Interpretable machine learning-based terrorist attack success rate prediction

PurposesRapid coronary artery lesions (RCAL) are strongly linked to major adverse cardiovascular events in patients with acute coronary syndrome (ACS). This work developed a public online prediction platform for RCAL (OpRCAL) by comparing the performance of nine machine learning models.MethodsWe retrospectively examined the clinical data of 324 patients with ACS who received percutaneous coronary intervention (PCI). Using both univariate and multivariate analyses, the potential independent risk factors for RCAL were studied. Following the screening of all variables using Lasso regression, multiple machine learning models were constructed. The optimal model was then chosen and validated using an external cohort. Furthermore, to elucidate the contribution of each feature to the model, the shapley additive explanation (SHAP) values of the variables were calculated. Finally, a prediction platform for RCAL in patients with ACS following PCI was established.ResultsThe number of coronary lesions, systolic blood pressure (SBP), N-terminal pro-brain natriuretic peptide (NT-proBNP), QRS interval, and platelet count were found as independent risk factors for RCAL. Among the nine machine learning models constructed after identifying twelve different variables using Lasso regression, the random forest (RF) model performed best in the training cohort and showed good generalization in the external test cohort, with area under curve of 0.774 (95%CI: 0.640–0.909). Finally, we constructed an online platform named OpRCAL for clinicians to predict RCAL in patients with ACS following PCI based on the RF model.ConclusionsThe RF model exhibits high accuracy and generalizability in predicting RCAL, thereby providing a valuable instrument to assist clinical decision-making.

Contributions of various driving factors to air pollution events: Interpretability analysis from Machine learning perspective

To predict the potential geographic distribution of Oncomelania hupensis in Yunnan Province using random forest (RF) and maximum entropy (MaxEnt) models, so as to provide insights into O. hupensis surveillance and control in Yunnan Province. The O. hupensis snail survey data in Yunnan Province from 2015 to 2016 were collected and converted into O. hupensis snail distribution site data. Data of 22 environmental variables in Yunnan Province were collected, including twelve climate variables (annual potential evapotranspiration, annual mean ground surface temperature, annual precipitation, annual mean air pressure, annual mean relative humidity, annual sunshine duration, annual mean air temperature, annual mean wind speed, ≥ 0 ℃ annual accumulated temperature, ≥ 10 ℃ annual accumulated temperature, aridity and index of moisture), eight geographical variables (normalized difference vegetation index, landform type, land use type, altitude, soil type, soil textureclay content, soil texture-sand content and soil texture-silt content) and two population and economic variables (gross domestic product and population). Variables were screened with Pearson correlation test and variance inflation factor (VIF) test. The RF and MaxEnt models and the ensemble model were created using the biomod2 package of the software R 4.2.1, and the potential distribution of O. hupensis snails after 2016 was predicted in Yunnan Province. The predictive effects of models were evaluated through cross-validation and independent tests, and the area under the receiver operating characteristic curve (AUC), true skill statistics (TSS) and Kappa statistics were used for model evaluation. In addition, the importance of environmental variables was analyzed, the contribution of environmental variables output by the models with AUC values of > 0.950 and TSS values of > 0.850 were selected for normalization processing, and the importance percentage of environmental variables was obtained to analyze the importance of environmental variables. Data of 148 O. hupensis snail distribution sites and 15 environmental variables were included in training sets of RF and MaxEnt models, and both RF and MaxEnt models had high predictive performance, with both mean AUC values of > 0.900 and all mean TSS values and Kappa values of > 0.800, and significant differences in the AUC (t = 19.862, P < 0.05), TSS (t = 10.140, P < 0.05) and Kappa values (t = 10.237, P < 0.05) between two models. The AUC, TSS and Kappa values of the ensemble model were 0.996, 0.954 and 0.920, respectively. Independent data verification showed that the AUC, TSS and Kappa values of the RF model and the ensemble model were all 1, which still showed high performance in unknown data modeling, and the MaxEnt model showed poor performance, with TSS and Kappa values of 0 for 24%(24/100) of the modeling results. The modeling results of 79 RF models, 38 MaxEnt models and their ensemble models with AUC values of > 0.950 and TSS values of > 0.850 were included in the evaluation of importance of environmental variables. The importance of annual sunshine duration (SSD) was 32.989%, 37.847% and 46.315% in the RF model, the MaxEnt model and their ensemble model, while the importance of annual mean relative humidity (RHU) was 30.947%, 15.921% and 28.121%, respectively. Important environment variables were concentrated in modeling results of the RF model, dispersed in modeling results of the MaxEnt model, and most concentrated in modeling results of the ensemble model. The potential distribution of O. hupensis snails after 2016 was predicted to be relatively concentrated in Yunnan Province by the RF model and relatively large by the MaxEnt model, and the distribution of O. hupensis snails predicted by the ensemble model was mostly the joint distribution of O. hupensis snails predicted by RF and MaxEnt models. Both RF and MaxEnt models are effective to predict the potential distribution of O. hupensis snails in Yunnan Province, which facilitates targeted O. hupensis snail control.

Simple SummaryThe objective response rate of lenvatinib combined with transarterial chemoembolization for unresectable hepatocellular carcinoma is unsatisfactory. We aimed to develop predictive models using demographic characteristics, pre-treatment serum biomarkers and tumor characteristics of unresectable hepatocellular carcinoma patients by five machine learning algorithms to predict the response under combined treatments. We identified the 10 most important predictors, including K, low-density lipoprotein, D-dimer, red blood cell, alanine aminotransferase, albumin, monocyte, tumor size, triglyceride, and age. In addition, we applied the Shapley Additive exPlanation to explain the best-performing random forest predictive model to provide a reasonable explanation of the efficacy prediction at an individualized level. The combination of machine learning and Shapley Additive exPlanation can provide valuable suggestions for clinical decision making.Background: Lenvatinib and transarterial chemoembolization (TACE) are first-line treatments for unresectable hepatocellular carcinoma (HCC), but the objective response rate (ORR) is not satisfactory. We aimed to predict the response to lenvatinib combined with TACE before treatment for unresectable HCC using machine learning (ML) algorithms based on clinical data. Methods: Patients with unresectable HCC receiving the combination therapy of lenvatinib combined with TACE from two medical centers were retrospectively collected from January 2020 to December 2021. The response to the combination therapy was evaluated over the following 4–12 weeks. Five types of ML algorithms were applied to develop the predictive models, including classification and regression tree (CART), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The performance of the models was assessed by the receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve (AUC). The Shapley Additive exPlanation (SHAP) method was applied to explain the model. Results: A total of 125 unresectable HCC patients were included in the analysis after the inclusion and exclusion criteria, among which 42 (33.6%) patients showed progression disease (PD), 49 (39.2%) showed stable disease (SD), and 34 (27.2%) achieved partial response (PR). The nonresponse group (PD + SD) included 91 patients, while the response group (PR) included 34 patients. The top 40 most important features from all 64 clinical features were selected using the recursive feature elimination (RFE) algorithm to develop the predictive models. The predictive power was satisfactory, with AUCs of 0.74 to 0.91. The SVM model and RF model showed the highest accuracy (86.5%), and the RF model showed the largest AUC (0.91, 95% confidence interval (CI): 0.61–0.95). The SHAP summary plot and decision plot illustrated the impact of the top 40 features on the efficacy of the combination therapy, and the SHAP force plot successfully predicted the efficacy at the individualized level. Conclusions: A new predictive model based on clinical data was developed using ML algorithms, which showed favorable performance in predicting the response to lenvatinib combined with TACE for unresectable HCC. Combining ML with SHAP could provide an explicit explanation of the efficacy prediction.

The study aimed to develop and externally validate multiparametric MRI (mpMRI) radiomics-based interpretable machine learning (ML) model for preoperative differentiating between benign and malignant prostate masses. Patients who underwent mpMRI with suspected malignant prostate masses were retrospectively recruited from two independent hospitals between May 2016 and May 2023. The prostate mass regions in T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) MRI images were segmented by ITK-SNAP. PyRadiomics was utilized to extract radiomic features. Inter- and intraobserver correlation analysis, t-test, Spearman correlation analysis, and the least absolute shrinkage and selection operator (LASSO) algorithm with a five-fold cross-validation were applied for feature selection. Five ML learning models were built using the chosen features. Model performance was evaluated with internal and external validation, using area under the curve (AUC), calibration curves, and decision curve analysis to select the optimal model. The interpretability of the most robust model was conducted via SHapley Additive exPlanation (SHAP). A total of 567 patients were enrolled, consisting of the training (n = 352), internal test (n = 152), and external test (n = 63) sets. In total, 2,632 radiomic features were extracted from regions of interest (ROIs) of T2WI and DWI images, which were reduced to 18 via LASSO. Five ML models were established, among which the random forest (RF) model presented the best predictive ability, with AUCs of 0.929 (95% confidential interval [CI]: 0.885-0.963) and 0.852 (95% CI: 0.758-0.934) in the internal and external test sets, respectively. The calibration and decision curve analyses confirmed the excellent clinical usefulness of the RF model. Besides, the contributing relations of the radiomic features were uncovered using SHAP. Radiomic features from mpMRI combined with machine learning facilitate accurate preoperative evaluation of the malignancy in prostate masses. SHAP can disclose the underlying prediction process of the ML model, which may promote its clinical applications.

• ML models for predicting SCM concretes compressive strength developed • Multiple datasets devised from a global dataset were used for training • Multiple ML models used in conjunction with multiple datasets for best results • Accurate prediction results obtained for all SCM concrete types studied • Prediction uncertainty bounds established by conformal prediction analysis Supplementary cementitious materials (SCM) used as partial replacements of cement can reduce carbon emissions and construction costs. The amount and types of SCM used directly influence the compressive strength of concrete, which is a crucial indicator of concrete performance. However, predicting compressive strength is challenging for SCM-based concretes due to their complex compositions, especially when multiple types of SCM are used. This study used five machine learning (ML) models, namely artificial neural network (ANN), random forest (RF), extra trees (ET), extreme gradient boosting (XGB), and adaptive boosting (AdaBoost) to predict the 28-day compressive strength of SCM concretes incorporating fly ash (FA), silica fume (SF), and ground granulated blast furnace slag (GGBFS). Firstly, a global dataset comprising 1456 data points was organized into seven individual and six combined datasets for training of the five ML models. After this, the performances of the ML models’ predictions using individual and combined datasets were compared using root mean squared error (RMSE) and coefficient of determination (R 2 ) to identify the optimal ML model-dataset configurations for each type of SCM-based concrete. It is found that in general, XGB models developed using the combined datasets demonstrated superior prediction accuracy, achieving an R² value exceeding 0.8. Both Shapley Additive Explanation (SHAP) and partial dependence plots (PDPs) were employed to illustrate the effects of input variables on compressive strength. Finally, uncertainty quantification using the Jackknife method combined with a normalized nonconformity measure was employed to provide accurate uncertainty bounds for compressive strength predictions.

The nonlinearity of hedonic datasets demands flexible automated valuation models to appraise housing prices accurately, and artificial intelligence models have been employed in mass appraisal to this end. However, they have been referred to as “black-box” models owing to difficulties associated with interpretation. In this study, we compared the results of traditional hedonic pricing models with those of machine learning algorithms, e.g., random forest and deep neural network models. Commonly implemented measures, e.g., Gini importance and permutation importance, provide only the magnitude of each explanatory variable’s importance, which results in ambiguous interpretability. To address this issue, we employed the SHapley Additive exPlanation (SHAP) method and explored its effectiveness through comparisons with traditionally explainable measures in hedonic pricing models. The results demonstrated that (1) the random forest model with the SHAP method could be a reliable instrument for appraising housing prices with high accuracy and sufficient interpretability, (2) the interpretable results retrieved from the SHAP method can be consolidated by the support of statistical evidence, and (3) housing characteristics and local amenities are primary contributors in property valuation, which is consistent with the findings of previous studies. Thus, our novel methodological framework and robust findings provide informative insights into the use of machine learning methods in property valuation based on the comparative analysis.

The rapid popularization of unmanned aerial vehicles (UAVs; also referred to as drones), in both the recreational and industrial sectors, has paved the way for rapid developments in drone capabilities. Although the threat of UAVs used by terrorists has been recognized by specialists in both Counter-Terrorism and Counter-Terrorism Medicine (CTM), there are limited data on the extent and characteristics of drone use by terrorist organizations. Data collection was performed using a retrospective database search through the Global Terrorism Database (GTD). The GTD was searched using the internal database search functions for all terrorist attacks using UAVs from January 1, 1970 - December 31, 2019. Years 2020 and 2021 were not yet available at the time of the study. Primary weapon type, number and type of UAVs used, related attacks, location (country, world region), and number of deaths and injuries were collated. Results were exported into an Excel spreadsheet (Microsoft Corp.; Redmond, Washington USA) for analysis. There were 76 terrorist attacks using UAVs. The first attack occurred in 2016, and the number of attacks per year varied considerably (range: 4-36). Forty-seven of the 76 attacks (70%) were successful. Twenty-seven individually listed events (36%) were related and part of nine coordinated, multi-part incidents. A total of 50 deaths and 132 injuries were recorded, which equated to 1.09 deaths (range: 0-6) and 2.89 injuries (range: 0-20) per successful attack. The mean number of UAVs used in an attack was 1.28 (range: 1-5) and multiple UAVs were used in 22% of attacks. The use of UAVs to carry out terrorist attacks is on the rise. Seventy-six terrorist attacks using this novel method were recorded since 2016, killing 50 and injuring 132 people. While the use of UAV-related explosives appears less lethal than traditional explosive attacks, advancing technologies and swarming capabilities, increasing ability to carry larger payloads, and the possibility of UAVs to disperse chemical, biological, radiological, and nuclear (CBRN) weapons will likely increase UAV lethality in the future, requiring CTM specialists be more proactive.

Autism spectrum disorder (ASD) is a multifaceted neurodevelopmental condition that affects millions of individuals globally. This study leverages the publicly available UCI Machine Learning ASD Screening Dataset, which contains behavioral questionnaire responses from children aged 4-11 years, to develop and compare multiple machine learning (ML) models for early ASD diagnosis. This study applies SHAP (SHapley Additive exPlanations) to interpret and analyze the feature importance of various attributes in the dataset. Advanced ML models like Extreme Gradient Boosting (XGBoost), Random Forest (RF), Extra Trees Classifier (ETC), Support Vector Machines (SVM), and Multilayer Perceptrons (MLPs) were implemented to evaluate and compare their performance in predicting early ASD. The developed ASD model underwent a rigorous evaluation through comprehensive performance metrics, including accuracy, precision, recall, F1-score, specificity, and Matthews correlation coefficient. Ranking-based metrics, such as area under the receiver operating characteristic curve (AUROC), provided additional insights into classification robustness, while 10-fold cross-validation ensured reliability and generalizability. Results indicate that XGBoost achieved the highest diagnostic performance (accuracy = 97.8%, AUROC = 0.99), followed closely by MLP, with RF and ETC offering balanced performance and interpretability. SHAP analysis identified key behavioral features influencing model predictions, enabling explainable AI-driven insights. These findings suggest that ML-based tools can support clinicians in identifying ASD earlier, allowing for timelier interventions in disability services, particularly in underserved populations. While results are promising, the use of secondary data and the lack of clinical validation remain limitations, highlighting the need for real-world pilot testing. These findings underscore the transformative potential of ML techniques in enhancing ASD diagnostics. Despite their promise, the results are constrained by reliance on secondary data and the absence of clinical validation, underscoring the need for real-world pilot testing. Nonetheless, incorporating these models into clinical practice could accelerate early detection, facilitate personalized interventions, and optimize resource allocation for improved ASD management outcomes.

The shear behaviour of Ultra High-Performance Fiber Reinforced Concrete (UHPFRC) is complex due to fiber contributions alongside conventional reinforcement and concrete effects. This paper presents a novel Machine Learning (ML) approach to predict the shear capacity of UHPFRC beams, offering an alternative to conventional empirical and analytical methods. A database of 282 experimental data points was used to train multiple ML models, including Support Vector Regression (SVR), k-Nearest Neighbour (kNN), Decision Tree Regressor (DTR), Random Forest Regressor (RFR), Artificial Neural Network (ANN), Gradient Boosting Regressor (GBR), Light Gradient Boosting Regressor (LGBR), and Extreme Gradient Boosting Regressor (XGBR). Among these, boosting-based models performed best, with XGBR achieving the highest accuracy with an R 2 score of 0.91. Further, a feature importance analysis identified the shear span-to-depth ratio as the most influential parameter on the shear capacity, with longitudinal and transverse reinforcement ratios also playing key roles. A SHapley Additive exPlanation (SHAP) analysis was conducted, offering an interpretable framework for understanding the contribution of each feature to the model’s prediction. This analysis further clarified feature contributions, identifying optimal parameter ranges for shear capacity. This data-driven approach bridges empirical methods and computational modelling enhancing confidence in ML-based predictions and guiding efficient UHPFRC design.

A robust predictive diagnosis model for diabetes mellitus using Shapley-incorporated machine learning algorithms

This study aimed to apply four machine learning algorithms to develop the optimal model to predict decline in platelet count (DPC) after interventional closure in children with patent ductus arteriosus (PDA). Data from children with PDA who underwent successful transcatheter closure at the Second Affiliated Hospital of Wenzhou Medical University and Yuying Children's Hospital from January 2016, to December 2022, were collected. The cohort data were split into training and testing sets. DPC following the intervention is defined as a percentage DPC ≥25% [(baseline platelet count-nadir platelet count)/baseline platelet count]. The extra tree algorithm was used for feature selection and four ML algorithms [random forest (RF), adaptive boosting, extreme gradient boosting, and logistic regression] were established. Moreover, SHapley Additive exPlanation (SHAP) to explain the importance of features and the ML models. This study included 330 children who underwent successful transcatheter closure of PDA, of which 113 (34.2%) experienced DPC. After 62 clinical features were considered, the extra tree algorithm selected six clinical features to build the ML models. Amongst the four ML algorithms, the RF model achieved the greatest AUC. SHAP analysis revealed that pulmonary artery systolic pressure, size of defect and weight were the top three most important clinical features in the RF model. Furthermore, clinical descriptions of two children with PDA, with accurate predictions, and explanations of the prediction results were provided. In this study, an ML model (RF) capable of predicting post-intervention DPC in children with PDA undergoing transcatheter closure was established.

Risk assessment and categorization of terrorist attacks can assist enhance awareness of terrorism and give crucial information support for anti-terrorism efforts. This study utilizes quantitative approaches for the risk assessment and categorization of terrorist attacks. A total of 210,454 terrorist attacks that occurred worldwide from 1970 through 2020 were collected in the Global Terrorism Database, and 22 indicators related to the risk of terrorist attacks were selected. Then, the moment estimation theory and four comprehensive evaluation models were utilized to identify the top 10 riskiest terrorist attacks in the world. Furthermore, the five clustering analysis methods and three evaluation criteria were performed for the risk categorization of terrorist attacks, and the visual analysis was carried out using the kernel density estimation method. The research results have identified the top 10 riskiest global terrorist attacks, which were led by the September 11 terrorist attack event, along with their downward counterfactual events. The spatial distribution of global terrorist attack risk is primarily composed of four “turbulent cores” in the region of Central Asia, Middle East & North Africa, South Asia, and Central America & Caribbean. This study also provided insights and recommendations for anti-terrorism efforts. It has realized the risk assessment and categorization of terrorist attacks, aiding in the swift identification of its risk levels, and holds immense significance for safeguarding global national security and societal stability under new circumstances.

Diabetes is a chronic hyperglycemic disease caused by insufficient insulin secretion. Traditional diagnostic methods cannot provide early prevention, while data-driven machine learning methods can analyze medical data for early prediction. This study employs four machine learning algorithms—Logistic Regression, Support Vector Machine, Decision Tree, and Random Forest—to analyze and model relevant data. By comparing model performance indicators such as accuracy and recall, it was found that the Random Forest model performs better overall. Using SHAP waterfall and beeswarm plots further to explain the prediction results of the Random Forest model and comparing these results with the variable importance ranking within the Random Forest, it was discovered that Serum Creatinine, Blood Urea, Triglycerides, and Hemoglobin are the most significant factors contributing to diabetes. This finding suggests that these factors should be the focus in predicting the risk of diabetes onset.

BackgroundLumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.MethodsWe utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.ResultsIn the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.ConclusionsThe RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.