Unlocking Environmental Innovation Through Board Diversity and Governance: A Machine Learning Approach

Climate signals, driven by complex interactions and nonlinear relationships, shape weather patterns and long-term trends, complicating the identification of dominant drivers due to collinearity. This study investigates the consistency and uncertainty of machine learning (ML) techniques for feature importance in climate science, comparing SHapley Additive exPlanations (SHAP), Partial Dependence Plots (PDPs), and gain-based feature importance from Extreme Gradient Boosting (XGBoost). SHAP’s integration with Feed Forward Neural Networks (FFNN) and XGBoost is evaluated to assess model-specific uncertainties. Using winter precipitation data from Ohio, USA, as a case study, the relative contributions of global warming (GW) and the Interdecadal Pacific Oscillation (IPO) to precipitation changes are quantified. Results show GW consistently ranks higher than IPO in at least 60% of stations across all methods, with SHAP and PDPs agreeing in 89% of stations. Global SHAP importance from FFNN and XGBoost aligns in 82% of stations, with GW contributing 15% more than IPO on average, though disagreements in 18% of stations highlight model-dependent uncertainties. Temporal analysis using SHAP values indicates a moderate discrepancy in feature importance between FFNN and XGBoost models (Pearson correlation ≈ 0.5), despite their consensus on the increasing dominance of GW in recent decades, contributing to wetter winters. Regression analysis further confirms that GW accounts for approximately 70% of the multi-decadal variability in winter precipitation across Ohio, with PDPs indicating a strong monotonicity (ρ = 0.94) between warming levels and precipitation increase. PDPs visualize marginal effects but struggle with interactions, while gain-based methods tend to favor features with a greater number of effective split points that reduce loss. SHAP, though robust for ranking, varies with the base model. An ensemble framework is proposed, demonstrating the value of combining these ML techniques complementarily to account for uncertainties and enhance interpretability. This study highlights the importance of addressing methodological uncertainties in feature importance rankings to provide robust insights for climate modeling.

Assessing the association of multi-environmental chemical exposures on metabolic syndrome: A machine learning approach.

BackgroundWeaning from mechanical ventilation (MV) is an essential issue in critically ill patients, and we used an explainable machine learning (ML) approach to establish an extubation prediction model.MethodsWe enrolled patients who were admitted to intensive care units during 2015–2019 at Taichung Veterans General Hospital, a referral hospital in central Taiwan. We used five ML models, including extreme gradient boosting (XGBoost), categorical boosting (CatBoost), light gradient boosting machine (LightGBM), random forest (RF) and logistic regression (LR), to establish the extubation prediction model, and the feature window as well as prediction window was 48 h and 24 h, respectively. We further employed feature importance, Shapley additive explanations (SHAP) plot, partial dependence plot (PDP) and local interpretable model-agnostic explanations (LIME) for interpretation of the model at the domain, feature, and individual levels.ResultsWe enrolled 5,940 patients and found the accuracy was comparable among XGBoost, LightGBM, CatBoost and RF, with the area under the receiver operating characteristic curve using XGBoost to predict extubation was 0.921. The calibration and decision curve analysis showed well applicability of models. We also used the SHAP summary plot and PDP plot to demonstrate discriminative points of six key features in predicting extubation. Moreover, we employed LIME and SHAP force plots to show predicted probabilities of extubation and the rationale of the prediction at the individual level.ConclusionsWe developed an extubation prediction model with high accuracy and visualised explanations aligned with clinical workflow, and the model may serve as an autonomous screen tool for timely weaning.

IntroductionThe need for eXplainable Artificial Intelligence (XAI) in healthcare is more critical than ever, especially as regulatory frameworks such as the European Union Artificial Intelligence (EU AI) Act mandate transparency in clinical decision support systems. Post hoc XAI techniques such as Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) are widely used to interpret Machine Learning (ML) models for disease risk prediction, particularly in tabular Electronic Health Record (EHR) data. However, their reliability under real-world scenarios is not fully understood. Class imbalance is a common challenge in many real-world datasets, but it is rarely accounted for when evaluating the reliability and consistency of XAI techniques.MethodsIn this study, we design a comparative evaluation framework to assess the impact of class imbalance on the consistency of model explanations generated by LIME, SHAP, and PDPs. Using UK primary care data from the Clinical Practice Research Datalink (CPRD), we train three ML models: XGBoost (XGB), Random Forest (RF), and Multi-layer Perceptron (MLP), to predict lung cancer risk and evaluate how interpretability is affected under class imbalance when compared against a balanced dataset. To our knowledge, this is the first study to evaluate explanation consistency under class imbalance across multiple models and interpretation methods using real-world clinical data.ResultsOur main finding is that class imbalance in the training data can significantly affect the reliability and consistency of LIME and SHAP explanations when evaluated against models trained on balanced data. To explain these empirical findings, we also present a theoretical analysis of LIME and SHAP to understand why explanations change under different class distributions. It is also found that PDPs exhibit noticeable variation between models trained on imbalanced and balanced datasets with respect to clinically relevant features for predicting lung cancer risk.DiscussionThese findings highlight a critical vulnerability in current XAI techniques, i.e., their interpretability are significantly affected under skewed class distributions, which is common in medical data and emphasises the importance of consistent model explanations for trustworthy ML deployment in healthcare.

Increasing and compelling evidence has been proved that heavy metal exposure is involved in the development of insulin resistance (IR). We trained an interpretable predictive machine learning (ML) model for IR in the non-diabetic populations based on levels of heavy metal exposure. A total of 4354 participants from the NHANES (2003-2020) with complete information were randomly divided into a training set and a test set. Twelve ML algorithms, including random forest (RF), XGBoost (XGB), logistic regression (LR), GaussianNB (GNB), ridge regression (RR), support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), AdaBoost (AB), Gradient Boosting Decision Tree (GBDT), Voting Classifier (VC), and K-Nearest Neighbour (KNN), were constructed for IR prediction using the training set. Among these models, the RF algorithm had the best predictive performance, showing an accuracy of 80.14%, an AUC of 0.856, and an F1 score of 0.74 in the test set. We embedded three interpretable methods, the permutation feature importance analysis, partial dependence plot (PDP), and Shapley additive explanations (SHAP) in RF model for model interpretation. Urinary Ba, urinary Mo, blood Pb, and blood Cd levels were identified as the main influencers of IR. Within a specific range, urinary Ba (0.56-3.56µg/L) and urinary Mo (1.06-20.25µg/L) levels exhibited the most pronounced upwards trend with the risk of IR, while blood Pb (0.05-2.81µg/dL) and blood Cd (0.24-0.65µg/L) levels showed a declining trend with IR. The findings on the synergistic effects demonstrated that controlling urinary Ba levels might be more crucial for the management of IR. The SHAP decision plot offered personalized care for IR based on heavy metal control. In conclusion, by utilizing interpretable ML approaches, we emphasize the predictive value of heavy metals for IR, especially Ba, Mo, Pb, and Cd.

BackgroundMachine learning (ML) model is increasingly used to predict short-term outcome in critically ill patients, but the study for long-term outcome is sparse. We used explainable ML approach to establish 30-day, 90-day and 1-year mortality prediction model in critically ill ventilated patients.MethodsWe retrospectively included patients who were admitted to intensive care units during 2015–2018 at a tertiary hospital in central Taiwan and linked with the Taiwanese nationwide death registration data. Three ML models, including extreme gradient boosting (XGBoost), random forest (RF) and logistic regression (LR), were used to establish mortality prediction model. Furthermore, we used feature importance, Shapley Additive exPlanations (SHAP) plot, partial dependence plot (PDP), and local interpretable model-agnostic explanations (LIME) to explain the established model.ResultsWe enrolled 6994 patients and found the accuracy was similar among the three ML models, and the area under the curve value of using XGBoost to predict 30-day, 90-day and 1-year mortality were 0.858, 0.839 and 0.816, respectively. The calibration curve and decision curve analysis further demonstrated accuracy and applicability of models. SHAP summary plot and PDP plot illustrated the discriminative point of APACHE (acute physiology and chronic health exam) II score, haemoglobin and albumin to predict 1-year mortality. The application of LIME and SHAP force plots quantified the probability of 1-year mortality and algorithm of key features at individual patient level.ConclusionsWe used an explainable ML approach, mainly XGBoost, SHAP and LIME plots to establish an explainable 1-year mortality prediction ML model in critically ill ventilated patients.

BackgroundSince the inconspicuous nature of early signs associated with Chronic Obstructive Pulmonary Disease (COPD), individuals often remain unidentified, leading to suboptimal opportunities for timely prevention and treatment. The purpose of this study was to create an explainable artificial intelligence framework combining data preprocessing methods, machine learning methods, and model interpretability methods to identify people at high risk of COPD in the smoking population and to provide a reasonable interpretation of model predictions.MethodsThe data comprised questionnaire information, physical examination data and results of pulmonary function tests before and after bronchodilatation. First, the factorial analysis for mixed data (FAMD), Boruta and NRSBoundary-SMOTE resampling methods were used to solve the missing data, high dimensionality and category imbalance problems. Then, seven classification models (CatBoost, NGBoost, XGBoost, LightGBM, random forest, SVM and logistic regression) were applied to model the risk level, and the best machine learning (ML) model’s decisions were explained using the Shapley additive explanations (SHAP) method and partial dependence plot (PDP).ResultsIn the smoking population, age and 14 other variables were significant factors for predicting COPD. The CatBoost, random forest, and logistic regression models performed reasonably well in unbalanced datasets. CatBoost with NRSBoundary-SMOTE had the best classification performance in balanced datasets when composite indicators (the AUC, F1-score, and G-mean) were used as model comparison criteria. Age, COPD Assessment Test (CAT) score, gross annual income, body mass index (BMI), systolic blood pressure (SBP), diastolic blood pressure (DBP), anhelation, respiratory disease, central obesity, use of polluting fuel for household heating, region, use of polluting fuel for household cooking, and wheezing were important factors for predicting COPD in the smoking population.ConclusionThis study combined feature screening methods, unbalanced data processing methods, and advanced machine learning methods to enable early identification of COPD risk groups in the smoking population. COPD risk factors in the smoking population were identified using SHAP and PDP, with the goal of providing theoretical support for targeted screening strategies and smoking population self-management strategies.

Biochar, as an eco-friendly, carbon-rich,and economical adsorbent, proven effective in removing toxic dyes from aquatic environments. This study evaluated the efficacy of machine learning (ML) models in predicting the adsorption capacity of biochar for dye removal. Nine models, namely CatBoost, XGBoost, Gradient Boosted Decision Trees, Random Forest, Histogram-Based Gradient Boosting, Kernel Extreme Learning Machine, Kriging, Light Gradient Boosting Machine, and AdaBoost, were deployed to ascertain their predictive accuracies. The CatBoost model was highlighted for its exceptional performance, achieving the highest R2 (0.9880) and the lowest RMSE (0.0839). The stability of the model was affirmed through residual analysis and random partitioning dataset. A detailed feature importance analysis revealed that experimental conditions predominantly affect adsorption, accounting for 50.8%, followed by biochar characteristics (34.1%) and dye types (15.1%). The most significant feature impacting dye adsorption was identified as the C0 through SHapley Additive exPlanations. Partial dependence plots were used further to illustrate the influence of features on the predictive model. Additionally, experimental validation of the ML approach yielded R2 of 0.9037, reinforcing the applicability of the model. This study adds to supportive evidence of the use of ML for the prediction of adsorption capacity and encourages the development of user-friendly software, using PySimpleGUI, opening new paths to advanced data-driven methods in environmental engineering.Graphical

Background The use of incinerated bottom ash (IBA) as a sustainable construction material offers potential environmental benefits but introduces complex interactions with cement chemistry. Magnesium phosphate cement (MPC), known for its rapid hardening and superior bonding, can be optimized through the controlled incorporation of IBA. However, limited studies have addressed how the chemical components of IBA affect the compressive strength of MPC, particularly using data-driven approaches. Methods A database of 396 experimental samples was compiled from previous studies considering mix proportions, oxide compositions, and curing conditions. Four ensemble machine learning algorithms—Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), Gradient Boosting Regressor (GBR), and Random Forest (RFR)—were employed to predict compressive strength. Model robustness was validated through 5-fold cross-validation. Feature interpretation was achieved using SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDP) to quantify individual and interactive effects of chemical and physical parameters. Results The XGB model achieved the highest predictive accuracy, with mean training and testing R2 values greater than 0.90 and 0.80, and the lowest mean absolute percentage error of 16.71%. SHAP analysis identified curing age as the most dominant factor, followed by FA/C, W/C, and MgO/PO4 ratios. IBA content and specific oxides such as Fe2O3 and Al2O3 contributed positively to strength within optimal ranges. PDP confirmed nonlinear dependencies, indicating a 26% reduction in strength as W/C increased from 0.1 to 0.6, while extended curing up to 28 days improved performance substantially. Conclusion The integration of SHAP and PDP provided a transparent interpretation of feature interactions in IBA-modified MPC. The developed XGB model demonstrated strong generalization and interpretability. The combined modeling approach offers a reliable predictive framework for optimizing IBA incorporation in sustainable binder systems and advancing eco-efficient material design.

Achieving sustainable cities and promoting responsible consumption require innovative approaches to chemical design and manufacturing. Precise prediction of chemical biodegradability is crucial for evaluating environmental concerns and facilitating the transition towards green chemistry. This study investigates the effectiveness of ten distinct groups of three-dimensional (3D) molecular descriptors for classifying compounds with rapid biodegradability. The Merck molecular force field (MMFF94s) was used to compute descriptors and generate 3D conformations for a dataset of chemical compounds. The dataset underwent rigorous preprocessing, including feature selection, outlier management, and scaling. Support Vector Machines (SVMs) were tested alongside three tree-based ensemble learning algorithms: Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), and Random Forest. Bayesian optimization was employed to optimize model hyperparameters and enhance cross-validated Area Under the Receiver Operating Characteristic Curve (AUC). The GETAWAY descriptors, 3D autocorrelation descriptors, and 3D-MoRSE descriptors consistently demonstrated superior performance compared to other descriptors across all machine learning models. An SVM model trained on 3D autocorrelation descriptors achieved the highest prediction accuracy (0.88), sensitivity (0.83), specificity (0.91), F1-score (0.82), Cohen’s Kappa statistic (0.74), and an AUC of 0.93 on an independent test set. Advanced analytical techniques, including Permutation Feature Importance (PFI), SHapley Additive exPlanations(SHAP), and partial dependency plots (PDP) were utilized to identify the most influential 3D autocorrelation descriptors. The findings of this study demonstrate that 3D molecular descriptors, particularly 3D autocorrelations, play a critical role in developing accurate and interpretable models for predicting chemical biodegradability. These models contribute significantly to the advancement of green chemical design and the development of effective regulatory policies that support the objectives of SDG 11 (Sustainable Cities and Communities) and SDG 12 (Responsible Consumption and Production). By fostering sustainable chemical manufacturing practices, we can create healthier and more resilient urban environments while minimizing the environmental impact of human activities.

Tree-based machine learning (ML) algorithms, such as Extra Trees (ET), Random Forest (RF), Gradient Boosting Machine (GBM), and XGBoost (XGB) are among the most widely used in early drug discovery, given their versatility and performance. However, models based on these algorithms often suffer from misclassification and reduced interpretability issues, which limit their applicability in practice. To address these challenges, several approaches have been proposed, including the use of SHapley Additive Explanations (SHAP). While SHAP values are commonly used to elucidate the importance of features driving models' predictions, they can also be employed in strategies to improve their prediction performance. Building on these premises, we propose a novel approach that integrates SHAP and features value analyses to reduce misclassification in model predictions. Specifically, we benchmarked classifiers based on ET, RF, GBM, and XGB algorithms using data sets of compounds with known antiproliferative activity against three prostate cancer (PC) cell lines (i.e., PC3, LNCaP, and DU-145). The best-performing models, based on RDKit and ECFP4 descriptors with GBM and XGB algorithms, achieved MCC values above 0.58 and F1-score above 0.8 across all data sets, demonstrating satisfactory accuracy and precision. Analyses of SHAP values revealed that many misclassified compounds possess feature values that fall within the range typically associated with the opposite class. Based on these findings, we developed a misclassification-detection framework using four filtering rules, which we termed "RAW", SHAP, "RAW OR SHAP", and "RAW AND SHAP". These filtering rules successfully identified several potentially misclassified predictions, with the "RAW OR SHAP" rule retrieving up to 21%, 23%, and 63% of misclassified compounds in the PC3, DU-145, and LNCaP test sets, respectively. The developed flagging rules enable the systematic exclusion of likely misclassified compounds, even across progressively higher prediction confidence levels, thus providing a valuable approach to improve classifier performance in virtual screening applications.

Compressive strength prediction of cement base under sulfate attack by machine learning approach

To comprehensively analyze the association between preoperative maximum standardized uptake value (SUVmax) on 18F-fluorodeoxyglucose positron emission tomography-computed tomography and postoperative recurrence in resected non-small cell lung cancer (NSCLC) using machine learning (ML) and statistical approaches. This retrospective study included 643 patients who had undergone NSCLC resection. ML models (random forest, gradient boosting, extreme gradient boosting, and AdaBoost) and a random survival forest model were developed to predict postoperative recurrence. Model performance was evaluated using the receiver operating characteristic (ROC) AUC and concordance index (C-index). Shapley additive explanations (SHAP) and partial dependence plots (PDPs) were used to interpret model predictions and quantify feature importance. The relationship between SUVmax and recurrence risk was evaluated by using a multivariable Cox proportional hazards model. The random forest model showed the highest predictive performance (ROC AUC, 0.90; 95% CI, 0.86 to 0.97). The SHAP analysis identified SUVmax as an important predictor. The PDP analysis showed a nonlinear relationship between SUVmax and recurrence risk, with a sharp increase at SUVmax 2-5. The random survival forest model achieved a C-index of 0.82. A permutation importance analysis identified SUVmax as the most important feature. In the Cox model, increased SUVmax was associated with a higher risk of recurrence (adjusted hazard ratio, 1.03 [95% CI, 1.00 to 1.06]). Preoperative SUVmax showed significant predictive value for postoperative recurrence after NSCLC resection. The nonlinear relationship between SUVmax and recurrence risk, with a sharp increase at relatively low SUVmax values, suggests its potential as a sensitive biomarker for early identification of high-risk patients. This may contribute to more precise assessments of the risk of recurrence and personalized treatment strategies for NSCLC.

On the interpretability of machine learning methods in crash frequency modeling and crash modification factor development

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.