Explore the vast range of titles available.

Background Due to the class imbalance issue faced when Alzheimer’s disease (AD) develops from normal cognition (NC) to mild cognitive impairment (MCI), present clinical practice is met with challenges regarding the auxiliary diagnosis of AD using machine learning (ML). This leads to low diagnosis performance. We aimed to construct an interpretable framework, extreme gradient boosting-Shapley additive explanations (XGBoost-SHAP), to handle the imbalance among different AD progression statuses at the algorithmic level. We also sought to achieve multiclassification of NC, MCI, and AD. Methods We obtained patient data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, including clinical information, neuropsychological test results, neuroimaging-derived biomarkers, and APOE-ε4 gene statuses. First, three feature selection algorithms were applied, and they were then included in the XGBoost algorithm. Due to the imbalance among the three classes, we changed the sample weight distribution to achieve multiclassification of NC, MCI, and AD. Then, the SHAP method was linked to XGBoost to form an interpretable framework. This framework utilized attribution ideas that quantified the impacts of model predictions into numerical values and analysed them based on their directions and sizes. Subsequently, the top 10 features (optimal subset) were used to simplify the clinical decision-making process, and their performance was compared with that of a random forest (RF), Bagging, AdaBoost, and a naive Bayes (NB) classifier. Finally, the National Alzheimer’s Coordinating Center (NACC) dataset was employed to assess the impact path consistency of the features within the optimal subset. Results Compared to the RF, Bagging, AdaBoost, NB and XGBoost (unweighted), the interpretable framework had higher classification performance with accuracy improvements of 0.74%, 0.74%, 1.46%, 13.18%, and 0.83%, respectively. The framework achieved high sensitivity (81.21%/74.85%), specificity (92.18%/89.86%), accuracy (87.57%/80.52%), area under the receiver operating characteristic curve (AUC) (0.91/0.88), positive clinical utility index (0.71/0.56), and negative clinical utility index (0.75/0.68) on the ADNI and NACC datasets, respectively. In the ADNI dataset, the top 10 features were found to have varying associations with the risk of AD onset based on their SHAP values. Specifically, the higher SHAP values of CDRSB , ADAS13 , ADAS11 , ventricle volume , ADASQ4 , and FAQ were associated with higher risks of AD onset. Conversely, the higher SHAP values of LDELTOTAL , mPACCdigit , RAVLT_immediate , and MMSE were associated with lower risks of AD onset. Similar results were found for the NACC dataset. Conclusions The proposed interpretable framework contributes to achieving excellent performance in imbalanced AD multiclassification tasks and provides scientific guidance (optimal subset) for clinical decision-making, thereby facilitating disease management and offering new research ideas for optimizing AD prevention and treatment programs.

As Earth science transitions into the era of big data, artificial intelligence (AI) not only holds significant potential for addressing geoscience challenges, but also plays a pivotal role in accelerating our comprehension of the complex, interactive, and multi-scale processes of Earth's behaviors. As geoscience AI models are progressively utilized for significant predictions in crucial situations, geoscience researchers are increasingly demanding their interpretability and versatility. This study proposes an interpretable geoscience artificial intelligence (XGeoS-AI) framework to unravel the mystery of image recognition in the Earth sciences, and its effectiveness and versatility are exemplified through the application to computed tomography (CT) image analysis. To enhance interpretability, the XGeoS-AI framework incorporates a local region threshold generation method (LRT) inspired by human visual mechanisms. Different kinds of artificial intelligence (AI) engines, including support vector regression (SVR), multilayer perceptron (MLP), convolutional neural network (CNN), are integrated within the XGeoS-AI framework to efficiently address geoscience image recognition challenges. Experimental findings affirm the effectiveness, versatility, and heuristics of the XGeoS-AI framework, underscoring its potential to revolutionize geoscience image recognition. Interpretable AI should receive more and more attention in the field of the Earth sciences, which is the key to promoting more rational and wider applications of AI in the field of Earth sciences.

Urinary calculi recurrence substantially exacerbates healthcare resource consumption and socioeconomic burdens, yet the underlying mechanisms remain unclear. This study aimed to identify critical risk factors for calculi recurrence, develop a machine learning (ML) algorithm-based predictive model, and evaluate its predictive performance. This retrospective cohort study analyzed 1,146 urinary calculi patients treated at the Department of Urology, the Second Affiliated Hospital of Zhengzhou University (2019–2024). Key risk factors were identified using least absolute shrinkage and selection operator (LASSO) regression combined with multivariate logistic regression, and a binary predictive model for recurrence risk was developed. Model performance was validated via the area under the curve (AUC), with SHAP (Shapley Additive Explanations) values applied to interpret predictions. This study ultimately included 708 patients. The Random Forest model was selected as the optimal algorithm, demonstrating the following performance in the validation set: AUC 0.741 (95% CI: 0.664–0.818), sensitivity 0.552 (0.426–0.674), specificity 0.828 (0.756–0.885), positive predictive value 0.597 (0.464–0.719), negative predictive value 0.800 (0.727–0.861), F1-score 0.574, and Brier score 0.186, indicating satisfactory model calibration. SHAP feature attribution analysis identified the top four factors associated with recurrence: 24-hour urinary calcium excretion, hypertension status, serum creatinine level, and 24-hour urinary oxalate excretion. This study innovatively integrated metabolic data with imaging characteristics to establish a machine learning-based predictive model for quantitative recurrence risk assessment in urinary calculi. The integration of key metabolic parameters with imaging features has enhanced the predictive performance of the model, providing an evidence-based decision-making tool for personalized metabolic intervention and recurrent stone prevention strategies.

Sedimentary facies modeling is a critical approach for understanding geological phenomena, yet the strong heterogeneity of reservoir systems poses a serious challenge for their refined characterization. In this study, we innovatively propose an interpretable attention-guided generative adversarial network framework with dual-domain learning, which achieves precise sedimentary facies modeling under the constraints of well facies and soft probability data. Specifically, we first effectively extract and preserve prior information of sedimentary facies models from both spatial and frequency domain perspectives. Then, during simulation, to enhance the capability of the network model for finely characterizing complex heterogeneous models, cross-spatial attention mechanisms are designed to effectively capture short-range and long-range dependencies between multi-scale pattern features. Additionally, through systematic feature map visualization analysis, we elucidate the processes of conditional fitting and complex sedimentary facies model reconstruction, intuitively demonstrating the functional mechanisms of each module. Finally, systematic experiments are conducted on multiple datasets to validate the effectiveness of the proposed method. The results demonstrate that the generated sedimentary facies models exhibit high consistency with training datasets in terms of visual realism and statistical indicators. Quantitative comparisons reveal remarkable performance of the method, achieving low Wasserstein distance (0.09), Kernel Inception Distance (0.0017) and Kernel Maximum Mean Discrepancy (0.21). These findings further confirm the high realism of the generated realizations regarding pattern features. This study offers a reliable and practical method for geological reservoir modeling, thereby advancing quantitative, precise geological research with broad application prospects.

The construction of cascade dam systems profoundly reshapes river hydrological processes, yet the analysis of their spatial heterogeneity effects has long been constrained by the mechanistic deficiencies and interpretability limitations of traditional mechanistic models. Focusing on the middle-lower Han River (a 652 km reach regulated by seven dams) as a representative case, this study develops an LSTM-Attention-SHAP interpretable framework to achieve, for the first time, intelligent decoupling of dam-induced hydrological effects and mechanistic analysis of spatial differentiation. Key findings include the following: (1) The LSTM model demonstrates exceptional predictive performance of water level and flow rate in intensively regulated reaches (average Nash–Sutcliffe Efficiency, NSE = 0.935 at Xiangyang, Huangzhuang, and Xiantao stations; R2 = 0.988 for discharge at Xiantao Station), while the attention mechanism effectively captures sensitive factors such as the abrupt threshold (>560 m3/s) in the Tangbai River tributary; (2) Shapley Additive exPlanations (SHAP) values reveal spatial heterogeneous dam contributions: the Cuijiaying Dam increases discharge at Xiangyang station (mean SHAP +0.22) but suppresses water level at Xiantao station (mean SHAP −0.15), whereas the Wangfuzhou Dam shows a stable negative correlation with Xiangyang water levels (mean SHAP −0.18); (3) dam operations induce cascade effects through altered channel storage capacity. These findings provide spatially adaptive strategies for flood risk zoning and ecological operations in globally intensively regulated rivers such as the Yangtze and Mekong.

The immune system acts as an intricate apparatus that is dedicated to mounting a defense and ensures host survival from microbial threats. To engage this faceted immune response and provide protection against infectious diseases, vaccinations are a critical tool to be developed. However, vaccine responses are governed by levels that, when interrogated, separately only explain a fraction of the immune reaction. To address this knowledge gap, we conducted a feasibility study to determine if multi-view modeling could aid in gaining actionable insights on response markers shared across populations, capture the immune system’s diversity, and disentangle confounders. We thus sought to assess this multi-view modeling capacity on the responsiveness to the Hepatitis B virus (HBV) vaccination. Seroconversion to vaccine-induced antibodies against the HBV surface antigen (anti-HBs) in early converters (n = 21; <2 months) and late converters (n = 9; <6 months) and was defined based on the anti-HBs titers (>10IU/L). The multi-view data encompassed bulk RNA-seq, CD4+ T-cell parameters (including T-cell receptor data), flow cytometry data, and clinical metadata (including age and gender). The modeling included testing single-view and multi-view joint dimensionality reductions. Multi-view joint dimensionality reduction outperformed single-view methods in terms of the area under the curve and balanced accuracy, confirming the increase in predictive power to be gained. The interpretation of these findings showed that age, gender, inflammation-related gene sets, and pre-existing vaccine-specific T-cells could be associated with vaccination responsiveness. This multi-view dimensionality reduction approach complements clinical seroconversion and all single modalities. Importantly, this modeling could identify what features could predict HBV vaccine response. This methodology could be extended to other vaccination trials to identify the key features regulating responsiveness.

Predicting gas-bearing properties in tight sandstone reservoirs presents a global challenge. Traditional methods based on well log interpretation rely heavily on individual experience, which can introduce significant unknown errors. Prediction methods using seismic data and logging labels often fail to capture complex interactions between geological features, resulting in low accuracy. Furthermore, these methods typically determine only gas presence without providing quantitative results. To address these limitations, this study proposes a novel interpretable machine learning (ML) framework. Its novelty lies in: (1) directly linking well testing conclusions to logging data to provide high-resolution, semi-quantitative gas-bearing labels, eliminating intermediate interpretation errors; (2) a systematic comparison of 19 ML algorithms across different paradigms (traditional ML, deep learning, and ensemble learning) using five tailored evaluation metrics, identifying LightGBM as the optimal model for this task (Accuracy = 99.76%); and (3) integrating interpretability directly into the prediction workflow based on cooperative game theory to provide global and local explanations that align with petroleum geological knowledge, significantly enhancing the model’s transparency and credibility. Applied to the Xujiahe Formation in the Sichuan Basin, this framework achieves decimeter-level accuracy and demonstrates strong generalization capability. This work proposes a novel framework that enables semi-quantitative gas-bearing property predictions with the potential for basin-scale application, directly identifying sweet spots and offering a more streamlined and interpretable high-accuracy artificial intelligence method for oil and gas resource exploration and development.

With emerging learning techniques and large datasets, the advantages of applying deep learning models in the field of tourism demand forecasting have been increasingly recognized. However, the lack of sufficient interpretability has led to questioning the credibility of most existing deep learning models. This study attempts to meet these challenges by proposing an interpretable deep learning framework, which combines the long short-term memory model with Shapley Additive interpretation. Results of two case studies conducted in China confirm that our model can perfectly reconcile interpretability and forecasting accuracy. The study has greatly promoted the development of tourism demand forecasting models and provides important practical implications for improving the ability of management decision making and resource optimization.

Ionic conductivity is a critical determinant of electrolyte performance in lithium‐ion batteries, governing functionalities such as rate capability and low‐temperature operability. Conventional optimizations, empirical or simulation‐based, face significant limitations in either resource efficiency or predictive accuracy. To address these challenges, we developed an interpretable machine learning (ML) framework that combines least absolute shrinkage and selection operator (LASSO) regression with SHapley Additive exPlanations analysis to elucidate structure–property relationships in multicomponent electrolytes. This framework proposes a novel descriptor, model‐input‐weighted sum of LASSO features, which quantitatively captures the collective influence of molecular characteristics on ionic conductivity. Our approach achieves state‐of‐the‐art predictive accuracy (RMSE = 1.33 mS cm−1, R2${R}^{2}$  = 0.88) while identifying two dominant molecular features: PEOE_VSA1, representing surface charge distribution, and NumAtomStereoCenters, reflecting stereochemical complexity. This led to the design of an optimized ternary electrolyte (1 mol L−1 LiTFSI in MA:THF:DMF, 5:3:2 molar ratio) demonstrating unprecedented conductivity values: 15.74 mS cm−1 at 25°C and 2.69 mS cm−1 at −70°C. These results validate our framework's ability to guide the development of high‐performance electrolytes for low‐temperature applications. This study establishes a robust ML framework for accelerated electrolyte discovery, providing fundamental insights into molecular determinants of ionic conductivity. An interpretable machine learning framework that combines least absolute shrinkage and selection operator (LASSO) regression with SHapley Additive exPlanations analysis was used to investigate the structure–property relationships in multicomponent lithium‐ion battery electrolytes. By leveraging LASSO dimensionality reduction and Pearson correlation analysis in the molecular feature extraction process, we identified 8 key molecular feature descriptors that significantly influence ionic conductivity. The framework proposes a novel descriptor, the model‐input‐weighted sum of LASSO features, which quantitatively captures the collective influence of molecular characteristics on ionic conductivity, achieving state‐of‐the‐art predictive accuracy. Application of this methodology led to the design of an optimized ternary electrolyte system (1 mol L−1 LiTFSI in MA:THF:DMF, 5:3:2 molar ratio) demonstrating unprecedented conductivity values: 15.74 mS cm−1 at 25°C and 2.69 mS cm−1 at −70°C.

With emerging learning techniques and large datasets, the advantages of applying deep learning models in the field of tourism demand forecasting have been increasingly recognized. However, the lack of sufficient interpretability has led to questioning the credibility of most existing deep learning models. This study attempts to meet these challenges by proposing an interpretable deep learning framework, which combines the long short-term memory model with Shapley Additive interpretation. Results of two case studies conducted in China confirm that our model can perfectly reconcile interpretability and forecasting accuracy. The study has greatly promoted the development of tourism demand forecasting models and provides important practical implications for improving the ability of management decision making and resource optimization.