Characterizing Uncertainty in Deep Convection Triggering Using Explainable Machine Learning

Development and validation of an explainable machine learning model for mortality prediction among patients with infected pancreatic necrosis.

Sudden Sensorineural Hearing Loss (SSNHL) is routinely encountered in otolaryngology clinics. The prognosis of SSNHL varies dramatically and depends on multiple influence factors. This study aimed to develop an explainable Machine Learning (ML) model with easily accessible features to predict the prognosis of SSNHL. This bi-center retrospective study included 534 patients with SSNHL. We randomly split the data into training and validation sets. Univariate analysis and Least Absolute Shrinkage and Selection Operator (LASSO) regression were employed to select predominant features, including demographic, disease-specific characteristics, and laboratory items. We evaluated the performance of five ML models constructed with six crucial variables using the Area Under the receiver operating characteristic Curve (AUC), accuracy, specificity, sensitivity, and F1 scores. These models were further calibrated by calibration curve and Brier score. Clinical utility was evaluated by Decision Curve Analysis (DCA). The Shapley Additive Explanations (SHAP) method was applied to interpret feature contribution and explain the ML models. The Random Forest (RF) model reached the highest AUC of 0.998. Its accuracy, sensitivity, specificity, and F1 score were 0.981, 0.963, 0.989, and 0.967, respectively. DCA curve analysis revealed a comparable net benefit of the models. The SHAP method revealed that the primary features were degree of hearing loss, audiogram type, age, Mean Corpuscular Volume (MCV), onset to treatment, and serum Albumin (ALB) accordingly. The explainable ML model was superb in predicting hearing outcome and providing information on feature contributions. Clinicians can better understand the contributors to hearing recovery and guide aural rehabilitation using the SHAP method. Level 3.

Objective: This study aims to utilize an explainable machine learning framework to identify and rank the critical protective factors that buffer against the deleterious effects of specific childhood trauma subtypes on adolescent resilience within low-socioeconomic Iraqi contexts. Methods and Materials: A cross-sectional design was employed with a sample of adolescents (mean age years; female) from low-socioeconomic districts in Iraq. Data were collected using culturally adapted and validated instruments, including the Childhood Trauma Questionnaire-Short Form (CTQ-SF), the Connor-Davidson Resilience Scale (CD-RISC), and the Resilience Scale for Adolescents (READ). To analyze the complex, non-linear relationships between variables, an eXtreme Gradient Boosting (XGBoost) machine learning model was developed. The model’s interpretability was enhanced using SHapley Additive exPlanations (SHAP) to calculate the global predictive importance and interaction effects of specific risk and protective factors. Findings: The XGBoost model demonstrated robust predictive performance, explaining a significant portion of the variance in adolescent resilience ( , ). SHAP value analysis revealed that Family Cohesion emerged as the paramount protective factor (SHAP ), while Emotional Abuse (SHAP ) and Emotional Neglect (SHAP ) were identified as the most detrimental risk factors, surpassing physical and sexual abuse in predictive weight. Furthermore, a critical non-linear threshold effect was discovered: the protective utility of peer support increased significantly only when emotional neglect scores were below a specific clinical threshold (CTQ-SF ). Conclusion: Explainable machine learning provides granular insights into trauma recovery, highlighting that emotional maltreatment profoundly damages adolescent adaptation. Interventions in low-resource settings must prioritize systemic family-based therapies to foster cohesion and adopt a phased clinical approach that addresses foundational emotional neglect before introducing peer-based support systems.

Deficiencies in convection trigger functions, used in deep convection parameterizations in General Circulation Models (GCMs), have critical impacts on climate simulations. A novel convection trigger function is developed using the machine learning (ML) classification model XGBoost. The large‐scale environmental information associated with convective events is obtained from the long‐term constrained variational analysis forcing data from the Atmospheric Radiation Measurement (ARM) program at its Southern Great Plains (SGP) and Manaus (MAO) sites representing, respectively, continental mid‐latitude and tropical convection. The ML trigger is separately trained and evaluated per site, and jointly trained and evaluated at both sites as a unified trigger. The performance of the ML trigger is compared with four convective trigger functions commonly used in GCMs: dilute convective available potential energy (CAPE), undilute CAPE, dilute dynamic CAPE (dCAPE), and undilute dCAPE. The ML trigger substantially outperforms the four CAPE‐based triggers in terms of theF1 score metric, widely used to estimate the performance of ML methods. The site‐specific ML trigger functions can achieve, respectively, 91% and 93%F1 scores at SGP and MAO. The unified trigger also has a 91%F1 score, with virtually no degradation from the site‐specific training, suggesting the potential of a global ML trigger function. The ML trigger alleviates a GCM deficiency regarding the overprediction of convection occurrence, offering a promising improvement to the simulation of the diurnal cycle of precipitation. Furthermore, to overcome the black box issue of the ML methods, insights derived from the ML model are discussed, which may be leveraged to improve traditional CAPE‐based triggers.

Objectives: The early detection of low bone mineral density (BMD) is essential for preventing osteoporosis and related complications. While dual-energy X-ray absorptiometry (DXA) remains the gold standard for diagnosis, its cost and limited availability restrict its use in large-scale screening. This study investigated whether raw bioelectrical impedance analysis (BIA) data combined with explainable machine learning (ML) models could accurately classify osteopenia in women aged 40 to 55. Methods: In a cross-sectional design, 138 women underwent same-day BIA and DXA assessments. Participants were categorized as osteopenic (T-score between −1.0 and −2.5; n = 33) or normal (T-score ≥ −1.0) based on DXA results. Overall, 24.1% of the sample were classified as osteopenic, and 32.85% were postmenopausal. Raw BIA outputs were used as input features, including impedance values, phase angles, and segmental tissue parameters. A sequential forward feature selection (SFFS) algorithm was employed to optimize input dimensionality. Four ML classifiers were trained using stratified five-fold cross-validation, and SHapley Additive exPlanations (SHAP) were applied to interpret feature contributions. Results: The neural network (NN) model achieved the highest classification accuracy (92.12%) using 34 selected features, including raw impedance measurements, derived body composition indices such as regional lean mass estimates and the edema index, as well as a limited number of categorical variables, including self-reported physical activity status. SHAP analysis identified muscle mass indices and fluid distribution metrics, features previously associated with bone health, as the most influential predictors in the current model. Other classifiers performed comparably but with lower precision or interpretability. Conclusions: ML models based on raw BIA data can classify osteopenia with high accuracy and clinical transparency. This approach provides a cost-effective and interpretable alternative for the early identification of individuals at risk for low BMD in resource-limited or primary care settings.

This study focuses on using various machine learning (ML) models to evaluate the shear behaviors of ultra-high-performance concrete (UHPC) beams reinforced with glass fiber-reinforced polymer (GFRP) bars. The main objective of the study is to predict the shear strength of UHPC beams reinforced with GFRP bars using ML models. We use four different ML models: support vector machine (SVM), artificial neural network (ANN), random forest (R.F.), and extreme gradient boosting (XGBoost). The experimental database used in the study is acquired from various literature sources and comprises 54 test observations with 11 input features. These input features are likely parameters related to the composition, geometry, and properties of the UHPC beams and GFRP bars. To ensure the ML models' generalizability and scalability, random search methods are utilized to tune the hyperparameters of the algorithms. This tuning process helps improve the performance of the models when predicting the shear strength. The study uses the ACI318M-14 and Eurocode 2 standard building codes to predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams. The ML models' predictions are compared to the results obtained from these building code standards. According to the findings, the XGBoost model demonstrates the highest predictive test performance among the investigated ML models. The study employs the SHAP (SHapley Additive exPlanations) analysis to assess the significance of each input parameter in the ML models' predictive capabilities. A Taylor diagram is used to statistically compare the accuracy of the ML models. This study concludes that ML models, particularly XGBoost, can effectively predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams.

Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak

12074 Background: Skeletal-related events (SREs) are detrimental clinical events in bone metastasis from advanced cancer, defined by pathologic fracture, spinal cord compression, and inevitable surgical or radiational intervention to the bone. Given their negative impact on quality of life and prognosis and interpatient heterogeneity in the SRE risk, accurate identification of patients with high SRE risk is critical. Methods: The patient-level data from three randomized clinical trials that administered zoledronic acid (ZA) to patients with bone-metastatic breast cancer, castration-resistant prostate cancer (CRPC), and other types of cancer were analyzed. (N = 460, 452, and 315, respectively) Machine learning (ML) models to predict SREs within 18 months (breast cancer), 12 months (CRPC), and 9 months (other cancers) were developed based on more than 40 baseline clinical and laboratory data. Seven ML algorithms and five feature selection methods were utilized to develop multiple models. The ML model with the best performance was identified based on the F1 score and the area under the receiver operating characteristic curve (AUC-ROC) for each cancer type and interrogated for important features with Shapley additive explanations. Lastly, the ML models’ ability to stratify patients by the cumulative SRE risk was evaluated by calculating hazard ratio (HR) with Cox-proportional hazards models. Results: Among the multiple ML models developed with different algorithms and feature selection methods, the model developed utilizing the random forests algorithm and the Boruta method for selecting features demonstrated the best performance in all types of cancer (F1 0.70, 0.67, and 0.67, and AUC-ROC 0.72, 0.68, and 0.73 for breast cancer, CRPC, and other cancers, respectively). In the ML model for breast cancer, performance status (PS), history of SRE, serum alkaline phosphatase (ALP), history of anti-neoplastic surgery, radiation therapy, and pathologic fracture were included as important features. Serum ALP, albumin, sodium, Gleason scores, and geographic regions were shown to be relevant in the CRPC model. For other cancers, serum ALP, albumin, total protein, phosphorus, red blood cell count, white blood cell count, visceral metastases, and history of arthritis were incorporated in the ML model. The ML model prediction successfully stratified the patients for cumulative SRE risk in all three cohorts. (HR with 95% confidence interval: 2.43 [1.86 – 3.18], 1.92 [1.51 – 2.45], and 3.06 [2.29 – 4.09] for breast cancer, CRPC, and other types of cancer, respectively). Conclusions: ML models incorporating baseline clinical and laboratory data can identify patients with bone metastasis on ZA harboring a high SRE risk.

Single-center, retrospective cohort study. Data from the Virtual Pediatric Systems for patients admitted to Cleveland Clinic Children`s PICU between January 2008 and December 2019 was obtained. Light Gradient Boosting Machine Regressor (a gradient boosting decision tree algorithm) was used for building the machine learning models. Variable importance was analyzed by SHapley Additive exPlanations. All of the 11 Pediatric Index of Mortality 3 variables were used as input variables in the machine learning models to predict Pediatric Index of Mortality 3 risk of mortality as the outcome variable. Mean absolute error, root mean squared error, and R-squared were calculated for each of the 11 machine learning models as model performance parameters. Quaternary children's hospital. PICU patients. None. Five-thousand sixty-eight patients were analyzed. The machine learning models were able to maintain similar predictive error until the number of input variables decreased to four. The machine learning model with five input variables (mechanical ventilation in the first hour of PICU admission, very-high-risk diagnosis, surgical recovery from a noncardiac procedure, low-risk diagnosis, and base excess) produced lowest mean root mean squared error of 1.49 (95% CI, 1.05-1.93) and highest R-squared of 0.73 (95% CI, 0.6-0.86) with mean absolute error of 0.43 (95% CI, 0.35-0.5) among all the 11 machine learning models. Explainable machine learning methods were feasible in simplifying the Pediatric Index of Mortality 3 scoring system with similar risk of mortality predictions compared to the original Pediatric Index of Mortality 3 model tested in a single-center dataset.

The accurate detection and assessment of stress play a pivotal role in enhancing individual well-being and healthcare outcomes. Traditional methods of stress detection often grapple with limitations in accuracy and scalability. With the advent of machine learning (ML), the potential to revolutionize stress detection has emerged. This paper presents a comprehensive study on the application of ML algorithms for stress detection, with a focus on physiological and behavioral data analysis. Central to our approach is the integration of SHapley Additive exPlanations (SHAP), an Explainable Artificial Intelligence (XAI) technique, to interpret ML models. SHAP provides a novel lens to understand the impact of individual features in the complex decision-making processes of ML models, thereby enhancing the transparency and reliability of stress predictions. We demonstrate how SHAP not only aids in elucidating model decisions but also contributes to refining the models for greater accuracy. Our results highlight the effectiveness of ML in detecting stress and the pivotal role of XAI in making these models more interpretable and trustworthy. This study underscores the synergy between advanced ML techniques and XAI, paving the way for more nuanced and reliable stress detection methodologies that are essential in diverse settings, from healthcare to workplace environments.

Chronic pain around the temporomandibular joint (TMJ) and masticatory muscles is a primary symptom of temporomandibular disorders (TMD). However, the clinical significance of magnetic resonance imaging (MRI) features in predicting TMD-related pain remains unclear. This study aimed to develop and interpret machine learning (ML) models based on MRI characteristics for predicting pain severity in patients with TMD. The present retrospective study included 584 patients with TMD between January 2022 and December 2024, yielding a total of 755 TMJ MRI data sets. Pain severity was classified using the visual analogue scale (VAS). Demographic variables (age, sex) and MRI features-including lesion side, disc position, disc morphology, disc signal, disc perforation, bilaminar zone tear, joint space, joint effusion, condylar movement, bony changes and morphology/signal of the lateral pterygoid muscle-were collected. Eleven ML models based on demographic and MRI features were developed: logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), adaptive boosting (AdaBoost), gradient boosting classifier (GBC), bagging classifier (BC), extremely randomised trees (ETC), decision tree classifier (DTC) and multilayer perceptron (MLP). Model performance was evaluated using multiple metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity and F1 score. Precision-recall (PR) curves and calibration curves were plotted to assess discrimination and model calibration. Decision curve analysis (DCA) was conducted to evaluate the clinical net benefit across a range of threshold probabilities. Model interpretability was enhanced using Shapley Additive Explanations (SHAP), which quantified the contribution of each feature to individual predictions. Feature selection was conducted based on mean SHAP values, and separate LightGBM models were constructed using the Top 3, 5, and 9 most important features, as well as the full-feature set, for performance comparison. The data set was randomly divided into a training set (n = 604) and a test set (n = 151). Among the 11 ML models, the LightGBM model demonstrated the best predictive performance, with an AUC of 0.899, and was therefore identified as the optimal model. SHAP analysis identified age, disc position and condylar movement as the top three contributing features. Feature selection analysis indicated that selecting the top nine SHAP-ranked variables led to the highest diagnostic performance, with an AUC of 0.829. This study developed an interpretable, high-performing MRI-based ML model incorporating SHAP analysis to integrate imaging and clinical features for objective pain assessment, which may help identify high-risk TMD patients and guide personalised treatment strategies.

Urban flooding has emerged as one of the most critical challenges in rapidly developing cities, driven by climate change, intense rainfall events, and increasing land-use pressures. Accurate flood hazard mapping is essential for informed urban planning and disaster risk reduction, yet traditional approaches often face limitations in capturing complex hydrodynamic processes and ensuring interpretability for decision-makers. This study presents an integrated methodology that combines two-dimensional HEC-RAS hydrodynamic modelling with explainable machine learning (XAI) techniques for flood hazard zonation in urban watersheds. The HEC-RAS model successfully simulated flood depths and flow velocities, validated against observed data with a strong correlation coefficient (R2 = 0.92) and low error indices. Machine learning models were tested using rainfall intensity, land use, slope, and proximity to rivers as predictors, with Random Forest achieving the highest performance (91% accuracy). To address the ‘black-box’ limitation, Shapley Additive Explanations (SHAP) were applied, identifying rainfall intensity and river proximity as the most significant drivers of flood risk. An integrated hazard map was developed by combining hydrodynamic outputs with Random Forest predictions. Validation against historical flood records yielded an overall accuracy of 89% and a Kappa statistic of 0.84, confirming the robustness of the approach. Sensitivity and statistical analyses further highlighted the impacts of rainfall variability and land-use change on flood susceptibility. The findings demonstrate that integrating hydrodynamic modelling with explainable AI enhances the accuracy, interpretability, and practical utility of flood hazard mapping, offering a valuable framework for urban planners and policymakers in managing flood risks under dynamic climate and land-use scenarios.

The number of deaths from cardiovascular disease is projected to reach 23.3 million by 2030. As a contribution to preventing this phenomenon, this paper proposed a machine learning (ML) model to predict patients with arteriosclerotic heart disease (AHD). We also interpreted the prediction model results based on the ML approach and deployed modelagnostic ML methods to identify informative features and their interpretations. We used a hematology Electronic Health Record (EHR) with information on erythrocytes, hematocrit, hemoglobin, mean corpuscular hemoglobin, mean corpuscular hemoglobin concentration, leukocytes, thrombocytes, age, and sex. To detect and predict AHD, we explored random forest (RF), XGBoost, and AdaBoost models. We examined the prediction model results based on the confusion matrix and accuracy measures. We used the Shapley Additive exPlanations (SHAP) framework to interpret the ML model and quantify the contribution of features to predictions. Our study included data from 6,837 patients, with 4,702 records from patients diagnosed with AHD and 2,135 records from patients without an AHD diagnosis. AdaBoost outperformed RF and XGBoost, achieving an accuracy of 0.78, precision of 0.82, F1-score of 0.85, and recall of 0.88. According to the SHAP summary bar plot method, hemoglobin was the most important attribute for detecting and predicting AHD patients. The SHAP local interpretability bar plot revealed that hemoglobin and mean corpuscular hemoglobin concentration had positive impacts on AHD prediction based on a single observation. ML models based on real clinical data can be used to predict AHD.

The abundant post-earthquake data from the Canterbury, New Zealand (NZ) area is poised for use with machine learning (ML) to further advance our ability to better predict and understand the effects of liquefaction. Liquefaction manifestation is one of the identifiable effects of liquefaction, a nonlinear phenomenon that is still not well understood. ML algorithms are often termed as “black-box” models that have little to no explainability for the resultant predictions, making them difficult for use in practice. With the SHapley Additive exPlanations (SHAP) algorithm wrapper, mathematically backed explanations can be fit to the model to track input feature influences on the final prediction. In this paper, Random Forest (RF) is chosen as the ML model to be utilized as it is a powerful non-parametric classification model, then SHAP is applied to calculate explanations for the predictions at a global and local feature scale. The RF model hyperparameters are optimized with a two-step grid search and a five-fold cross-validation to avoid overfitting. The overall model accuracy is 71% over six ordinal categories predicting the Canterbury Earthquake Sequence measurements from 2010, 2011, and 2016. Insights from the SHAP application onto the RF model include the influences of PGA, GWT depths, and SBTs for each ordinal class prediction. This preliminary exploration using SHAP can pave the way for both reinforcing the performance of current ML models by comparing to previous knowledge and using it as a discovery tool for identifying which research areas are pertinent to unlocking more understanding of liquefaction mechanics.

Machine learning (ML) techniques allow for finding hidden patterns and signatures in data. Currently, these methods are gaining increased interest in engineering in general and in vibroacoustics in particular. Although ML methods are successfully applied, it is hardly understood how these black box-type methods make their decisions. Explainable machine learning aims at overcoming this issue by deepening the understanding of the decision-making process through perturbation-based model diagnosis. This paper introduces machine learning methods and reviews recent techniques for explainability and interpretability. These methods are exemplified on sound absorption coefficient spectra of one sound absorbing foam material measured in an impedance tube. Variances of the absorption coefficient measurements as a function of the specimen thickness and the operator are modeled by univariate and multivariate machine learning models. In order to identify the driving patterns, i.e. how and in which frequency regime the measurements are affected by the setup specifications, Shapley additive explanations are derived for the ML models. It is demonstrated how explaining machine learning models can be used to discover and express complicated relations in experimental data, thereby paving the way to novel knowledge discovery strategies in evidence-based modeling.