Search Results (753)

Background/Objectives: Cancer-associated cachexia in head and neck squamous cell carcinoma (HNSCC) is challenging to diagnose due to its complex pathophysiology. This study aimed to identify metabolic biomarkers linked to cachexia and survival in HNSCC patients using [¹⁸F]FDG-PET/CT imaging and machine learning (ML) techniques. Methods: We retrospectively analyzed 253 HNSCC patients from Vienna General Hospital and the MD Anderson Cancer Center. Automated organ segmentation was employed to quantify metabolic and volumetric data from [¹⁸F]FDG-PET/CT scans across 29 tissues and organs. Patients were categorized into low weight loss (LoWL; grades 0–2) and high weight loss (HiWL; grades 3–4) groups, according to the weight loss grading system (WLGS). Machine learning models, combined with Cox regression, were used to identify survival predictors. Shapley additive explanation (SHAP) analysis was conducted to determine the significance of individual features. Results: The HiWL group exhibited increased glucose metabolism in skeletal muscle and adipose tissue (p = 0.01), while the LoWL group showed higher lung metabolism. The one-year survival rate was 84.1% in the LoWL group compared to 69.2% in the HiWL group (p < 0.01). Pancreatic volume emerged as a key biomarker associated with cachexia, with the ML model achieving an AUC of 0.79 (95% CI: 0.77–0.80) and an accuracy of 0.82 (95% CI: 0.81–0.83). Multivariate Cox regression confirmed pancreatic volume as an independent prognostic factor (HR: 0.66, 95% CI: 0.46–0.95; p < 0.05). Conclusions: The integration of metabolic and volumetric data provided a strong predictive model, highlighting pancreatic volume as a key imaging biomarker in the metabolic assessment of cachexia in HNSCC. This finding enhances our understanding and may improve prognostic evaluations and therapeutic strategies. Full article

Natural language inference (NLI) is a fundamental and quite challenging task in natural language processing, requiring efficient methods that are able to determine whether given hypotheses derive from given premises. In this paper, we apply explainability techniques to natural-language-inference methods as a means to illustrate the decision-making procedure of its methods. First, we investigate the performance and generalization capabilities of several transformer-based models, including BERT, ALBERT, RoBERTa, and DeBERTa, across widely used datasets like SNLI, GLUE Benchmark, and ANLI. Then, we employ stacking-ensemble techniques to leverage the strengths of multiple models and improve inference performance. Experimental results demonstrate significant improvements of the ensemble models in inference tasks, highlighting the effectiveness of stacking. Specifically, our best-performing ensemble models surpassed the best-performing individual transformer by 5.31% in accuracy on MNLI-m and MNLI-mm tasks. After that, we implement LIME and SHAP explainability techniques to shed light on the decision-making of the transformer models, indicating how specific words and contextual information are utilized in the transformer inferences procedures. The results indicate that the model properly leverages contextual information and individual words to make decisions but, in some cases, find difficulties in inference scenarios with metaphorical connections which require deeper inferential reasoning. Full article

Using survey data from three dwelling types in Jakarta, we examine how dwelling type, socioeconomic identity, and commuting distance affect women’s travel-mode choices and motivations behind women’s choices for nearby and distant non-working trips. We compared the performance of the multinomial logit (MNL) model with two machine-learning classifiers, random forest (RF) and XGBoost, using Shapley additive explanations (SHAP) for interpretation. The models’ efficacy varies across different datasets, with XGBoost mostly outperforming other models. The women’s preferred commuting modes varied by dwelling type and trip purpose, but their motives for choosing the nearest activity were similar. Over half of the women rely on private motorized vehicles, with women living in the gated community heavily relying on private cars. For nearby shopping trips, low income and young age discourage women in urban villages (kampungs) and apartment complexes from walking. Women living in gated communities often choose private cars to fulfill household responsibilities, enabling them to access distant options. For nearby leisure, longer commutes discourage walking except for residents of apartment complexes. Car ownership and household responsibilities increase private car use for distant options. SHAP analysis offers practitioners insights into identifying key variables affecting travel-mode choice to design effective targeted interventions that address women’s mobility needs. Full article

Stainless-steel is extensively utilized in the key structural components of the main equipment in the nuclear island of pressurized water reactor nuclear power plants. The operational experience of nuclear power plants demonstrates that stress corrosion is one of the significant factors influencing the long-term safe operation of stainless steel in the high-temperature water of pressurized water reactor nuclear power plants. This study is based on the stress corrosion crack growth rate data of 316SS and 304SS stainless steel in the simulated primary water environment of pressurized water reactor nuclear power plants. Data mining and modeling were conducted using multiple machine learning algorithms, including Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), and Gaussian Process Regression (GPR), and the Sharpley Additive explanation (SHAP) method was employed to analyze the interpretability of the model. The results indicate that the stress corrosion crack growth rate prediction model based on XGBoost outperforms other models in all assessment indicators. Compared with empirical equations, XGBoost exhibits high flexibility and excellent data-driven learning capabilities. In the test set, 90% of the prediction errors are within the range of experimental values, with the maximum error multiple being 2.5, which significantly improves the prediction accuracy. Moreover, the distribution of SHAP values is consistent with the theoretical study of the stress corrosion behavior of stainless-steel, effectively reflecting the impact of cold working, temperature, and stress intensity factor on the stress corrosion crack growth rate, thereby proving the reliability of the model’s prediction results. The achievements of this study hold significant reference value and application prospects for the prediction of the stress corrosion behavior of stainless-steel in a high-temperature and high-pressure water environment of pressurized water reactor nuclear power plants. Full article

Background: This study investigates the application of Machine Learning techniques to predict clinical outcomes in microsurgical clipping treatments of cerebral aneurysms, aiming to enhance healthcare processes through informed clinical decision making. Methods: Relying on a dataset of 344 patients’ preoperative characteristics, various ML classifiers were trained to predict outcomes measured by the Glasgow Outcome Scale (GOS). The study’s results were reported through the means of ROC-AUC scores for outcome prediction and the identification of key predictors using SHAP analysis. Results: The trained models achieved ROC-AUC scores of 0.72 ± 0.03 for specific GOS outcome prediction and 0.78 ± 0.02 for binary classification of outcomes. The SHAP explanation analysis identified intubation as the most impactful factor influencing treatment outcomes’ predictions for the trained models. Conclusions: The study demonstrates the potential of ML for predicting surgical outcomes of ruptured cerebral aneurysm treatments. It acknowledged the need for high-quality datasets and external validation to enhance model accuracy and generalizability. Full article

This study examines mortgage loan fallout using data provided by a leading financial institution. By accurately predicting mortgage loan fallout, lenders can protect their bottom line, maintain financial stability, and contribute to a healthier economy. The paper employs various machine learning models to predict mortgage fallout based on loan, market, property, and borrower characteristics. A large dataset of locked mortgage applications from a major U.S. lender was analyzed. The random forest model demonstrated superior predictive efficiency and stability. To understand the factors influencing mortgage fallout, the SHAP method, along with empirical analysis with logistic regression, was utilized to identify key determinants. The paper discusses the implications of these findings for mortgage lenders and future research. Full article

Unconfined compressive strength (UCS) is a critical property for assessing the engineering performances of sustainable materials, such as cement–fly ash mortar (CFAM), in the design of construction engineering projects. The experimental determination of UCS is time-consuming and expensive. Therefore, the present study aims to model the UCS of CFAM with boosting machine learning methods. First, an extensive database consisting of 395 experimental data points derived from the literature was developed. Then, three typical boosting machine learning models were employed to model the UCS based on the database, including gradient boosting regressor (GBR), light gradient boosting machine (LGBM), and Ada-Boost regressor (ABR). Additionally, the importance of different input parameters was quantitatively analyzed using the SHapley Additive exPlanations (SHAP) approach. Finally, the best boosting machine learning model’s prediction accuracy was compared to ten other commonly used machine learning models. The results indicate that the GBR model outperformed the LGBM and ABR models in predicting the UCS of the CFAM. The GBR model demonstrated significant accuracy, with no significant difference between the measured and predicted UCS values. The SHAP interpretations revealed that the curing time (T) was the most critical feature influencing the UCS values. At the same time, the chemical composition of the fly ash, particularly Al₂O₃, was more influential than the fly-ash dosage (FAD) or water-to-binder ratio (W/B) in determining the UCS values. Overall, this study demonstrates that SHAP boosting machine learning technology can be a useful tool for modeling and predicting UCS values of CFAM with good accuracy. It could also be helpful for CFAM design by saving time and costs on experimental tests. Full article

The ecosystems in the mountainous region of Southwest China are exceptionally fragile and constitute one of the global hotspots for wildfire occurrences. Understanding the complex interactions between wildfires and their environmental and anthropogenic factors is crucial for effective wildfire modeling and management. Despite significant advancements in wildfire modeling using machine learning (ML) methods, their limited explainability remains a barrier to utilizing them for in-depth wildfire analysis. This paper employs Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models along with the MODIS global fire atlas dataset (2004–2020) to study the influence of meteorological, topographic, vegetation, and human factors on wildfire occurrences in the mountainous region of Southwest China. It also utilizes Shapley Additive exPlanations (SHAP) values, a method within explainable artificial intelligence (XAI), to demonstrate the influence of key controlling factors on the frequency of fire occurrences. The results indicate that wildfires in this region are primarily influenced by meteorological conditions, particularly sunshine duration, relative humidity (seasonal and daily), seasonal precipitation, and daily land surface temperature. Among local variables, altitude, proximity to roads, railways, residential areas, and population density are significant factors. All models demonstrate strong predictive capabilities with AUC values over 0.8 and prediction accuracies ranging from 76.0% to 95.0%. XGBoost outperforms LR and RF in predictive accuracy across all factor groups (climatic, local, and combinations thereof). The inclusion of topographic factors and human activities enhances model optimization to some extent. SHAP results reveal critical features that significantly influence wildfire occurrences, and the thresholds of positive or negative changes, highlighting that relative humidity, rain-free days, and land use land cover changes (LULC) are primary contributors to frequent wildfires in this region. Based on regional differences in wildfire drivers, a wildfire-risk zoning map for the mountainous region of Southwest China is created. Areas identified as high risk are predominantly located in the Northwestern and Southern parts of the study area, particularly in Yanyuan and Miyi, while areas assessed as low risk are mainly distributed in the Northeastern region. Full article

The pursuit of the Sustainable Development Goals has highlighted rural electricity consumption patterns, necessitating innovative analytical approaches. This paper introduces a novel method for predicting rural electricity consumption by leveraging deep convolutional features extracted from satellite imagery. The study employs a pretrained remote sensing interpretation model for feature extraction, streamlining the training process and enhancing the prediction efficiency. A random forest model is then used for electricity consumption prediction, while the SHapley Additive exPlanations (SHAP) model assesses the feature importance. To explain the human geography implications of feature maps, this research develops a feature visualization method grounded in expert knowledge. By selecting feature maps with higher interpretability, the “black-box” model based on remote sensing images is further analyzed and reveals the geographical features that affect electricity consumption. The methodology is applied to villages in Xinxing County, Guangdong Province, China, achieving high prediction accuracy with a correlation coefficient of 0.797. The study reveals a significant positive correlations between the characteristics and spatial distribution of houses and roads in the rural built environment and electricity demand. Conversely, natural landscape elements, such as farmland and forests, exhibit significant negative correlations with electricity demand predictions. These findings offer new insights into rural electricity consumption patterns and provide theoretical support for electricity planning and decision making in line with the Sustainable Development Goals. Full article

The PISA 2022 literacy assessment highlights a significant decline in math performance among most OECD countries, with the magnitude of this decline being approximately three times that of the previous round. Remarkably, Hong Kong, Macao, Taipei, Singapore, Japan, and Korea ranked in the top six among all participating countries or economies, with Taipei, Singapore, Japan, and Korea also demonstrating improved performance. Given the widespread concern about the factors influencing secondary-school students’ mathematical literacy, this paper adopts machine learning and the SHapley Additive exPlanations (SHAP) method to analyze 34,968 samples and 151 features from six East Asian education systems within the PISA 2022 dataset, aiming to pinpoint the crucial factors that affect middle-school students’ mathematical literacy. First, the XGBoost model has the highest prediction accuracy for math literacy performance. Second, 15 variables were identified as significant predictors of mathematical literacy across the student population, particularly variables such as mathematics self-efficacy (MATHEFF) and expected occupational status (BSMJ). Third, mathematics self-efficacy was determined to be the most influential factor. Fourth, the factors influencing mathematical literacy vary among individual students, including the key influencing factors, the direction (positive or negative) of their impact, and the extent of this influence. Finally, based on our findings, four recommendations are proffered to enhance the mathematical literacy performance of secondary-school students. Full article

Customer profiling in e-commerce is a powerful tool that enables organizations to create personalized offers through direct marketing. One crucial objective of customer profiling is to predict whether a website visitor will make a purchase, thereby generating revenue. Machine learning models are the most accurate means to achieve this objective. However, the opaque nature of these models may deter companies from adopting them. Instead, they may prefer simpler models that allow for a clear understanding of the customer attributes that contribute to a purchase. In this study, we show that companies need not compromise on prediction accuracy to understand their online customers. By leveraging website data from a multinational communications service provider, we establish that the most pertinent customer attributes can be readily extracted from a black box model. Specifically, we show that the features that measure customer activity within the e-commerce platform are the most reliable predictors of conversions. Moreover, we uncover significant nonlinear relationships between customer features and the likelihood of conversion. Full article

Fractional vegetation cover (FVC) is an essential metric forvaluating ecosystem health and soil erosion. Traditional ground-measuring methods are inadequate for large-scale FVC monitoring, while remote sensing-based estimation approaches face issues such as spatial scale discrepancies between ground truth data and image pixels, as well as limited sample representativeness. This study proposes a method for FVC estimation integrating uncrewed aerial vehicle (UAV) and satellite imagery using machine learning (ML) models. First, we assess the vegetation extraction performance of three classification methods (OBIA-RF, threshold, and K-means) under UAV imagery. The optimal method is then selected for binary classification and aggregated to generate high-accuracy FVC reference data matching the spatial resolutions of different satellite images. Subsequently, we construct FVC estimation models using four ML algorithms (KNN, MLP, RF, and XGBoost) and utilize the SHapley Additive exPlanation (SHAP) method to assess the impact of spectral features and vegetation indices (VIs) on model predictions. Finally, the best model is used to map FVC in the study region. Our results indicate that the OBIA-RF method effectively extract vegetation information from UAV images, achieving an average precision and recall of 0.906 and 0.929, respectively. This method effectively generates high-accuracy FVC reference data. With the improvement in the spatial resolution of satellite images, the variability of FVC data decreases and spatial continuity increases. The RF model outperforms others in FVC estimation at 10 m and 20 m resolutions, with R² values of 0.827 and 0.929, respectively. Conversely, the XGBoost model achieves the highest accuracy at a 30 m resolution, with an R² of 0.847. This study also found that FVC was significantly related to a number of satellite image VIs (including red edge and near-infrared bands), and this correlation was enhanced in coarser resolution images. The method proposed in this study effectively addresses the shortcomings of conventional FVC estimation methods, improves the accuracy of FVC monitoring in soil erosion areas, and serves as a reference for large-scale ecological environment monitoring using UAV technology. Full article

The tetrazolium (TZ) test is a reliable but destructive method for identifying viable seeds. In this study, a non-destructive seed viability analysis method for Allium ulleungense was developed using multispectral imaging and stacking ensemble learning. Using the Videometerlab 4, multispectral imaging data were collected from 390 A. ulleungense seeds subjected to NaCl-accelerated aging treatments with three repetitions per treatment. Spectral values were obtained at 19 wavelengths (365–970 nm), and seed viability was determined using the TZ test. Next, 80% of spectral values were used to train Decision Tree, Random Forest, LightGBM, and XGBoost machine learning models, and 20% were used for testing. The models classified viable and non-viable seeds with an accuracy of 95–91% on the K-Fold value (n = 5) and 85–81% on the test data. A stacking ensemble model was developed using a Decision Tree as the meta-model, achieving an AUC of 0.93 and a test accuracy of 90%. Feature importance and SHAP value assessments identified 570, 645, and 940 nm wavelengths as critical for seed viability classification. These results demonstrate that machine learning-based spectral data analysis can be effectively used for seed viability assessment, potentially replacing the TZ test with a non-destructive method. Full article

Accurate prediction of the compression index (c_c) is essential for geotechnical infrastructure design, especially in clay-rich coastal regions. Traditional methods for determining $c_c$ are often time-consuming and inconsistent due to regional variability. This study presents an explainable ensemble learning framework for predicting the $c_c$ of clays. Using a comprehensive dataset of 1080 global samples, four key geotechnical input variables—liquid limit (LL), plasticity index (PI), initial void ratio (e₀), and natural water content w—were leveraged for accurate $c_c$ prediction. Missing data were addressed with K-Nearest Neighbors (KNN) imputation, effectively filling data gaps while preserving the dataset’s distribution characteristics. Ensemble learning techniques, including Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and a Stacking model, were applied. Among these, the Stacking model demonstrated the highest predictive performance with a Root Mean Squared Error (RMSE) of 0.061, a Mean Absolute Error (MAE) of 0.043, and a Coefficient of Determination ($R^2$) value of 0.848 on the test set. Model interpretability was ensured through SHapley Additive exPlanations (SHAP), with $e_0$ identified as the most influential predictor. The proposed framework significantly improves both prediction accuracy and interpretability, offering a valuable tool to enhance geotechnical design efficiency in coastal and clay-rich environments. Full article

This study included 468 patients and aimed to use multimodal ultrasound radiomic technology to predict the malignancy of TI-RADS 4-5 thyroid nodules. First, radiomic features are extracted from conventional two-dimensional ultrasound (transverse ultrasound and longitudinal ultrasound), strain elastography (SE), and shear-wave-imaging (SWE) images. Next, the least absolute shrinkage and selection operator (LASSO) is used to screen out features related to malignant tumors. Finally, a support vector machine (SVM) is used to predict the malignancy of thyroid nodules. The Shapley additive explanation (SHAP) method was used to intuitively analyze the specific contributions of radiomic features to the model’s prediction. Our proposed model has AUCs of 0.971 and 0.856 in the training and testing sets, respectively. Our proposed model has a higher prediction accuracy compared to those of models with other modal combinations. In the external validation set, the AUC of the model is 0.779, which proves that the model has good generalization ability. Moreover, SHAP analysis was used to examine the overall impacts of various radiomic features on model predictions and local explanations for individual patient evaluations. Our proposed multimodal ultrasound radiomic model can effectively integrate different data collected using multiple ultrasound sensors and has good diagnostic performance for TI-RADS 4-5 thyroid nodules. Full article