyses of the predictive performance among traditional AR models, machine learning models, and ensemble forecasting models. The findings indicate that artificial intelligence, big data, and internet FinTech have the most significant influence on systemic financial risk, whereas IoT, cloud computing, and blockchain FinTech have a relatively limited impact. Regarding predictive performance, machine learning models generally outperform traditional AR models, with the K-Nearest Neighbors (KNN) model demonstrating particularly superior prediction accuracy and optimal robustness. Furthermore, three ensemble forecasting models (MEAN, MEDIAN, and TRIMMED MEAN) outperform individual machine learning models in terms of predictive performance. Notably, the impact of FinTech of different technical types on systemic financial risk exhibits diversified and nonlinear relationships, with significant variations in directional effects, sensitivity, and inflection points.

Predicting the flexural behavior of fiber-reinforced ultra-high-performance concrete (UHPC) remains a significant challenge due to the complex interactions among numerous mix design parameters. This study presents a machine learning-based framework aimed at accurately estimating the modulus of rupture (MOR) of UHPC. A comprehensive dataset comprising 566 distinct mixtures, characterized by 41 compositional and fiber-related variables, was compiled. Seven regression models were trained and evaluated, with Random Forest, Extremely Randomized Trees, and XGBoost yielding coefficients of determination (R2) exceeding 0.84 on the test set. Feature importance was quantified using Shapley values, while partial dependence plots (PDPs) were employed to visualize both individual parameter effects and key interactions, notably between fiber factor, water-to-binder ratio, maximum aggregate size, and matrix compressive strength. To validate the predictive performance of the machine learning models, an independent experimental campaign was carried out comprising 26 UHPC mixtures designed with varying binder compositions—including supplementary cementitious materials such as fly ash, ground recycled glass, and calcium carbonate—and reinforced with mono-fiber (straight steel, hooked steel, and PVA) and hybrid-fiber systems. The best-performing models were integrated into a hybrid neural network, which achieved a validation accuracy of R2 = 0.951 against this diverse experimental dataset, demonstrating robust generalizability across both material and reinforcement variations. The proposed framework offers a robust predictive tool to support the design of more sustainable UHPC formulations incorporating supplementary cementitious materials without compromising flexural performance.

BackgroundBuilding machine learning models that are interpretable, explainable, and fair is critical for their trustworthiness in clinical practice. Interpretability, which refers to how easily a human can comprehend the mechanism by which a model makes predictions, is often seen as a primary consideration when adopting a machine learning model in health care. However, interpretability alone does not necessarily guarantee explainability, which offers stakeholders insights into a model’s predicted outputs. Moreover, many existing frameworks for model evaluation focus primarily on maximizing predictive accuracy, overlooking the broader need for interpretability, fairness, and explainability.ObjectiveThis study proposes a 3-stage machine learning framework for responsible model development through model assessment, selection, and explanation. We demonstrate the application of this framework for predicting cardiovascular disease (CVD) outcomes, specifically myocardial infarction (MI) and stroke, among people with type 2 diabetes (T2D).MethodsWe extracted participant data comprised of people with T2D from the ACCORD (Action to Control Cardiovascular Risk in Diabetes) dataset (N=9635), including demographic, clinical, and biomarker records. Then, we applied hold-out cross-validation to develop several interpretable machine learning models (linear, tree-based, and ensemble) to predict the risks of MI and stroke among patients with diabetes. Our 3-stage framework first assesses these models via predictive accuracy and fairness metrics. Then, in the model selection stage, we quantify the trade-off between accuracy and fairness using area under the curve (AUC) and Relative Parity of Performance Scores (RPPS), wherein RPPS measures the greatest deviation of all subpopulations compared with the population-wide AUC. Finally, we quantify the explainability of the chosen models using methods such as SHAP (Shapley Additive Explanations) and partial dependence plots to investigate the relationship between features and model outputs.ResultsOur proposed framework demonstrates that the GLMnet model offers the best balance between predictive performance and fairness for both MI and stroke. For MI, GLMnet achieves the highest RPPS (0.979 for gender and 0.967 for race), indicating minimal performance disparities, while maintaining a high AUC of 0.705. For stroke, GLMnet has a relatively high AUC of 0.705 and the second-highest RPPS (0.961 for gender and 0.979 for race), suggesting it is effective across both subgroups. Our model explanation method further highlights that the history of CVD and age are the key predictors of MI, while HbA1c and systolic blood pressure significantly influence stroke classification.ConclusionsThis study establishes a responsible framework for assessing, selecting, and explaining machine learning models, emphasizing accuracy-fairness trade-offs in predictive modeling. Key insights include: (1) simple models perform comparably to complex ensembles; (2) models with strong accuracy may harbor substantial differences in accuracy across demographic groups; and (3) explanation methods reveal the relationships between features and risk for MI and stroke. Our results underscore the need for holistic approaches that consider accuracy, fairness, and explainability in interpretable model design and selection, potentially enhancing health care technology adoption.