Search

This paper proposes an interpretation methodology for the effect of transient process data on quality of injection molded parts. The transient process data measured in the actual processing space have been regarded as the most relevant information to manufacturing processes and product quality. However, its interpretation to pinpoint which feature in the data would affect part quality has traditionally relied on knowledge and understanding of the manufacturing process. The main objective of this method is to reduce the dependency of the transient process data analysis on process knowledge and understanding by using explainable artificial intelligence (XAI). The contribution of the 'section-wise' features in the transient process data to the quality prediction of machine learning (ML) models was investigated for the first time. The interpretation results of the effect of cavity pressure and mold surface temperature on four different quality factors represented reasonable explanations of the characteristics of the polymer materials, product geometry, and molding process. Due to the intermediate relationship of the transient process data with the user-specified process parameters and the resulting quality variables, the interpretation results can be further utilized to optimize the process and provide the optimal transient process data profile for best part quality. [ABSTRACT FROM AUTHOR]

Examining the game-changing possibilities of explainable machine learning techniques, this study explores the fast-growing area of biochar production prediction. The paper demonstrates how recent advances in sensitivity analysis methodology, optimization of training hyperparameters, and state-of-the-art ensemble techniques have greatly simplified and enhanced the forecasting of biochar output and composition from various biomass sources. The study argues that white-box models, which are more open and comprehensible, are crucial for biochar prediction in light of the increasing suspicion of black-box models. Accurate forecasts are guaranteed by these explainable AI systems, which also give detailed explanations of the mechanisms generating the outcomes. For prediction models to gain confidence and for biochar production processes to enable informed decision-making, there must be an emphasis on interpretability and openness. The paper comprehensively synthesizes the most critical features of biochar prediction by a rigorous assessment of current literature and relies on the authors' own experience. Explainable machine learning techniques encourage ecologically responsible decision-making by improving forecast accuracy and transparency. Biochar is positioned as a crucial participant in solving global concerns connected to soil health and climate change, and this ultimately contributes to the wider aims of environmental sustainability and renewable energy consumption. [ABSTRACT FROM AUTHOR]

To learn about real world phenomena, scientists have traditionally used models with clearly interpretable elements. However, modern machine learning (ML) models, while powerful predictors, lack this direct elementwise interpretability (e.g. neural network weights). Interpretable machine learning (IML) offers a solution by analyzing models holistically to derive interpretations. Yet, current IML research is focused on auditing ML models rather than leveraging them for scientific inference. Our work bridges this gap, presenting a framework for designing IML methods—termed ’property descriptors’—that illuminate not just the model, but also the phenomenon it represents. We demonstrate that property descriptors, grounded in statistical learning theory, can effectively reveal relevant properties of the joint probability distribution of the observational data. We identify existing IML methods suited for scientific inference and provide a guide for developing new descriptors with quantified epistemic uncertainty. Our framework empowers scientists to harness ML models for inference, and provides directions for future IML research to support scientific understanding. [ABSTRACT FROM AUTHOR]

In engineering design, global sensitivity analysis (GSA) is used for analyzing the effects of inputs on the system response and is commonly studied with analytical or surrogate models. However, such models fail to capture nonlinear behaviors in complex systems and involve several modeling assumptions. Besides model-focused methods, a data-driven GSA approach, rooted in interpretable machine learning, would also identify the relationships between system components. Moreover, a special need in engineering design extends beyond performing GSA for input variables individually, but instead evaluating the contributions of variable groups on the system response. In this article, we introduce a flexible, interpretable artificial neural network model to uncover individual as well as grouped global sensitivity indices for understanding complex physical interactions in engineering design problems. The proposed model allows the investigation of the main effects and second-order effects in GSA according to functional analysis of variance (FANOVA) decomposition. To draw a higher-level understanding, we further use the subset decomposition method to analyze the significance of the groups of input variables. Using the design of a programmable material system (PMS) as an example, we demonstrate the use of our approach for examining the impact of material, architecture, and stimulus variables as well as their interactions. This information lays the foundation for managing design space complexity, summarizing the relationships between system components, and deriving design guidelines for PMS development. [ABSTRACT FROM AUTHOR]

Beta coefficients for linear regression models represent the ideal form of an interpretable feature effect. However, for non-linear models such as generalized linear models, the estimated coefficients cannot be interpreted as a direct feature effect on the predicted outcome. Hence, marginal effects are typically used as approximations for feature effects, either as derivatives of the prediction function or forward differences in prediction due to changes in feature values. While marginal effects are commonly used in many scientific fields, they have not yet been adopted as a general model-agnostic interpretation method for machine learning models. This may stem from the ambiguity surrounding marginal effects and their inability to deal with the non-linearities found in black box models. We introduce a unified definition of forward marginal effects (FMEs) that includes univariate and multivariate, as well as continuous, categorical, and mixed-type features. To account for the non-linearity of prediction functions, we introduce a non-linearity measure for FMEs. Furthermore, we argue against summarizing feature effects of a non-linear prediction function in a single metric such as the average marginal effect. Instead, we propose to average homogeneous FMEs within population subgroups, which serve as conditional feature effect estimates. [ABSTRACT FROM AUTHOR]

The interpretation of feature importance in machine learning models is challenging when features are dependent. Permutation feature importance (PFI) ignores such dependencies, which can cause misleading interpretations due to extrapolation. A possible remedy is more advanced conditional PFI approaches that enable the assessment of feature importance conditional on all other features. Due to this shift in perspective and in order to enable correct interpretations, it is beneficial if the conditioning is transparent and comprehensible. In this paper, we propose a new sampling mechanism for the conditional distribution based on permutations in conditional subgroups. As these subgroups are constructed using tree-based methods such as transformation trees, the conditioning becomes inherently interpretable. This not only provides a simple and effective estimator of conditional PFI, but also local PFI estimates within the subgroups. In addition, we apply the conditional subgroups approach to partial dependence plots, a popular method for describing feature effects that can also suffer from extrapolation when features are dependent and interactions are present in the model. In simulations and a real-world application, we demonstrate the advantages of the conditional subgroup approach over existing methods: It allows to compute conditional PFI that is more true to the data than existing proposals and enables a fine-grained interpretation of feature effects and importance within the conditional subgroups. [ABSTRACT FROM AUTHOR]

Interpretable machine learning aims at unveiling the reasons behind predictions returned by uninterpretable classifiers. One of the most valuable types of explanation consists of counterfactuals. A counterfactual explanation reveals what should have been different in an instance to observe a diverse outcome. For instance, a bank customer asks for a loan that is rejected. The counterfactual explanation consists of what should have been different for the customer in order to have the loan accepted. Recently, there has been an explosion of proposals for counterfactual explainers. The aim of this work is to survey the most recent explainers returning counterfactual explanations. We categorize explainers based on the approach adopted to return the counterfactuals, and we label them according to characteristics of the method and properties of the counterfactuals returned. In addition, we visually compare the explanations, and we report quantitative benchmarking assessing minimality, actionability, stability, diversity, discriminative power, and running time. The results make evident that the current state of the art does not provide a counterfactual explainer able to guarantee all these properties simultaneously. [ABSTRACT FROM AUTHOR]

Background: Acute myocardial infarctions are deadly to patients and burdensome to healthcare systems. Most recorded infarctions are patients' first, occur out of the hospital, and often are not accompanied by cardiac comorbidities. The clinical manifestations of the underlying pathophysiology leading to an infarction are not fully understood and little effort exists to use explainable machine learning to learn predictive clinical phenotypes before hospitalization is needed. Methods: We extracted outpatient electronic health record data for 2641 case and 5287 matched-control patients, all without pre-existing cardiac diagnoses, from the Michigan Medicine Health System. We compare six different interpretable, feature extraction approaches, including temporal computational phenotyping, and train seven interpretable machine learning models to predict the onset of first acute myocardial infarction within six months. Results: Using temporal computational phenotypes significantly improved the model performance compared to alternative approaches. The mean cross-validation test set performance exhibited area under the receiver operating characteristic curve values as high as 0.674. The most consistently predictive phenotypes of a future infarction include back pain, cardiometabolic syndrome, family history of cardiovascular diseases, and high blood pressure. Conclusions: Computational phenotyping of longitudinal health records can improve classifier performance and identify predictive clinical concepts. State-of-the-art interpretable machine learning approaches can augment acute myocardial infarction risk assessment and prioritize potential risk factors for further investigation and validation. [ABSTRACT FROM AUTHOR]

Background: Depression is one of the most common mental illnesses among middle-aged and older adults in China. It is of great importance to find the crucial factors that lead to depression and to effectively control and reduce the risk of depression. Currently, there are limited methods available to accurately predict the risk of depression and identify the crucial factors that influence it. Methods: We collected data from 25,586 samples from the harmonized China Health and Retirement Longitudinal Study (CHARLS), and the latest records from 2018 were included in the current cross-sectional analysis. Ninety-three input variables in the survey were considered as potential influential features. Five machine learning (ML) models were utilized, including CatBoost and eXtreme Gradient Boosting (XGBoost), Gradient Boosting decision tree (GBDT), Random Forest (RF), Light Gradient Boosting Machine (LightGBM). The models were compared to the traditional multivariable Linear Regression (LR) model. Simultaneously, SHapley Additive exPlanations (SHAP) were used to identify key influencing factors at the global level and explain individual heterogeneity through instance-level analysis. To explore how different factors are nonlinearly associated with the risk of depression, we employed the Accumulated Local Effects (ALE) approach to analyze the identified critical variables while controlling other covariates. Results: CatBoost outperformed other machine learning models in terms of MAE, MSE, MedAE, and R2metrics. The top three crucial factors identified by the SHAP were r4satlife, r4slfmem, and r4shlta, representing life satisfaction, selfreported memory, and health status levels, respectively. Conclusion: This study demonstrates that the CatBoost model is an appropriate choice for predicting depression among middle-aged and older adults in Harmonized CHARLS. The SHAP and ALE interpretable methods have identified crucial factors and the nonlinear relationship with depression, which require the attention of domain experts. [ABSTRACT FROM AUTHOR]

The main objective of this paper is to use the data‐driven approach to predict and evaluate the mechanical properties of concrete made with recycled concrete aggregate (RCA), including compressive strength and elastic modulus. Using 358 data samples, including 10 input variables, 10 popular machine learning (ML) algorithms are introduced to select the best ML performance model for predicting RCA concrete's compressive strength and elastic modulus. Gradient Boosting and Categorial Boosting have the best performance in predicting the compressive strength of RCA concrete, with R2 = 0.9112, RMSE = 5.3464 MPa, MAE = 4.0845 MPa, and R2 = 0.9175, RMSE = 5.1520 MPa, MAE = 3.7567 MPa, respectively. Light Gradient Boosting and Categorial Boosting have the best performance in predicting the elastic modulus of RCA concrete, with R2 = 0.8775, RMSE = 2.3560 GPa, MAE = 1.8330 GPa, and R2 = 0.9300, RMSE = 2.3560 MPa, MAE = 1.2589 MPa, respectively. Based on the Shapley Additive Explanation analysis, the influence of main factors on compressive strength and elastic modulus of RCA concrete values has been analyzed qualitatively and quantitatively. RCA replacement level and cement/sand ratio slightly affect compressive strength but have a dominant influence on the elastic modulus of RCA concrete. [ABSTRACT FROM AUTHOR]

The utilization of machine learning (ML) for rockburst assessment is hindered by an incomplete problem formalization in prior studies, which have focused more on predictive accuracy and less on factors such as explainability and uncertainty quantification. Despite achieving commendable accuracies, practitioners remain apprehensive about real-time implementation due to concerns surrounding transparency and validity, particularly when dealing with challenging or unfamiliar rock samples. This uncertainty may result in arbitrary predictions which are mostly incorrect. Establishing trust in ML applications, particularly in critical domains like rockburst assessment, requires models to provide transparent reasoning, communicate uncertainty, and exercise caution when making assertive predictions with unfamiliar data. This paper addresses these concerns by introducing a novel framework that combines interpretable ML techniques specifically Shapley additive explanation (SHAP), with adaptive conformal prediction (CP), built atop extreme gradient boosting to establish a transparent and reliable predictive framework. The validity of the proposed framework was rigorously assessed using conformal metrics, including marginal coverage, conditional coverage, and average prediction set size. Additionally, the SHAP technique was employed to elucidate explanations for predictions flagged as unreliable through CP. The results justify the framework's high effectiveness in generating valid predictions for rockburst grades, concurrently providing corresponding confidence levels and insights into the underlying mechanisms that drive these predictions. The proposed framework facilitates the identification of unreliable predictions, ensuring that only reliable predictions inform decision-making. This not only enhances user confidence in the predictive model but also contributes to the overall safety of underground engineering projects. Highlights: A framework that combines conformal prediction and interpretable machine learning for rockburst assessment is proposed. The proposed framework guarantees marginal coverage and, in most cases, conditional coverage on the test dataset. The conformal prediction identifies several predictions as unreliable, which require expert verification for decision-making purposes. Analysis using Shapley additive explanation revealed that the most important input feature for predicting rockbursts is wet condition. [ABSTRACT FROM AUTHOR]

As an important indicator of the surface quality of workpieces, surface roughness has a great impact on production costs and the quality performance of the finished components. Effective surface roughness prediction can not only increase productivity but also reduce costs. However, the current methods for surface roughness prediction have some limitations. On the one hand, the prediction accuracy of classical experimental and statistical-based surface roughness prediction methods is low. On the other hand, the results of deep learning-based surface roughness prediction methods are uninterpretable due to their black-box learning mechanism. Therefore, this paper presents an ensemble learning with a differential evolution algorithm, applies it to the prediction of surface roughness of abrasive water jet polishing (AWJP), and conducts an interpretability analysis to identify key factors contributing to the prediction accuracy of surface roughness. First, we proposed automatically constructing features by an Evolution Forest algorithm to train the base regression models. The differential evolution algorithm with a simplified encoding mechanism was then used to search for the best weighted-ensemble to integrate the base regression models for obtaining highly accurate prediction results. Extensive experiments have been conducted on AWJP to validate the effectiveness of our proposed methods. The results show that the prediction accuracy of our proposed method is higher than the existing machine learning algorithms. In addition, this is the first of its time for the contributions of machining parameters (i.e., features) on surface roughness prediction by using interpretable analysis methods. The analysis results can provide a reference basis for subsequent experiments and studies. [ABSTRACT FROM AUTHOR]

The growing global meat consumption has serious consequences on human health, the environment and ultimately impacts global food security. Therefore, identifying the drivers of meat consumption and predicting its evolution is necessary. We compared four machine learning methods in modelling meat consumption, leading to the selection of a random forest-based model to detect main drivers for global meat consumption. Our results show that per capita meat consumption is mainly driven by socioeconomic factors, such as national GDP and urbanization. However, the strength of these drivers declined between 1990 and 2018. Pork, beef, and poultry consumption are mainly driven by socioeconomic factors, whereas mutton consumption appears driven by other factors such as the per capita agricultural land. In this work, the model-agnostic interpretability method is introduced to measure the marginal effect of each driver on meat consumption. We found that there may be insufficient evidence to support the inverted U-shaped relationship between per capita GDP and meat consumption, which is reported in previous studies. Our analysis may provide avenues for predicting meat consumption at the national scale. [ABSTRACT FROM AUTHOR]

Random forests are a nonparametric machine learning method, which is currently gaining popularity in the behavioral sciences. Despite random forests' potential advantages over more conventional statistical methods, a remaining question is how reliably informative predictor variables can be identified by means of random forests. The present study aims at giving a comprehensible introduction to the topic of variable selection with random forests and providing an overview of the currently proposed selection methods. Using simulation studies, the variable selection methods are examined regarding their statistical properties, and comparisons between their performances and the performance of a conventional linear model are drawn. Advantages and disadvantages of the examined methods are discussed, and practical recommendations for the use of random forests for variable selection are given. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach called Stack-GA2M to identify fraudulent reviewers in an inherently interpretable manner by fusing both target and non-target features. Specifically, for local interpretability, we adopt GA2M (Standard Generalized Additive Model plus interactions) as the basic classifier to produce three subordinate models trained by using the target features and the non-target features as review textual features and reviewer behavioral features. For global interpretability, we adopt LR (Logistic Regression) as the meta classifier to stack the outputs of three subordinate models to identify the fraudulent reviewers. The white-box model of LR enables us to understand the global interpretability of the target features and the non-target features in identifying fraudulent reviewers. With GA2M, the local interpretability of each subordinate model is derived by using feature importance, spline shape functions for individual features, and heatmaps for interaction terms. Extensive experiments on Yelp dataset demonstrate that the proposed Stack-GA2M approach is superior to state-of-the-art techniques in identifying fraudulent reviewers and exhibits favorable inherent interpretability. [ABSTRACT FROM AUTHOR]

Background: Neuropsychopharmacological compounds may exert complex brain-wide effects due to an anatomically and genetically broad expression of their molecular targets and indirect effects via interconnected brain circuits. Electrophysiological measurements in multiple brain regions using electroencephalography (EEG) or local field potential (LFP) depth-electrodes may record fingerprints of such pharmacologically-induced changes in local activity and interregional connectivity (pEEG/pLFP). However, in order to reveal such patterns comprehensively and potentially derive mechanisms of therapeutic pharmacological effects, both activity and connectivity have to be estimated for many brain regions. This entails the problem that hundreds of electrophysiological parameters are derived from a typically small number of subjects, making frequentist statistics ill-suited for their analysis. Methods: We here present an optimized interpretable machine-learning (ML) approach which relies on predictive power in individual recording sequences to extract and quantify the robustness of compound-induced neural changes from multi-site recordings using Shapley additive explanations (SHAP) values. To evaluate this approach, we recorded LFPs in mediodorsal thalamus (MD), prefrontal cortex (PFC), dorsal hippocampus (CA1 and CA3), and ventral hippocampus (vHC) of mice after application of amphetamine or of the dopaminergic antagonists clozapine, raclopride, or SCH23390, for which effects on directed neural communication between those brain structures were so far unknown. Results: Our approach identified complex patterns of neurophysiological changes induced by each of these compounds, which were reproducible across time intervals, doses (where tested), and ML algorithms. We found, for example, that the action of clozapine in the analysed cortico-thalamohippocampal network entails a larger share of D1--as opposed to D2-receptor induced effects, and that the D2-antagonist raclopride reconfigures connectivity in the delta-frequency band. Furthermore, the effects of amphetamine and clozapine were surprisingly similar in terms of decreasing thalamic input to PFC and vHC, and vHC activity, whereas an increase of dorsal-hippocampal communication and of thalamic activity distinguished amphetamine from all tested anti-dopaminergic drugs. Conclusion: Our study suggests that communication from the dorsal hippocampus scales proportionally with dopamine receptor activation and demonstrates, more generally, the high complexity of neuropharmacological effects on the circuit level. We envision that the presented approach can aid in the standardization and improved data extraction in pEEG/pLFP-studies. [ABSTRACT FROM AUTHOR]

By applying AI techniques to a variety of pandemic-relevant data, artificial intelligence (AI) has substantially supported the control of the spread of the SARS-CoV-2 virus. Along with this, epidemiological machine learning studies of SARS-CoV-2 have been frequently published. While these models can be perceived as precise and policy-relevant to guide governments towards optimal containment policies, their black box nature can hamper building trust and relying confidently on the prescriptions proposed. This paper focuses on interpretable AI-based epidemiological models in the context of the recent SARS-CoV-2 pandemic. We systematically review existing studies, which jointly incorporate AI, SARS-CoV-2 epidemiology, and explainable AI approaches (XAI). First, we propose a conceptual framework by synthesizing the main methodological features of the existing AI pipelines of SARS-CoV-2. Upon the proposed conceptual framework and by analyzing the selected epidemiological studies, we reflect on current research gaps in epidemiological AI toolboxes and how to fill these gaps to generate enhanced policy support in the next potential pandemic. [ABSTRACT FROM AUTHOR]

Childhood asthma is one of the most common respiratory diseases with rising mortality and morbidity. The multi-omics data is providing a new chance to explore collaborative biomarkers and corresponding diagnostic models of childhood asthma. To capture the nonlinear association of multi-omics data and improve interpretability of diagnostic model, we proposed a novel deep association model (DAM) and corresponding efficient analysis framework. First, the Deep Subspace Reconstruction was used to fuse the omics data and diagnostic information, thereby correcting the distribution of the original omics data and reducing the influence of unnecessary data noises. Second, the Joint Deep Semi-Negative Matrix Factorization was applied to identify different latent sample patterns and extract biomarkers from different omics data levels. Third, our newly proposed Deep Orthogonal Canonical Correlation Analysis can rank features in the collaborative module, which are able to construct the diagnostic model considering nonlinear correlation between different omics data levels. Using DAM, we deeply analyzed the transcriptome and methylation data of childhood asthma. The effectiveness of DAM is verified from the perspectives of algorithm performance and biological significance on the independent test dataset, by ablation experiment and comparison with many baseline methods from clinical and biological studies. The DAM-induced diagnostic model can achieve a prediction AUC of 0.912, which is higher than that of many other alternative methods. Meanwhile, relevant pathways and biomarkers of childhood asthma are also recognized to be collectively altered on the gene expression and methylation levels. As an interpretable machine learning approach, DAM simultaneously considers the non-linear associations among samples and those among biological features, which should help explore interpretative biomarker candidates and efficient diagnostic models from multi-omics data analysis for human complex diseases. [ABSTRACT FROM AUTHOR]

The prediction of fatigue cracks on orthotropic steel decks is of great significance to the maintenance of bridges. However, fatigue cracks are affected by various uncertainties in reality, which encourages a data‐driven study for the sake of reliability and accuracy of predictions. Based on the crack inspection data from orthotropic steel decks on actual bridges in China, the feature engineering is conducted considering fatigue crack behaviors, and the machine learning models are trained and tested for predicting cracks, including XGBoost, random forest, and multiple decision trees. According to the receiver operating characteristic curves of the three models, the XGBoost model has the best performance, whereas the average AUC is about 0.75, limited by the insufficient data volume of positive samples. With the SHAP values of all features, the interpretation of the machine learning model is presented, indicating that the global effects, that is, the longitudinal position, the loading condition, and the bridge age, are always influential factors for fatigue cracks. The local features concerning the interactions between cracks have an effect on crack behaviors to a certain extent, but less important. Accordingly, the interpretable machine learning model can provide conservative predictions in a rather transparent way on this issue, which can benefit decision‐making in bridge designs, maintenance, and management. [ABSTRACT FROM AUTHOR]

Run-Off-Road (ROR) crashes are frequent and pose a significant risk of injury and fatality. Given the complexity of their mechanisms and the interaction of multiple factors, this study aims to comprehensively investigate the factors influencing the severity of ROR crashes, which have been understudied. Furthermore, addressing the current methodological challenge in machine learning (ML) crash modeling, this study proposes an approach to tackle unobserved heterogeneity in ML. An interpretable ML joint with prior latent class clustering is implemented. The significant risk factors and interactions are interpreted using SHAP (SHapley Additive exPlanations) method across clusters. This study utilizes ROR crash records, traffic, and geometric data from main suburban freeways in Iran collected over a 5-year period. The key interacting factors associated with severe ROR during adverse weather (cluster 1) are: co-occurrence of low congestion and higher speed variation; low congestion, nighttime darkness and rollover; roadway departure by buses and mini-buses and rollover occurrence; vehicle departure and collision with fixed objects. Moreover, the critical interactions for nighttime condition (cluster 2) are: curve sections combined with longitudinal slope; inside shoulder width <1.5 m and a hit median concrete NewJersey barrier. The risky interactions for crashes occurred in curves (cluster 3) are: departing in two-lane sections in low congestion conditions; vehicles collisions with the median concrete NewJersey barriers. The findings of this study enhance comprehension of the significant effects of interactions under various conditions, offering valuable insights for policymakers. Additionally, recommendations are offered to mitigate the risk of severe ROR crashes. • The factors effecting run-off-road crash severity are explored. • A machine learning (ML) model is used, and the results are interpreted by SHAP. • Prior clustering is implemented to address unobserved heterogeneity in ML. • The interactions of traffic, geometric and environmental factors are extracted. • The visualized outputs of this study offer valuable insights for policymakers. [ABSTRACT FROM AUTHOR]

The operation of the subway system necessitates a comprehensive understanding of passenger flow characteristics at station locations, as well as a keen awareness of the average travel distances at these stations. Moreover, the travel distances at the station level bear a direct relationship with the built environment composed of land use characteristics within the station's catchment area. To this end, we selected the land use features within an 800 m radius of the station (land use area, distribution of points of interest, and the surrounding living environment) as the influencing factors, with the travel distances at peak hours on the subway network in Xi'an as the research subject. An improved SSA-XGBOOST-SHAP interpretable machine learning framework was established. The research findings demonstrate that the proposed enhanced model outperforms traditional machine learning or linear regression methods in terms of R-squared, MAE, and RMSE. Furthermore, the distance from the city center, road network density, the number of public transit routes, and the land use mix have a pronounced influence on travel distances, reflecting the significant impact that mature built environments can have on passenger attraction. Additionally, the analysis reveals a notable nonlinear relationship and threshold effect between the built environment variables comprising land use and the travel distances during peak hours. The research results provide data-driven support for operational strategy management and line capacity optimization, as well as theoretical underpinnings for enhancing the efficiency and sustainability of the entire subway system. [ABSTRACT FROM AUTHOR]

Objective Predicting mortality after acute myocardial infarction (AMI) is crucial for timely prescription and treatment of AMI patients, but there are no appropriate AI systems for clinicians. Our primary goal is to develop a reliable and interpretable AI system and provide some valuable insights regarding short, and long-term mortality. Materials and methods We propose the RIAS framework, an end-to-end framework that is designed with reliability and interpretability at its core and automatically optimizes the given model. Using RIAS, clinicians get accurate and reliable predictions which can be used as likelihood, with global and local explanations, and "what if" scenarios to achieve desired outcomes as well. Results We apply RIAS to AMI prognosis prediction data which comes from the Korean Acute Myocardial Infarction Registry. We compared FT-Transformer with XGBoost and MLP and found that FT-Transformer has superiority in sensitivity and comparable performance in AUROC and F1 score to XGBoost. Furthermore, RIAS reveals the significance of statin-based medications, beta-blockers, and age on mortality regardless of time period. Lastly, we showcase reliable and interpretable results of RIAS with local explanations and counterfactual examples for several realistic scenarios. Discussion RIAS addresses the "black-box" issue in AI by providing both global and local explanations based on SHAP values and reliable predictions, interpretable as actual likelihoods. The system's "what if" counterfactual explanations enable clinicians to simulate patient-specific scenarios under various conditions, enhancing its practical utility. Conclusion The proposed framework provides reliable and interpretable predictions along with counterfactual examples. [ABSTRACT FROM AUTHOR]

Interpretable Machine Learning (IML) has rapidly advanced in recent years, offering new opportunities to improve our understanding of the complex Earth system. IML goes beyond conventional machine learning by not only making predictions but also seeking to elucidate the reasoning behind those predictions. The combination of predictive power and enhanced transparency makes IML a promising approach for uncovering relationships in data that may be overlooked by traditional analysis. Despite its potential, the broader implications for the field have yet to be fully appreciated. Meanwhile, the rapid proliferation of IML, still in its early stages, has been accompanied by instances of careless application. In response to these challenges, this paper focuses on how IML can effectively and appropriately aid geoscientists in advancing process understanding—areas that are often underexplored in more technical discussions of IML. Specifically, we identify pragmatic application scenarios for IML in typical geoscientific studies, such as quantifying relationships in specific contexts, generating hypotheses about potential mechanisms, and evaluating process‐based models. Moreover, we present a general and practical workflow for using IML to address specific research questions. In particular, we identify several critical and common pitfalls in the use of IML that can lead to misleading conclusions, and propose corresponding good practices. Our goal is to facilitate a broader, yet more careful and thoughtful integration of IML into Earth science research, positioning it as a valuable data science tool capable of enhancing our current understanding of the Earth system. Plain Language Summary: Artificial Intelligence is a rapidly advancing field, in which Interpretable Machine Learning (IML) is seen as having the potential to significantly improve our understanding of Earth's complex environmental systems. IML goes beyond the predictive power of machine learning models, focusing instead on uncovering the relationships within the data that are revealed by the model's learning process. However, there is still a lack of straightforward, practical domain‐specific guidelines for geoscientists that facilitate both broader and more careful application in the field. In this paper, we aim to demonstrate the real‐world benefits of IML in typical geoscientific analysis. We provide a clear, step‐by‐step workflow that shows how IML can be used to address specific questions. We also point out some common pitfalls in using IML and offer solutions to avoid them. Our goal is to make IML more accessible and useful to a wider range of geoscientists, and we believe that IML, if used properly and thoughtfully, can become an essential and valuable tool to advance our understanding of complex Earth systems. Key Points: We demonstrate the broader relevance of Interpretable Machine Learning (IML) to most geoscientists and underexplored opportunities for its useWe describe a workflow for the effective use of IML while cautioning against potential and common pitfallsWe suggest good practices for its adoption and advocate for more careful application to ensure reliable and robust insights for the field [ABSTRACT FROM AUTHOR]

Machine learning models built on behavioral and textual data can result in highly accurate prediction models, but are often very difficult to interpret. Linear models require investigating thousands of coefficients, while the opaqueness of nonlinear models makes things worse. Rule-extraction techniques have been proposed to combine the desired predictive accuracy of complex "black-box" models with global explainability. However, rule-extraction in the context of high-dimensional, sparse data, where many features are relevant to the predictions, can be challenging, as replacing the black-box model by many rules leaves the user again with an incomprehensible explanation. To address this problem, we develop and test a rule-extraction methodology based on higher-level, less-sparse "metafeatures". We empirically validate the quality of the explanation rules in terms of fidelity, stability, and accuracy over a collection of data sets, and benchmark their performance against rules extracted using the fine-grained behavioral and textual features. A key finding of our analysis is that metafeatures-based explanations are better at mimicking the behavior of the black-box prediction model, as measured by the fidelity of explanations. [ABSTRACT FROM AUTHOR]

To equip data-driven dynamic chemical process models with strong interpretability, we develop a light attention–convolution–gate recurrent unit (LACG) architecture with three sub-modules—a basic module, a brand-new light attention module, and a residue module—that are specially designed to learn the general dynamic behavior, transient disturbances, and other input factors of chemical processes, respectively. Combined with a hyperparameter optimization framework, Optuna, the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process. The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models, including the feedforward neural network, convolution neural network, long short-term memory (LSTM), and attention-LSTM. Moreover, compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1, the LACG parameters are demonstrated to be interpretable, and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM. This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling, paving a route to intelligent manufacturing.

Abstract Analyses of complex behaviors of Cerebrospinal Fluid (CSF) have become increasingly important in diseases diagnosis. The changes of the phase-contrast magnetic resonance imaging (PC-MRI) signal formed by the velocity of flowing CSF are represented as a set of velocity-encoded images or maps, which can be thought of as signal data in the context of medical imaging, enabling the evaluation of pulsatile patterns throughout a cardiac cycle. However, automatic segmentation of the CSF region in a PC-MRI image is challenging, and implementing an explained ML method using pulsatile data as a feature remains unexplored. This paper presents lightweight machine learning (ML) algorithms to perform CSF lumen segmentation in spinal, utilizing sets of velocity-encoded images or maps as a feature. The Dataset contains 57 PC-MRI slabs by 3T MRI scanner from control and idiopathic scoliosis participants are involved to collect data. The ML models are trained with 2176 time series images. Different cardiac periods image (frame) numbers of PC-MRIs are interpolated in the preprocessing step to align to features of equal size. The fivefold cross-validation procedure is used to estimate the success of the ML models. Additionally, the study focusses on enhancing the interpretability of the highest-accuracy eXtreme gradient boosting (XGB) model by applying the shapley additive explanations (SHAP) technique. The XGB algorithm presented its highest accuracy, with an average fivefold accuracy of 0.99% precision, 0.95% recall, and 0.97% F1 score. We evaluated the significance of each pulsatile feature's contribution to predictions, offering a more profound understanding of the model's behavior in distinguishing CSF lumen pixels with SHAP. Introducing a novel approach in the field, develop ML models offer comprehension into feature extraction and selection from PC-MRI pulsatile data. Moreover, the explained ML model offers novel and valuable insights to domain experts, contributing to an enhanced scholarly understanding of CSF dynamics.

Run-Off-Road (ROR) crashes are frequent and pose a significant risk of injury and fatality. Given the complexity of their mechanisms and the interaction of multiple factors, this study aims to comprehensively investigate the factors influencing the severity of ROR crashes, which have been understudied. Furthermore, addressing the current methodological challenge in machine learning (ML) crash modeling, this study proposes an approach to tackle unobserved heterogeneity in ML. An interpretable ML joint with prior latent class clustering is implemented. The significant risk factors and interactions are interpreted using SHAP (SHapley Additive exPlanations) method across clusters. This study utilizes ROR crash records, traffic, and geometric data from main suburban freeways in Iran collected over a 5-year period. The key interacting factors associated with severe ROR during adverse weather (cluster 1) are: co-occurrence of low congestion and higher speed variation; low congestion, nighttime darkness and rollover; roadway departure by buses and mini-buses and rollover occurrence; vehicle departure and collision with fixed objects. Moreover, the critical interactions for nighttime condition (cluster 2) are: curve sections combined with longitudinal slope; inside shoulder width

Copyright of Contemporary Accounting Research is the property of Canadian Academic Accounting Association and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

PURPOSE/OBJECTIVES: Malignant pleural mesothelioma (MPM) is a rare but aggressive cancer arising from the cells of the thoracic pleura with a poor prognosis. We aimed to develop a model, via interpretable machine learning (ML) methods, predicting overall survival for MPM following radiotherapy based on dosimetric metrics as well as patient characteristics. MATERIALS/METHODS: Sixty MPM (37 right, 23 left) patients treated on a Tomotherapy unit between 2013 and 2018 were retrospectively analyzed. All patients received 45 Gy (25 fractions). The multivariable Cox regression (Cox PH) model and Survival Support Vector Machine (sSVM) were applied to build predictive models of overall survival (OS) based on clinical, dosimetric, and combined variables. RESULTS: Significant differences in dosimetric endpoints for critical structures, i.e., the lung, heart, liver, kidney, and stomach, were observed according to target laterality. The OS was found to be insignificantly different (p = 0.18) between MPM patients who tested left- and right-sided, with 1-year OS of 77.3% and 75.0%, respectively. With Cox PH regression, considering dosimetric variables for right-sided patients alone, an increase in PTV_Min, Total_Lung_PTV_Mean, Contra_Lung_Volume, Contra_Lung_V20, Esophagus_Mean, and Heart_Volume had a greater hazard to all-cause death, while an increase in Total_Lung_PTV_V20, Contra_Lung_V5, and Esophagus_Max had a lower hazard to all-cause death. Considering clinical variables alone, males and increases in N stage had greater hazard to all-cause death; considering both clinical and dosimetric variables, increases in N stage, PTV_Mean, PTV_Min, and esophagus_Mean had greater hazard to all-cause death, while increases in T stage and Heart_V30 had lower hazard to all-cause-death. In terms of C-index, the Cox PH model and sSVM performed similarly and fairly well when considering clinical and dosimetric variables independently or jointly. CONCLUSIONS: Clinical and dosimetric variables may predict the overall survival of mesothelioma patients, which could guide personalized treatment planning towards a better treatment response. The identified predictors and their impact on survival offered additional value for translational application in clinical practice.

Effective management of chronic diseases and cancer can greatly benefit from disease-specific biomarkers that enable informative screening and timely diagnosis. IgG N-glycans found in human plasma have the potential to be minimally invasive disease-specific biomarkers for all stages of disease development due to their plasticity in response to various genetic and environmental stimuli. Data analysis and machine learning (ML) approaches can assist in harnessing the potential of IgG glycomics towards biomarker discovery and the development of reliable predictive tools for disease screening. This study proposes an ML-based N-glycomic analysis framework that can be employed to build, optimise, and evaluate multiple ML pipelines to stratify patients based on disease risk in an interpretable manner. To design and test this framework, a published colorectal cancer (CRC) dataset from the Study of Colorectal Cancer in Scotland (SOCCS) cohort (1999–2006) was used. In particular, among the different pipelines tested, an XGBoost-based ML pipeline, which was tuned using multi-objective optimisation, calibrated using an inductive Venn-Abers predictor (IVAP), and evaluated via a nested cross-validation (NCV) scheme, achieved a mean area under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.771 when classifying between age-, and sex-matched healthy controls and CRC patients. This performance suggests the potential of using the relative abundance of IgG N-glycans to define populations at elevated CRC risk who merit investigation or surveillance. Finally, the IgG N-glycans that highly impact CRC classification decisions were identified using a global model-agnostic interpretability technique, namely Accumulated Local Effects (ALE). We envision that open-source computational frameworks, such as the one presented herein, will be useful in supporting the translation of glycan-based biomarkers into clinical applications.