A Machine Learning-Based Quality Control Algorithm for Heavy Rainfall Using Multi-Source Data

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.

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

To accurately predict the impact of nitrogen reduction strategies on greenhouse gas emissions in agricultural systems and support informed decision-making for a green, low-carbon transition, this study proposes a multi-model ensemble prediction framework using integrated machine learning techniques. To address the limitations of traditional emission assessment methods—such as their inability to handle high-dimensional data, nonlinear interactions, and regional heterogeneity—three models are employed: eXtreme Gradient Boosting (XGBoost), Random Forest, and Light Gradient Boosting Machine (LightGBM). These models are combined using a Stacking ensemble approach to enhance predictive accuracy and robustness. Comprehensive performance evaluations and variable importance analyses were conducted. The proposed framework achieved an R² of 0.901 and a Root Mean Square Error (RMSE) of 0.301 on the N₂O Global dataset, significantly outperforming benchmark models such as Natural Gradient Boosting (NGBoost) (R²: 0.829; RMSE: 0.382) and Categorical Boosting (CatBoost) (R²: 0.864; RMSE: 0.341). It also demonstrated strong adaptability on the Rothamsted and DayCent datasets. SHapley Additive exPlanations (SHAP) analysis identified nitrogen application rate, rainfall frequency, and soil type as the most influential factors affecting emissions. Scenario simulations showed that a 20% reduction in nitrogen application could decrease emissions to 3.124 kg N₂O-N/ha/year. When combined with optimized management practices—such as cover cropping and improved tillage scheduling—emissions were further reduced to 2.487 kg N₂O-N/ha/year. Accordingly, the proposed method provides a practical exploration for enhancing the applicability and interpretability of models. It offers valuable insights for agricultural environmental modeling and emission reduction policy support, demonstrating both theoretical significance and practical relevance.

An experimental investigation to predict the compressive strength of lightweight Ceramsite aggregate UHPC using boosting and bagging techniques

The frequent occurrence and spread of wildfires pose a serious threat to the ecological environment and urban development. Therefore, assessing regional wildfire susceptibility is crucial for the early prevention of wildfires and formulation of disaster management decisions. However, current research on wildfire susceptibility primarily focuses on improving the accuracy of models, while lacking in-depth study of the causes and mechanisms of wildfires, as well as the impact and losses they cause to the ecological environment and urban development. This situation not only increases the uncertainty of model predictions but also greatly reduces the specificity and practical significance of the models. We propose a comprehensive evaluation framework to analyze the spatial distribution of wildfire susceptibility and the effects of influencing factors, while assessing the risks of wildfire damage to the local ecological environment and urban development. In this study, we used wildfire information from the period 2013–2022 and data from 17 susceptibility factors in the city of Guilin as the basis, and utilized eight machine learning algorithms, namely logistic regression (LR), artificial neural network (ANN), K-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), gradient boosting decision tree (GBDT), light gradient boosting machine (LGBM), and eXtreme gradient boosting (XGBoost), to assess wildfire susceptibility. By evaluating multiple indicators, we obtained the optimal model and used the Shapley Additive Explanations (SHAP) method to explain the effects of the factors and the decision-making mechanism of the model. In addition, we collected and calculated corresponding indicators, with the Remote Sensing Ecological Index (RSEI) representing ecological vulnerability and the Night-Time Lights Index (NTLI) representing urban development vulnerability. The coupling results of the two represent the comprehensive vulnerability of the ecology and city. Finally, by integrating wildfire susceptibility and vulnerability information, we assessed the risk of wildfire disasters in Guilin to reveal the overall distribution characteristics of wildfire disaster risk in Guilin. The results show that the AUC values of the eight models range from 0.809 to 0.927, with accuracy values ranging from 0.735 to 0.863 and RMSE values ranging from 0.327 to 0.423. Taking into account all the performance indicators, the XGBoost model provides the best results, with AUC, accuracy, and RMSE values of 0.927, 0.863, and 0.327, respectively. This indicates that the XGBoost model has the best predictive performance. The high-susceptibility areas are located in the central, northeast, south, and southwest regions of the study area. The factors of temperature, soil type, land use, distance to roads, and slope have the most significant impact on wildfire susceptibility. Based on the results of the ecological vulnerability and urban development vulnerability assessments, potential wildfire risk areas can be identified and assessed comprehensively and reasonably. The research results of this article not only can improve the specificity and practical significance of wildfire prediction models but also provide important reference for the prevention and response of wildfires.

The prediction of torque capacity in circular Concrete-Filled Double-Skin Tubular (CFDST) members under pure torsion is considered vital for structural design and analysis. In this study, torque capacity is predicted using machine learning (ML) algorithms, such as Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Random Forest (RF), and Decision Tree (DT), which are employed. The interpretation of the results is conducted using Shapley Additive Explanations (SHAPs). The performance of these ML models is evaluated against two traditional analytical formulas that have been proposed and are available in the literature. Through comprehensive analysis, it is shown that superior predictive capabilities are possessed by the CatBoost and XGBoost models, characterized by high R2 values and minimal mean errors. Additionally, insights into the influence of input features are provided by SHAP interpretation, with an emphasis on key parameters such as concrete compressive strength and steel tube dimensions. The gap between empirical models and ML techniques is bridged by this study, offering engineers a more accurate and efficient tool for CFDST structural design. Significant implications for optimizing CFDST column designs and advancing structural engineering practices are presented by these findings. Directions for future research include the further refinement of ML models and the integration of probabilistic analyses for enhanced structural resilience. Overall, the transformative potential of ML and SHAP interpretation in advancing the field of structural engineering is showcased by this study.

BackgroundAcute upper gastrointestinal bleeding (AUGIB) is one of the most common critical diseases encountered in the intensive care unit (ICU), with a mortality rate ranging from 15 to 20%. Accurate stratification of acute gastrointestinal bleeding into acute variceal gastrointestinal bleeding (AVGIB) and acute non-variceal gastrointestinal bleeding (ANGIB) subtypes is clinically essential as distinct entities require markedly different therapeutic approaches and even divergent prognostic implications. AUGIB characterized by hemorrhagic shock, hypotension, multiple organ dysfunction (MODS), and even circulatory failure is life-threatening. Machine learning (ML) prediction model can be an effective tool for mortality prediction, enabling the timely identification of high-risk patients and improving outcomes.MethodsA total of 3,050 acute upper gastrointestinal bleeding (AUGIB) patients were included in our research from the MIMIC-IV database, among which 625 patients were classified as AVGIB and 2,425 patients were categorized as ANGIB. Patients’ clinical features, intervention methods, vital signs, scores, and important laboratory results were collected. The Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors (SMOTE-ENN) and Adaptive Synthetic Sampling (ADASYN) were adopted to address the imbalance of the dataset. As many as 12 machine learning (ML) algorithms, namely, logistic regression (LR), decision tree (DT), random forest (RF), gradient boosting (GB), AdaBoost, XGBoost, Naive Bayes (NB), support vector machine (SVM), light gradient-boosting machine (LightGBM), K-nearest neighbors (KNN), extremely randomized trees (ET), and voting classifier (VC), were performed. The model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Shapley Additive exPlanations (SHAP) analysis was conducted to identify the most influential features contributing to mortality prediction.ResultsIn terms of AVGIB patients, extremely randomized trees model demonstrated excellent predictive value among other ML models, with the AUC of 0.996 ± 0.007, accuracy of 0.996 ± 0.009, precision of 0.957 ± 0.024, recall of 0.988 ± 0.012, and F1 score of 0.972 ± 0.007. The top 10 primary feature variables of ET model were whether combined with acute kidney failure, transfusion of albumin, vasoactive drugs, transfusion of plasma, transfusion of platelet, the max of international normalized ratio (INR), the max of prothrombin time (PT), and the max of activated partial thromboplastin time (APTT). In case of ANGIB patients, gradient boosting model proven to be the optimal machine learning models, with the AUC of 0.985 ± 0.002, accuracy of 0.948 ± 0.009, precision of 0.949 ± 0.009, recall of 0.968 ± 0.009, and F1 score of 0.959 ± 0.007. Similarly, the top 10 feature variables of GB model were Glasgow Coma Scale (GCS) score, vasoactive drugs, acute kidney failure, AIMS65 score, APACHE-II score, mechanical ventilation, the minimum of lactate, chronic liver disease, and the minimum and maximum of APTT. The SHAP visualization shows the weights of two ML models feature variables and the average sharp values of variables. Meanwhile, SHAP waterfall outputs the model prediction process with true positive and negative patients. Most importantly, two website prognostic prediction platforms were developed to enhance clinical accessibility: the ET model for AVGIB patients available at https://10zr656do5281.vicp.fun while the GB model for ANGIB patients accessible at http://10zr656do5281.vicp.fun.ConclusionThe ET model provides a reliable prognostic tool for AVGIB patients, while the GB model serves as a robust tool for ANGIB patients in predicting in-hospital mortality. By systematically integrating clinical features, risk stratification scores, vital signs, and invention measures, the ML models may deliver comprehensive predictions that benefit for clinical decision-making and potentially enhance clinical outcomes in the near future.

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.

In recent years, diabetes has become a global public health problem, and it is reported that the migrant Indians have more prevalence rate of Type-II diabetes. Also, the type-II diabetes in Indians are increased to a large extent due to modern lifestyle, food habits etc. In this work, an ElectroGastroGram (EGG) based non-invasive assessment for early prediction of type-II diabetes is proposed. Furthermore, the EGG signals are acquired from normal individuals and people with an age group between 50 and 65 who are suffering from Type-II diabetes using three electrode EGG acquisition devices. Also, the Explainable Artificial Intelligence (XAI) especially SHapley Additive exPlanations (SHAP) and Meta-Heuristics based feature selection methods are utilized to determine the prominent EGG signal features. A framework is devised using Meta-Heuristic based Hybrid Extreme Gradient (MH-XGB) Boost Classifier for an efficient classification of normal EGG signals and diabetic EGG signals. The proposed MH-XGB classifier is compared with the benchmark models namely Random Forest (RF) classifier and conventional Extreme Gradient Boosting (XGBoost) classifier by using performance metrics. Results demonstrate that the proposed MH-XGB classifier exhibits accuracy, sensitivity, specificity of 95.8%, 100%, and 92.3% respectively which is superior to other benchmark models. Additionally, it is demonstrated that the AUC, F1 Score and False Positive Rate (FPR) of the proposed MH-XGB classifier is 0.9545, 0.96 and 0.077 respectively. The proposed method is highly useful for early prediction of real-time societal disease (diabetes—Type-II) in an effective manner.

Estimating whether to treat the rupture risk of small intracranial aneurysms (IAs) with size ≤ 7mm in diameter is difficult but crucial. We aimed to construct and externally validate a convenient machine learning (ML) model for assessing the rupture risk of small IAs. One thousand four patients with small IAs recruited from two hospitals were included in our retrospective research. The patients at hospital 1 were stratified into training (70%) and internal validation set (30%) randomly, and the patients at hospital 2 were used for external validation. We selected predictive features using the least absolute shrinkage and selection operator (LASSO) method and constructed five ML models applying diverse algorithms including random forest classifier (RFC), categorical boosting (CatBoost), support vector machine (SVM) with linear kernel, light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost). The Shapley Additive Explanations (SHAP) analysis provided interpretation for the best ML model. The training, internal, and external validation cohorts included 658, 282, and 64 IAs, respectively. The best performance was presented by SVM as AUC of 0.817 in the internal [95% confidence interval (CI), 0.769-0.866] and 0.893 in the external (95% CI, 0.808-0.979) validation cohorts, which overperformed compared with the PHASES score significantly (all P < 0.001). SHAP analysis showed maximum size, location, and irregular shape were the top three important features to predict rupture. Our SVM model based on readily accessible features presented satisfying ability of discrimination in predicting the rupture IAs with small size. Morphological parameters made important contributions to prediction result.

To overcome the limitations of single models in addressing complex, nonlinear problems in predicting rock shear strength parameters and the hyperparameter random selection problem, this study constructed a novel prediction framework for rock shear strength parameters. First, the light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and random forest (RF) algorithms are employed as the base-learners for the ensemble model, with XGBoost serving as the meta-learner to build a stacking ensemble model. On the basis of the sparrow search algorithm (SSA), tent chaotic mapping is used to initialize the sparrow population, the Cauchy‒Gaussian hybrid mutation mechanism is used to dynamically select the probability control mutation type, the dynamic adaptive weight is used to adjust the balance between global exploration and local development, and Levy flight is used to help the sparrow population individuals jump out of the local optimum to construct the chaos-improved sparrow search algorithm (CISSA) to optimize the hyperparameters of the stacking model. Second, based on the 199 datasets of different rock types, the model was trained via fivefold cross-validation and evaluated based on the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE). Concurrently, the Shapley additive explanations (SHAP) method was employed to analyse the degree of contribution of each predictive index. The results demonstrate that the CISSA-Stacking model achieves R² values of 0.9936 and 0.9744 for c and φ, respectively, with corresponding RMSE of 0.4303 and 0.7635 and MAE of 0.2161 and 0.5867, indicating significantly superior overall performance compared with benchmark models. SHAP interpretability analysis revealed that the importance rankings for c are Vp, UCS, BTS, and ρ, whereas those for φ are ρ, UCS, Vp, and BTS. Finally, intelligent prediction software based on the CISSA-Stacking model was developed. The software is simple in operation, intuitive in results and excellent in performance, enables rapid and accurate prediction of c and φ through manual input of the Vp, ρ, UCS, and BTS indices or by importing tabular data containing these four indices. The engineering application further confirmed the accuracy and practical utility of both the model and the software, providing a new efficient method for engineers to quickly and accurately estimate rock shear strength parameters.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-32687-3.

Climate change is causing permafrost in the Qinghai–Tibet Plateau to degrade, triggering thermokarst hazards and impacting the environment. Despite their ecological importance, the distribution and risks of thermokarst lakes are not well understood due to complex influencing factors. In this study, we introduced a new interpretable ensemble learning method designed to improve the global and local interpretation of susceptibility assessments for thermokarst lakes. Our primary aim was to offer scientific support for precisely evaluating areas prone to thermokarst lake formation. In the thermokarst lake susceptibility assessment, we identified ten conditioning factors related to the formation and distribution of thermokarst lakes. In this highly accurate stacking model, the primary learning units were the random forest (RF), extremely randomized trees (EXTs), extreme gradient boosting (XGBoost), and categorical boosting (CatBoost) algorithms. Meanwhile, gradient boosted decision trees (GBDTs) were employed as the secondary learning unit. Based on the stacking model, we assessed thermokarst lake susceptibility and validated accuracy through six evaluation indices. We examined the interpretability of the stacking model using three interpretation methods: accumulated local effects (ALE), local interpretable model-agnostic explanations (LIME), and Shapley additive explanations (SHAP). The results showed that the ensemble learning stacking model demonstrated superior performance and the highest prediction accuracy. Approximately 91.20% of the total thermokarst hazard points fell within the high and very high susceptible areas, encompassing 20.08% of the permafrost expanse in the QTP. The conclusive findings revealed that slope, elevation, the topographic wetness index (TWI), and precipitation were the primary factors influencing the assessment of thermokarst lake susceptibility. This comprehensive analysis extends to the broader impacts of thermokarst hazards, with the identified high and very high susceptibility zones affecting significant stretches of railway and highway infrastructure, substantial soil organic carbon reserves, and vast alpine grasslands. This interpretable ensemble learning model, which exhibits high accuracy, offers substantial practical significance for project route selection, construction, and operation in the QTP.

While machine learning (ML) provides a powerful tool for correlating various factors and asphalt pavement cracking, its poor interpretability hinders a deeper mechanistic analysis of how these factors contribute to crack development. In this regard, this study proposed an interpretation framework for ML models, which consists of feature importance based on the SHapley Additive exPlanations (SHAP) method, factor influence analysis based on Accumulated Local Effects (ALE) and local conditional effects (LCE), and feature interaction analysis based on H-statistic and second-order ALE. Using the U.S. long-term pavement performance (LTPP) database, a gradient boosting regression tree (GBR) model was developed with maintenance, design, traffic, and climate factors as inputs and transverse, longitudinal, and alligator cracking as outputs. The generalization performance of all three cracking models exceeded 82%. Results indicated that transverse cracking is primarily triggered by low-temperature events, while longitudinal and alligator cracking are mainly caused by fatigue damage induced by traffic loads. Feature interaction analysis further revealed significant interactions in transverse cracking between the cumulative freezing index (CFI) and traffic load (CESAL) and in fatigue cracking between freeze‒thaw cycles (CFT) and precipitation (CTP). The outcome of this study is expected to bridge the gap between data-driven predictions and mechanistic understanding, providing interpretable insights for the design of durable asphalt pavements and the optimization of maintenance strategies.

This research aims to develop a model and methodology for forecasting logarithmic returns (logreturns) for a new asset class of AI (Artificial Intelligence) tokens. To obtain one day ahead forecasts for the 0.9, 0.5, and 0.1 quantiles, the use of XGBoost quantile models is proposed, which represent an ensemble, based on gradient boosted regression trees. Quantile models have an advantage in terms of forecasting over traditionally used regression models because they allow for the estimation of not only point forecasts but also of their confidence intervals, while remaining robust to outliers. This is especially important when forming the forecasts for various cryptocurrencies’ market characteristics, which are known to be highly volatile. In addition to forecasting, the study conducts a post-forecast analysis using the SHAP (Shapley Additive explanations) method, which allows to interpret the XGBoost model, revealing key factors that are important for forecasting AI tokens’ logreturns. Based on the results of feature importance analysis with SHAP, a significant influence of AI stocks’ market characteristics, cryptocurrency market investor sentiment, seasonal fluctuations, as well as features related to the Blockchain ecosystem was identified. The paper also discusses and addresses the shortcomings of modern forecasting and post-forecasting analysis approaches for time series in general. The obtained results, in addition to academic interest, are relevant for private investors, risk managers, firms and regulators.

To construct machine learning prediction model for sepsis-associated encephalopathy (SAE), and analyze the application value of the model on early identification of SAE risk in elderly septic patients. Patients aged over 60 years with a primary diagnosis of sepsis admitted to intensive care unit (ICU) from 2008 to 2023 were selected from Medical Information Mart for Intensive Care-IV 2.2 (MIMIC-IV 2.2). Demographic variables, disease severity scores, comorbidities, interventions, laboratory indicators, and hospitalization details were collected. Key factors associated with SAE were identified using univariate Logistic regression analysis. The data were randomly divided into training and validation sets in a 7 : 3 ratio. Multivariable Logistic regression analysis was conducted in the training set and visualized using a nomogram model for prediction of SAE. The discrimination of the model was evaluated in the validation set using the receiver operator characteristic curve (ROC curve), and its calibration was assessed using calibration curve. Furthermore, multiple machine learning algorithms, including multi-layer perceptron (MLP), support vector machine (SVM), naive bayes (NB), gradient boosting machine (GBM), random forest (RF), and extreme gradient boosting (XGB), were constructed in the training set. Their predictive performance was subsequently evaluated on the validation set. Taking the XGB model as an example, the interpretability of the model through the SHapley Additive exPlanations (SHAP) algorithm was enhanced to identify the key predictive factors and their contributions. A total of 2 204 septic patients were finally enrolled, of whom 840 developed SAE (38.1%). A total of 21 variables associated with SAE were screened through univariate Logistic regression analysis. Multivariable Logistic regression analysis showed that endotracheal intubation [odds ratio (OR) = 0.40, 95% confidence interval (95%CI) was 0.19-0.88, P < 0.001], oxygen therapy (OR = 0.76, 95%CI was 0.53-0.95, P = 0.023), tracheotomy (OR = 0.20, 95%CI was 0.07-0.53, P < 0.001), continuous renal replacement therapy (CRRT; OR = 0.32, 95%CI was 0.15-0.70, P < 0.001), cerebrovascular disease (OR = 0.31, 95%CI was 0.16-0.60, P < 0.001), rheumatic disease (OR = 0.44, 95%CI was 0.19-0.99, P < 0.001), male (OR = 0.68, 95%CI was 0.54-0.86, P = 0.001), and maximum anion gap (AG; OR = 0.95, 95%CI was 0.93-0.97, P < 0.001) were associated with an decreased probability of SAE, and age (OR = 1.05, 95%CI was 1.03-1.06, P < 0.001), acute physiology score III (APSIII; OR = 1.02, 95%CI was 1.01-1.02, P < 0.001), Oxford acute severity of illness score (OASIS; OR = 1.04, 95%CI was 1.03-1.06, P < 0.001), and length of hospital stay (OR = 1.01, 95%CI was 1.01-1.02, P < 0.001) were associated with an increased probability of SAE. A nomogram model was constructed based on these variables. In the validation set, ROC curve analysis showed that the model achieved an area under the ROC curve (AUC) of 0.723, and the calibration curve showed good consistency between the predicted probability of the model and the observed probability. Among the machine learning algorithms, including MLP, SVM, NB, GBM, RF, and XGB, the SVM model and RF model demonstrated relatively good predictive performance, with AUC of 0.748 and 0.739, respectively, and the sensitivity was both exceeding 85%. The predictive performance of the XGB model was explained through SHAP analysis, and the results indicated that APSIII score (SHAP value was 0.871), age (SHAP value was 0.521), and OASIS score (SHAP value was 0.443) were important factors affecting the predictive performance of the model. The machine learning-based SAE prediction model exhibits good predictive capability and holds significant application value for the early identification of SAE risk in elderly septic patients.