Improving Machine Learning Classification Predictions through SHAP and Features Analysis Interpretation.

Prediction of gully erosion susceptibility through the lens of the SHapley Additive exPlanations (SHAP) method using a stacking ensemble model.

Forecasting Hematological Activity in Antiphospholipid Syndrome Using Predictive Models

Background: Stroke remains a critical global health concern, disproportionately affecting individuals with hypertension which is a well-established, modifiable risk factor. Traditional risk scoring systems often fall short in accurately predicting stroke onset due to their reliance on fixed clinical thresholds and limited variable interaction modeling. As the complexity of health data increases, machine learning (ML) and explainable artificial intelligence (XAI) present powerful tools to uncover hidden patterns and enable precision risk stratification. Objectives: This study proposes a novel, interpretable machine learning framework that uses ensemble learning and SHapley Additive exPlanations (SHAP) to enhance stroke risk prediction in hypertensive patients. The objective is twofold: to improve the predictive power of stroke models and to provide clinically relevant insights that support real-time, data-driven decisions in preventive care. Methods: We utilized a real-world clinical dataset encompassing demographic, physiological, and behavioral variables associated with stroke. Data preprocessing included k-nearest neighbor imputation for missing values, normalization of continuous features, and class balancing via Synthetic Minority Oversampling Technique (SMOTE). A hybrid feature selection pipeline, combining the sparsityenforcing capabilities of LASSO regression with the iterative refinement of Recursive Feature Elimination (RFE), was employed to identify the most salient predictors. Multiple ML models, including logistic regression, deep neural networks, random forests, and gradient boosting machines, were trained and validated using cross-validation. SHAP values were computed post-training to enable individualized, interpretable model outputs. Results: Ensemble models, particularly Gradient Boosting and Random Forest, demonstrated superior discriminative performance, achieving AUC-ROC scores above 0.78 following class balancing. The integrated LASSO-RFE approach revealed age, hypertension status, and average glucose levels as dominant predictors across models. SHAP visualizations confirmed the influence of these features, while also highlighting nuanced interactions involving lifestyle and socioeconomic variables. Logistic Regression, when optimized for recall, achieved the highest balanced accuracy (0.77), reinforcing the clinical utility of simpler models when interpretability is paramount. Conclusion: This study introduces a transparent and high-performing machine learning framework for stroke risk prediction in hypertensive individuals. By integrating ensemble learning, hybrid feature selection, and explainable AI, the framework bridges the gap between predictive modeling and clinical applicability. These findings support the deployment of interpretable ML tools in routine care, enabling proactive interventions, personalized patient education, and ultimately, reduced stroke incidence.

To identify factors affecting and key environmental factors of the Oncomelania hupensis snail density in the Yangtze River Delta region using machine learning methods. Administrative village-level O. hupensis snail survey data in the Yangtze River Delta (including Shanghai Municipality, Jiangsu Province, Zhejiang Province and Anhui Province) from 2011 to 2021 were retrieved from the Information Management System for Parasitic Disease Control of Chinese Center for Disease Control and Prevention. Environmental factor data were captured from the Google Earth Engine platform, including elevation, slope, terrain, normalized difference vegetation index (NDVI), vegetation type, soil type, total petroleum hydrocarbon (TPH), ammonium nitrogen, inorganic nitrogen, dissolved oxygen, pH of water, chemical oxygen demand (COD) and inorganic phosphorus, and climatic factor data in the study region were retrieved from the Copernicus Climate Data Store, including annual precipitation, aridity index and annual mean temperature (AMT). O. hupensis snail survey data in the Yangtze River Delta region from 2011 to 2021 were randomly divided into a training set (70%) and a test set (30%), and five machine learning models were selected for machine learning model construction and comparative analysis of the O. hupensis snail density using the software R 4.3.0, including random forest (RF), eXtreme gradient boosting (XGBoost), support vector machine (SVM), gradient boosting machine (GBM) and neural network (NN). The XGBoost model was employed to construct a predictive model for the O. hupensis snail density, and the impact of each environmental factor on O. hupensis snail distribution was quantified. The SHapley Additive exPlanations (SHAPs) values were calculated to estimate the average contribution of each variable to the model prediction, and the core environmental factors affecting the O. hupensis snail population density were screened. Among the five machine learning models, the XGBoost model exhibited the optimal comprehensive performance, with the coefficient of determination (R2) of 0.855, mean squared error (MSE) of 0.188, root mean squared error (RMSE) of 0.434 and mean absolute error (MAE) of 0.155, respectively. Analysis of factors affecting the O. hupensis snail density with the XGBoost model showed that among the 16 environmental factors, the top four high-impact factors ranked by SHAPs values included annual precipitation, elevation, aridity index and NDVI, with cumulative SHAPs contributions of 75%, which was higher than that of other environmental factors. If NDVI was higher than 0.6, the O. hupensis snail density increased with NDVI and peaked if NDVI was 0.8 (1.60 snails/0.1 m2). The O. hupensis snail density increased with elevation if the elevation ranged from 14 to 40 m, and slowly rose if the annual precipitation ranged from 900 to 1 300 mm, and then increased rapidly to the peak (1.52 snails/0.1 m2) if the annual precipitation ranged from 1 300 to 1 500 mm. In addition, the O. hupensis snail density increased rapidly to the maximum (1.60 snails/0.1 m2) if the aridity index ranged from 0.8 to 1.1, and decreased gradually if the aridity index exceeded 1.1. The XGBoost model shows excellent performance in prediction of the O. hupensis snail density and identification of key environmental factors in the Yangtze River Delta region. Annual precipitation, elevation, aridity index and NDVI are key environmental factors affecting the distribution and density of O. hupensis snails in the Yangtze River Delta region.

Prostate cancer is still one of the most common and fatal types of cancer in men worldwide. Early detection is the key to enhancing patient survival and reducing the use of invasive treatments. This research examines the use of machine learning as a tool for assisting the classification of prostate cancer cases based on standard clinical biomarkers. A public dataset of 100 patient samples was utilized, containing clinical features like PSA levels, perimeter, radius, texture, and more. A predictive model was created based on the XGBoost algorithm and its performance was tested using a 5-fold cross-validation method. The model resulted in a mean F1 score of 0.90 and a mean ROC–AUC of 0.93, indicating superior predictive capability. To improve interpretability, SHAP (Shapley Additive exPlanations) values were calculated, which identified PSA, perimeter, and texture as the most predictive features. These results indicate that machine learning algorithms, when combined with publicly available clinical biomarkers, can be used to develop trustworthy, interpretable, and cost-efficient tools for prostate cancer detection at an early stage. The method has the potential to be of use in supporting clinical decision-making and minimizing the necessity for invasive diagnostic testing. KEYWORDS: Prostate cancer, Machine learning, XGBoost algorithm, SHAP values, Clinical biomarkers

Artificial intelligence-based analysis of behavior and brain images in cocaine-self-administered marmosets

The application of Artificial Intelligence (AI) and Machine Learning (ML) models is increasingly leveraged to automate and optimize Data Centre (DC) operations. However, the interpretability and transparency of these complex models pose critical challenges. Hence, this paper explores the Shapley Additive exPlanations (SHAP) values model explainability method for addressing and enhancing the critical interpretability and transparency challenges of predictive maintenance models. This method computes and assigns Shapley values for each feature, then quantifies and assesses their impact on the model’s output. By quantifying the contribution of each feature, SHAP values can assist DC operators in understanding the underlying reasoning behind the model’s output in order to make proactive decisions. As DC operations are dynamically changing, we additionally investigate how SHAP can capture the temporal behaviors of feature importance in the dynamic DC environment over time. We validate our approach with selected predictive models using an actual dataset from a High-Performance Computing (HPC) DC sourced from the Enea CRESCO6 cluster in Italy. The experimental analyses are formalized using summary, waterfall, force, and dependency explanations. We delve into temporal feature importance analysis to capture the features’ impact on model output over time. The results demonstrate that model explainability can improve model transparency and facilitate collaboration between DC operators and AI systems, which can enhance the operational efficiency and reliability of DCs by providing a quantitative assessment of each feature’s impact on the model’s output.

Suspended sediment concentration (SSC) significantly impacts water quality, aquatic ecosystems, and reservoir capacity, making accurate prediction vital for effective watershed management. Traditional empirical and physically based models often struggle to handle the complexities and non-linear dynamics of sediment transport. Machine learning (ML) techniques, with their ability to model non-linear relationships and process large datasets, offer a promising alternative. This study explores the application of ML models, including extra trees (ET), random forest (RF), categorical boosting (CatBoost), and extreme gradient boosting (XGBoost) and their combination with genetic programming (GP), to predict SSC. Key environmental variables such as precipitation, streamflow, and seasonality are used as inputs, and the models are trained and validated using historical hydrological data. The SHapley Additive exPlanations (SHAP) framework is employed to interpret the models, offering insights into the influence of each input variable on SSC predictions. Results demonstrate that ML models outperform traditional approaches in accuracy and robustness, particularly in capturing peak sediment events. The findings underline the potential of ML in improving SSC prediction and guiding sustainable watershed management practices.Keywords: Suspended Sediment Concentration (SSC), Machine Learning (ML), SHAP Values, Hydrological Modeling, Sediment Transport, Watershed Management.

Breast cancer continues to be a leading cause of death among women in the world. The prediction of survival outcomes based on treatment modalities, i.e., chemotherapy, hormone therapy, surgery, and radiation therapy is an essential step towards personalization in treatment planning. However, Machine Learning (ML) models may improve these predictions by investigating intricate relationships between clinical variables and survival. This study investigates the performance of several ML models to predict survival rate in patients undergoing diverse breast cancer treatments i.e., chemotherapy, hormone therapy, surgery and radiation using multiple clinical parameters. The dataset consisted of 5000 samples and turned into downloaded from Kaggle. The models assessed blanketed Support Vector Machines (SVM), K-Nearest Neighbor (KNN), AdaBoost, Gradient Boosting, Random Forest, Gaussian Naive Bayes, Logistic Regression, Extreme Gradient Boosting (XG boost), and Decision tree. Performance of the models was assessed using parameters such as Accuracy, Precision, Recall, F1-Score and Area under the Receiver Operating Characteristic Curve (AUC-ROC). SHAP (SHapley Additive exPlanations) values analysis was done to provide an explanation for the impact of a feature on model predictions using Waterfall and Beeswarm plots. Anticipated baseline (E(f(x))) were in comparison to the predictions (f(x)) for each therapy group. Performance of Gradient Boosting was shown to be the best with an Accuracy: 0.972, Precision: 0.973, Recall: 0.972, F1-Score: 0.973, and AUC-ROC Score: 0.997. Chemotherapy had a notably bad impact on survival, with an f(x) of -0.274 and an E(f(x)) of -0.025. Hormone therapy showed the maximum detrimental effect on survival, with an f(x) of -0.408. Surgical operation had an extraordinarily impartial impact (f(x) = -0.041), even as radiation therapy positively impacted survival results with an f(x) of 0.22. Gradient Boosting was the most predictive algorithm for breast cancer survival outcomes. This SHAP-primarily based analysis provides a complete knowledge of ways one-of-a-kind treatments have an effect on survival predictions in breast cancer patients. Radiation therapy indicates the most tremendous effect on survival, whilst hormone therapy reveals the maximum poor effect. Future studies need to explore personalized treatment strategies that comprise these insights to enhance patient effects.

Nuclear data (ND) are the input data for neutron‐transport simulations to answer questions related to nuclear technologies. Subsets of ND, here > 20,000 data points, are validated with respect to thousands of criticality experiments that represent various applications on a small scale. The aim of validation with these experiments is to find errors in ND or methods. The key challenge here is that several hundreds of ND are used to simulate one integral value. Hence, one cannot clearly identify what ND are leading to bias in criticality measurements. In fact, a mistake in one nuclear‐data observable can be compensated with an error in another, and the predicted criticality value would still be predicted in agreement with experimental data. Random forest (RF) was previously employed to predict bias in criticality measurements using sensitivities of simulated criticality experiments to ND. The SHapley Additive exPlanations (SHAP) metric was then applied to attribute the importance of each ND experiment and observable to bias prediction. This, however, did not highlight what ND were jointly related to predicting bias. This is important as it could inform us about where compensating errors in ND could hide. We tackle this shortcoming here by first decomposing the ND sensitivities to integral‐experiment simulations into principal components. Then we use principal component projections to predict bias via the RF and SHAP. The SHAP values and principal components are employed to reconstruct detailed SHAP values for each ND observable. We demonstrate that these extended SHAP bias predictions are more robust, less noisy, and more efficient. In addition, we show that this approach accounts for covariance in ND sensitivities and automates the identification of where compensating errors could hide in ND.

ObjectivesThis study aims to build a machine learning (ML) model to predict the recurrence probability for postoperative non-lactating mastitis (NLM) by Random Forest (RF) and XGBoost algorithms. It can provide the ability to identify the risk of NLM recurrence and guidance in clinical treatment plan.MethodsThis study was conducted on inpatients who were admitted to the Mammary Department of Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine between July 2019 to December 2021. Inpatient data follow-up has been completed until December 2022. Ten features were selected in this study to build the ML model: age, body mass index (BMI), number of abortions, presence of inverted nipples, extent of breast mass, white blood cell count (WBC), neutrophil to lymphocyte ratio (NLR), albumin-globulin ratio (AGR) and triglyceride (TG) and presence of intraoperative discharge. We used two ML approaches (RF and XGBoost) to build models and predict the NLM recurrence risk of female patients. Totally 258 patients were randomly divided into a training set and a test set according to a 75%-25% proportion. The model performance was evaluated based on Accuracy, Precision, Recall, F1-score and AUC. The Shapley Additive Explanations (SHAP) method was used to interpret the model.ResultsThere were 48 (18.6%) NLM patients who experienced recurrence during the follow-up period. Ten features were selected in this study to build the ML model. For the RF model, BMI is the most important influence factor and for the XGBoost model is intraoperative discharge. The results of tenfold cross-validation suggest that both the RF model and the XGBoost model have good predictive performance, but the XGBoost model has a better performance than the RF model in our study. The trends of SHAP values of all features in our models are consistent with the trends of these features’ clinical presentation. The inclusion of these ten features in the model is necessary to build practical prediction models for recurrence.ConclusionsThe results of tenfold cross-validation and SHAP values suggest that the models have predictive ability. The trend of SHAP value provides auxiliary validation in our models and makes it have more clinical significance.

Prediction of plasma trough concentration of voriconazole in adult patients using machine learning

Due to rising demand, the worldwide cement market is expected to increase from $340.61 billion in 2022 to $481.73 billion by 2029. Quarrying, raw material processing, and calcination are steps in cement production. The societies in India and Nepal have to deal with environmental issues such as air pollution, resource depletion, and the effects of climate change. A case study of Nepal's Udayapur Cement Industry Limited (UCIL) exposed antiquated production methods that reduce energy efficiency. Utilizing regression models like Extra Trees (Extremely Randomized Trees) Regressor, CatBoost (Categorial Boosting) Regressor, and XGBoost (eXtreme Gradient Boosting) Regressor, Random Forest and Ensemble of Sparse Embedded Trees (SET) machine learning is used to examine the demand, supply, and Gross Domestic Product (GDP) performance of cement manufacturing in India which shares a common cement related infrastructure to Nepal. Since businesses understand how important sustainability is to attract new customers and minimizing environmental effects, our study emphasizes the necessity of sustainable practices in the cement production industry. On evaluation, the Extra Trees Regressor showed strong performance, along with the SET (Stacking) model, which was further validated using a nested cross-validation technique. Random Forest, on the other hand, had trouble; it displayed the greatest RMSE (15617.85) and the lowest testing (0.8117), suggesting poorer generalization. The SET (Stacking) Ensemble model gained a testing R 2 score (0.9372) and a testing RMSE (9019.76). In cross-validation, the Extra Trees model with a mean cross-validation R 2 score of 0.93 and a low standard deviation of 0.04 proved to be the best-performing model, as evidenced by lower differences in R 2 score across folds compared to other models, demonstrating its high predictive performance. The SHAP (SHapley Additive exPlanations) interpretability analysis indicates that population is the primary factor influencing GDP estimates. A Tkinter-based application was also developed to forecast GDP using the training model. To attain sustainability and lessen the effects of climate change on the cement sector, these findings highlight the adoption of cutting-edge technologies and energy-efficient procedures.

Institutional delivery dropout (IDD), defined as delivery outside a health facility despite attending antenatal care (ANC), remains a significant barrier to reducing maternal mortality in Nigeria. Traditional statistical models often fall short of capturing the complex, non-linear interactions among the socio-demographic factors that drive this critical health behavior. Using a comprehensive dataset of 16,100 women from the 2018 Nigeria Demographic and Health Survey (NDHS), we applied and compared seven diverse machine learning (ML) algorithms, including models such as Support Vector Machine (SVM), Gradient Boosting (GB), and Extreme Gradient Boosting (XGBoost). The model performance was systematically evaluated using metrics such as accuracy, Area Under the Receiver Operating Characteristic curve (AUROC), F1-score, and detailed confusion matrices. Furthermore, SHapley Additive explanations (SHAP) were used to provide transparent interpretations of feature importance and predictive contributions. Gradient Boosting was the best-performing model, achieving the highest F1-score (0.755) and AUROC (0.82). SVM achieved the highest accuracy (0.740) and recall (0.780). SHAP identified education level, household wealth, and religion as strong predictors of IDD. The performance metrics reported with confidence intervals showed modest variability across the models. Machine learning approaches were effective in identifying women at an increased risk of institutional delivery dropout. SHAP analysis provides insights into the key sociodemographic predictors of IDD, highlighting the value of interpretable ML methods in maternal health research.

Dissolved organic matter (DOM) assemblages in freshwater rivers are formed from mixtures of simple to complex compounds that are highly variable across time and space. These mixtures largely form due to the environmental heterogeneity of river networks and the contribution of diverse allochthonous and autochthonous DOM sources. Most studies are, however, confined to local and regional scales, which precludes an understanding of how these mixtures arise at large, e.g., continental, spatial scales. The processes contributing to these mixtures are also difficult to study because of the complex interactions between various environmental factors and DOM. Here we propose the use of machine learning (ML) approaches to identify ecological processes contributing toward mixtures of DOM at a continental-scale. We related a dataset that characterized the molecular composition of DOM from river water and sediment with Fourier-transform ion cyclotron resonance mass spectrometry to explanatory physicochemical variables such as nutrient concentrations and stable water isotopes (2H and 18O). Using unsupervised ML, distinctive clusters for sediment and water samples were identified, with unique molecular compositions influenced by environmental factors like terrestrial input and microbial activity. Sediment clusters showed a higher proportion of protein-like and unclassified compounds than water clusters, while water clusters exhibited a more diversified chemical composition. We then applied a supervised ML approach, involving a two-stage use of SHapley Additive exPlanations (SHAP) values. In the first stage, SHAP values were obtained and used to identify key physicochemical variables. These parameters were employed to train models using both the default and subsequently tuned hyperparameters of the Histogram-based Gradient Boosting (HGB) algorithm. The supervised ML approach, using HGB and SHAP values, highlighted complex relationships between environmental factors and DOM diversity, in particular the existence of dams upstream, precipitation events, and other watershed characteristics were important in predicting higher chemical diversity in DOM. Our data-driven approach can now be used more generally to reveal the interplay between physical, chemical, and biological factors in determining the diversity of DOM in other ecosystems.