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]

Recent developments in big data technologies are revolutionizing the field of healthcare predictive analytics (HPA), enabling researchers to explore challenging problems using complex prediction models. Nevertheless, healthcare practitioners are reluctant to adopt those models as they are less transparent and accountable due to their black-box structure. We believe that instance-level, or local, explanations enhance patient safety and foster trust by enabling patient-level interpretations and medical knowledge discovery. Therefore, we propose the RObust Local EXplanations (ROLEX) method to develop robust, instance-level explanations for HPA models in this study. ROLEX adapts state-of-the-art methods and ameliorates their shortcomings in explaining individual-level predictions made by black-box machine learning models. Our analysis with a large real-world dataset related to a prevalent medical condition called fragility fracture and two publicly available healthcare datasets reveals that ROLEX outperforms widely accepted benchmark methods in terms of local faithfulness of explanations. In addition, ROLEX is more robust since it does not rely on extensive hyperparameter tuning or heuristic algorithms. Explanations generated by ROLEX, along with the prototype user interface presented in this study, have the potential to promote personalized care and precision medicine by providing patient-level interpretations and novel insights. We discuss the theoretical implications of our study in healthcare, big data, and design science. [ABSTRACT FROM AUTHOR]

Background: Advances in DNA sequencing revolutionized plant genomics and significantly contributed to the study of genetic diversity. However, predicting phenotypes from genomic data remains a challenge, particularly in the context of plant breeding. Despite significant progress, accurately predicting phenotypes from high-dimensional genomic data remains a challenge, particularly in identifying the key genetic factors influencing these predictions. This study aims to bridge this gap by integrating explainable artificial intelligence (XAI) techniques with advanced machine learning models. This approach is intended to enhance both the predictive accuracy and interpretability of genotype-to-phenotype models, thereby improving their reliability and supportingmore informed breeding decisions. Results: This study compares several ML methods for genotype-to-phenotype prediction, using data available from an almond germplasm collection. After preprocessing and feature selection, regression models are employed to predict almond shelling fraction. Best predictions were obtained by the Random Forest method (correlation = 0.727 ± 0.020, an R2 = 0.511 ± 0.025, and an RMSE = 7.746 ± 0.199). Notably, the application of the SHAP (SHapley Additive exPlanations) values algorithm to explain the results highlighted several genomic regions associated with the trait, including one, having the highest feature importance, located in a gene potentially involved in seed development. Conclusions: Employing explainable artificial intelligence algorithms enhances model interpretability, identifying genetic polymorphisms associated with the shelling percentage. These findings underscore XAI's efficacy in predicting phenotypic traits from genomic data, highlighting its significance in optimizing crop production for sustainable agriculture. [ABSTRACT FROM AUTHOR]

Airway diseases cause significant challenges while diagnosing it accurately as well as timely. In current years, the combination of deep learning techniques with Explainable Artificial Intelligence (XAI), has emerged as a promising possibility to enhance the understanding as well as interpretability of complex medical data which are associated with these conditions. The study explores the usage of advanced convolutional neural networks (CNNs) on large-scale of Chest X-ray or CT scan image datasets and their application in the domain of medical imaging to detect as well as classify airway diseases such as pneumoconiosis, pulmonary embolism, Covid-19, tuberculosis, and Lung cancer. The visualization of the images have been enhanced by applying sharpening techniques and are later subsequently used to train various deep learning models which include InceptionResNetV2, MobileNet, Xception, ResNet152, EfficientNetV2M, and DenseNet169. Further, various parameters have been used for the evaluation of the performance of these models in determining the most optimal choice. During training the model, it has been found that the highest accuracy, precision, recall, and F1 score has been computed by InceptionResNetV2 with 99.15%, 98% and 99% (both) respectively on a loss of 0.0275. Besides this, a graphical user interface (GUI) has been also developed to improvise the interaction between the AI based model and end users. The GUI is based on the theory of XAI which after predicting the diseases provides in detail explanation of treatment as well as preventive measures of the disease. The motto of the research is to escalate the knowledge of deep learning techniques for various lung based issues as well as to enlighten with the significance of XAI in promoting interpretability as well as transparency. The findings of the research implies towards the advancement of decision support systems at various medical sectors to promote effective as well as personalized interventions in the realm of pulmonology. [ABSTRACT FROM AUTHOR]

Background Aims Materials and Methods Results Discussion Conclusion Given that students from socio‐economically disadvantaged family backgrounds are more likely to suffer from low academic performance, there is an interest in identifying features of academic resilience, which may mitigate the relationship between disadvantaged socio‐economic status and academic performance.This study sought to combine machine learning and explainable artificial intelligence (XAI) technique to identify key features of academic resilience in mathematics learning during COVID‐19.Based on PISA 2022 data in 79 countries/economies, the random forest model coupled with Shapley additive explanations (SHAP) value technique not only uncovered the key features of academic resilience but also examined the contributions of each key feature.Findings indicated that 35 features were identified in the classification of academically resilient and non‐academically resilient students, which largely validated the previous academic resilient framework. Notably, gender differences were shown in the distribution of some key features. Research findings also indicated that resilient students tended to have a stable emotional state, high levels of self‐efficacy, low levels of truancy and positive future aspirations.This study has established a research paradigm essentially methodological in nature to bridge the gap between psychological theories and big data in the field of educational psychology.To sum up, our study shed light on the issues of education equity and quality from a global perspective in the times of the COVID‐19 pandemic. [ABSTRACT FROM AUTHOR]

Currently, hydrogen generation is considered a crucial aspect of sustainable energy production. This paper disscusses the hypothesis that hydrogen generation occurs during the operation of the membrane electrode assembly and is an acceptable and eco-friendly method for producing hydrogen without carbon dioxide. This paper considers the hypothesis by simulating hydrogen generation in fuel cells that rely on fossil fuels using proton fuel cells. The O ptimized H ydrogen G eneration-based R egression (OHGR) model is based on a deep learning architecture. The architecture is based on stacking multiple neural networks with crossover connections that feed information through a pool of activation functions. The OHGR predicts the amount of hydrogen generated in 1 mA cm−2 and can exceed 10–20 mA cm−2 after long-term operation. For given temperatures, pressures, and humidity, which are considered fundamental factors in the hydrogen crossing phenomenon.The OHGR uses a stochastic gradient as an optimization engine that informs the most-recommended values for temperature, pressure, and humidity to generate the optimal amount of hydrogen. In addition, the OHGR model is interoperated to accept the same number of most significant features obtained from the principal component analysis. The OHGR was evaluated using empirical regression evaluation metrics, including the root mean square error, R2, Mean Square Error, and Mean Absolute Error. The optimization process was designed to include the hypothesis and hyperparameters to determine the most significant values for the OGHR and its outcomes. The introduced OHGR model is sufficiently efficient to predict the generated hydrogen with RMSE = 0.220 and R2 = 0.564, indicating an enhancement of the OHGR model compared to recently reported models. Since the sustainability of hydrogen generation is important for energy availability and reducing climate change, the OHGR model is justified using the SHapley Additive exPlanations (SHAP) method to ensure that the model is transparent, reliable, and trustworthy. [Display omitted] • Optimized Hydrogen Generation-based Regression (OHGR) model using a custom architecture. • OHGR predicts generated hydrogen PEM by optimizing temp, pressure & humidity of CNN structure. • OHGR uses an optimization engine to detect most recommended to generate hydrogen. • OHGR accepts same number of significant features by principal component analysis. • XAI is used to ensure transparent, reliable, and trusted of OHGR using SHAP. [ABSTRACT FROM AUTHOR]

Pregnancy termination remains a complex and sensitive issue with approximately 45% of abortions worldwide being unsafe, and 97% of abortions occurring in developing countries. Unsafe pregnancy terminations have implications for women's reproductive health. This research aims to compare black box models in their prediction of pregnancy termination among reproductive-aged women and identify factors associated with pregnancy termination using explainable artificial intelligence (XAI) methods. We used comprehensive secondary data on reproductive-aged women's demographic and socioeconomic data from the Demographic Health Survey (DHS) from six countries in East Africa in the analysis. This study implemented five black box ML models, Bagging classifier, Random Forest, Extreme Gradient Boosting (XGB) Classifier, CatBoost Classifier, and Extra Trees Classifier on a dataset with 338,904 instances and 18 features. Additionally, SHAP, Eli5, and LIME XAI techniques were used to determine features associated with pregnancy termination and Statistical analysis were employed to understand the distribution of pregnancy termination. The results demonstrated that machine learning algorithms were able to predict pregnancy termination on DHS data with an overall accuracy ranging from 79.4 to 85.6%. The ML classifier random forest achieved the highest result, with an accuracy of 85.6%. Based on the results of the XAI tool, the most contributing factors for pregnancy termination are wealth index, current working experience, and source of drinking water, sex of household, education level, and marital status. The outcomes of this study using random forest is expected to significantly contribute to the field of reproductive healthcare in East Africa and can assist healthcare providers in identifying individuals' countries at greater risk of pregnancy termination, allowing for targeted interventions and support. [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]

Highlights Artificial intelligence (AI) techniques are increasingly used for structural health monitoring (SHM) of polymer composite structures. However, to be confident in the trustworthiness of AI models, the models must be reliable, interpretable, and explainable. The use of explainable artificial intelligence (XAI) is critical to ensure that the AI model is transparent in the decision‐making process and that the predictions it provides can be trusted and understood by users. However, existing SHM methods for polymer composite structures lack explainability and transparency, and therefore reliable damage detection. Therefore, an interpretable deep learning model based on an explainable vision transformer (X‐ViT) is proposed for the SHM of composites, leading to improved repair planning, maintenance, and performance. The proposed approach has been validated on carbon fiber reinforced polymers (CFRP) composites with multiple health states. The X‐ViT model exhibited better damage detection performance compared to existing popular methods. Moreover, the X‐ViT approach effectively highlighted the area of interest related to the prediction of each health condition in composites through the patch attention aggregation process, emphasizing their influence on the decision‐making process. Consequently, integrating the ViT‐based explainable deep‐learning model into the SHM of polymer composites provided improved diagnostics along with increased transparency and reliability. Autonomous damage detection of polymer composites using vision transformer based deep learning model. Explainable artificial intelligence by highlighting region of interest using patch attention. Comparison with the existing state of the art structural health monitoring methods. [ABSTRACT FROM AUTHOR]

In the high-stakes realm of critical care, where daily decisions are crucial and clear communication is paramount, comprehending the rationale behind Artificial Intelligence (AI)-driven decisions appears essential. While AI has the potential to improve decision-making, its complexity can hinder comprehension and adherence to its recommendations. "Explainable AI" (XAI) aims to bridge this gap, enhancing confidence among patients and doctors. It also helps to meet regulatory transparency requirements, offers actionable insights, and promotes fairness and safety. Yet, defining explainability and standardising assessments are ongoing challenges and balancing performance and explainability can be needed, even if XAI is a growing field. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) is being applied to improve the efficiency of software systems used in various domains, especially in the health and forensic sciences. Explainable AI (XAI) is one of the fields of AI that interprets and explains the methods used in AI. One of the techniques used in XAI to provide such interpretations is by computing the relevance of the input features to the output of an AI model. File fragment classification is one of the vital issues of file carving in Cyber Forensics (CF) and becomes challenging when the filesystem metadata is missing. Other major challenges it faces are: proliferation of file formats, file embeddings, automation, We leverage and utilize interpretations provided by XAI to optimize the classification of file fragments and propose a novel sifting approach, named SIFT (Sifting File Types). SIFT employs TF-IDF to assign weight to a byte (feature), which is used to select features from a file fragment. Threshold-based LIME and SHAP (the two XAI techniques) feature relevance values are computed for the selected features to optimize file fragment classification. To improve multinomial classification, a Multilayer Perceptron model is developed and optimized with five hidden layers, each layer with i × n neurons, where i = the layer number and n = the total number of classes in the dataset. When tested with 47,482 samples of 20 file types (classes), SIFT achieves a detection rate of 82.1% and outperforms the other state-of-the-art techniques by at least 10%. To the best of our knowledge, this is the first effort of applying XAI in CF for optimizing file fragment classification. [ABSTRACT FROM AUTHOR]

Recent advancements in artificial intelligence (AI) have prompted researchers to expand into the field of oculomics; the association between the retina and systemic health. Unlike conventional AI models trained on well-recognized retinal features, the retinal phenotypes that most oculomics models use are more subtle. Consequently, applying conventional tools, such as saliency maps, to understand how oculomics models arrive at their inference is problematic and open to bias. We hypothesized that neuron activation patterns (NAPs) could be an alternative way to interpret oculomics models, but currently, most existing implementations focus on failure diagnosis. In this study, we designed a novel NAP framework to interpret an oculomics model. We then applied our framework to an AI model predicting systolic blood pressure from fundus images in the United Kingdom Biobank dataset. We found that the NAP generated from our framework was correlated to the clinically relevant endpoint of cardiovascular risk. Our NAP was also able to discern two biologically distinct groups among participants who were assigned the same predicted systolic blood pressure. These results demonstrate the feasibility of our proposed NAP framework for gaining deeper insights into the functioning of oculomics models. Further work is required to validate these results on external datasets. [ABSTRACT FROM AUTHOR]

AbstractThe brain-computer interface (BCI) systems based on motor imagery typically rely on a large number of electrode channels to acquire information. The rational selection of electroencephalography (EEG) channel combinations is crucial for optimizing computational efficiency and enhancing practical applicability. However, evaluating all potential channel combinations individually is impractical. This study aims to explore a strategy for quickly achieving a balance between maximizing channel reduction and minimizing precision loss. To this end, we developed a spatio-temporal attention perception network named STAPNet. Based on the channel contributions adaptively generated by its subnetwork, we propose an extended step bi-directional search strategy that includes variable ratio channel selection (VRCS) and strided greedy channel selection (SGCS), designed to enhance global search capabilities and accelerate the optimization process. Experimental results show that on the High Gamma and BCI Competition IV 2a public datasets, the framework respectively achieved average maximum accuracies of 91.47% and 84.17%. Under conditions of zero precision loss, the average number of channels was reduced by a maximum of 87.5%. Additionally, to investigate the impact of neural information loss due to channel reduction on the interpretation of complex brain functions, we employed a heatmap visualization algorithm to verify the universal importance and complete symmetry of the selected optimal channel combination across multiple datasets. This is consistent with the brain’s cooperative mechanism when processing tasks involving both the left and right hands. [ABSTRACT FROM AUTHOR]

Purpose: To determine if an explainable artificial intelligence (XAI) model enhances the accuracy and transparency of predicting embryo ploidy status based on embryonic characteristics and clinical data. Methods: This retrospective study utilized a dataset of 1908 blastocyst embryos. The dataset includes ploidy status, morphokinetic features, morphology grades, and 11 clinical variables. Six machine learning (ML) models including Random Forest (RF), Linear Discriminant Analysis (LDA), Logistic Regression (LR), Support Vector Machine (SVM), AdaBoost (ADA), and Light Gradient-Boosting Machine (LGBM) were trained to predict ploidy status probabilities across three distinct datasets: high-grade embryos (HGE, n = 1107), low-grade embryos (LGE, n = 364), and all-grade embryos (AGE, n = 1471). The model's performance was interpreted using XAI, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) techniques. Results: The mean maternal age was 38.5 ± 3.85 years. The Random Forest (RF) model exhibited superior performance compared to the other five ML models, achieving an accuracy of 0.749 and an AUC of 0.808 for AGE. In the external test set, the RF model achieved an accuracy of 0.714 and an AUC of 0.750 (95% CI, 0.702–0.796). SHAP's feature impact analysis highlighted that maternal age, paternal age, time to blastocyst (tB), and day 5 morphology grade significantly impacted the predictive model. In addition, LIME offered specific case-ploidy prediction probabilities, revealing the model's assigned values for each variable within a finite range. Conclusion: The model highlights the potential of using XAI algorithms to enhance ploidy prediction, optimize embryo selection as patient-centric consultation, and provides reliability and transparent insights into the decision-making process. [ABSTRACT FROM AUTHOR]

Background/Objectives: The purpose of this study was to analyze relevant areas in acute-stage fluorescein angiography (FA) images, predicting the long-term visual prognosis of branch retinal vein occlusion (BRVO) based on gradient-weighted class activation mapping (Grad-CAM). Methods: This retrospective observational study included 136 eyes with BRVO that were followed up for more than a year post-FA. Cropped grayscale images centered on the fovea (200 × 200 pixels) were manually pre-processed from early-phase FA at the acute phase. Pairs of the cropped FA images and the best-corrected visual acuity (BCVA) in remission at least one year post-FA were used to train a 38-layer ResNet with five-fold cross-validation. Correlations between the ResNet-predicted and true (actually measured) logMAR BCVAs in remission, and between the foveal avascular zone (FAZ) area measured by ImageJ (version 1.52r) from FA images and true logMAR BCVA in remission were evaluated. The heat maps generated by Grad-CAM were evaluated to determine which areas were consumed as computational resources for BCVA prediction. Results: The correlation coefficient between the predicted and true logMAR BCVAs in remission was 0.47, and that between the acute-stage FAZ area and true logMAR BCVA in remission was 0.42 (p < 0.0001 for both). The Grad-CAM-generated heat maps showed that retinal vessels adjacent to the FAZ and the FAZ per se had high selectivity (95.7% and 62.2%, respectively). Conclusions: The Grad-CAM-based analysis demonstrated FAZ-neighboring vessels as the most relevant predictor for the long-term visual prognosis of BRVO. [ABSTRACT FROM AUTHOR]

Background: Sepsis is characterized by an atypical immune response to infection and is a dangerous health problem leading to significant mortality. Current diagnostic methods exhibit insufficient sensitivity and specificity and require the discovery of precise biomarkers for the early diagnosis and treatment of sepsis. Platelets, known for their hemostatic abilities, also play an important role in immunological responses. This study aims to develop a model integrating machine learning and explainable artificial intelligence (XAI) to identify novel platelet metabolomics markers of sepsis. Methods: A total of 39 participants, 25 diagnosed with sepsis and 14 control subjects, were included in the study. The profiles of platelet metabolites were analyzed using quantitative 1H-nuclear magnetic resonance (NMR) technology. Data were processed using the synthetic minority oversampling method (SMOTE)-Tomek to address the issue of class imbalance. In addition, missing data were filled using a technique based on random forests. Three machine learning models, namely extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and kernel tree boosting (KTBoost), were used for sepsis prediction. The models were validated using cross-validation. Clinical annotations of the optimal sepsis prediction model were analyzed using SHapley Additive exPlanations (SHAP), an XAI technique. Results: The results showed that the KTBoost model (0.900 accuracy and 0.943 AUC) achieved better performance than the other models in sepsis diagnosis. SHAP results revealed that metabolites such as carnitine, glutamate, and myo-inositol are important biomarkers in sepsis prediction and intuitively explained the prediction decisions of the model. Conclusion: Platelet metabolites identified by the KTBoost model and XAI have significant potential for the early diagnosis and monitoring of sepsis and improving patient outcomes. [ABSTRACT FROM AUTHOR]

Even highly motivated undergraduates drift off their STEM career pathways. In large introductory STEM classes, instructors struggle to identify and support these students. To address these issues, we developed co‐redesign methods in partnership with disciplinary experts to create high‐structure STEM courses that better support students and produce informative digital event data. To those data, we applied theory‐ and context‐relevant labels to reflect active and self‐regulated learning processes involving LMS‐hosted course materials, formative assessments, and help‐seeking tools. We illustrate the predictive benefits of this process across two cycles of model creation and reapplication. In cycle 1, we used theory‐relevant features from 3 weeks of data to inform a prediction model that accurately identified struggling students and sustained its accuracy when reapplied in future semesters. In cycle 2, we refit a model with temporally contextualized features that achieved superior accuracy using data from just two class meetings. This modelling approach can produce durable learning analytics solutions that afford scaled and sustained prediction and intervention opportunities that involve explainable artificial intelligence products. Those same products that inform prediction can also guide intervention approaches and inform future instructional design and delivery.Practitioner notesWhat is already known about this topicLearning analytics includes an evolving collection of methods for tracing and understanding student learning through their engagements with learning technologies.Prediction models based on demographic data can perpetuate systemic biases.Prediction models based on behavioural event data can produce accurate predictions of academic success, and validation efforts can enrich those data to reflect students' self‐regulated learning processes within learning tasks.What this paper addsLearning analytics can be successfully applied to predict performance in an authentic postsecondary STEM context, and the use of context and theory as guides for feature engineering can ensure sustained predictive accuracy upon reapplication.The consistent types of learning resources and cyclical nature of their provisioning from lesson to lesson are hallmarks of high‐structure active learning designs that are known to benefit learners. These designs also provide opportunities for observing and modelling contextually grounded, theory‐aligned and temporally positioned learning events that informed prediction models that accurately classified students upon initial and later reapplications in subsequent semesters.Co‐design relationships where researchers and instructors work together toward pedagogical implementation and course instrumentation are essential to developing unique insights for feature engineering and producing explainable artificial intelligence approaches to predictive modelling.Implications for practice and/or policyHigh‐structure course designs can scaffold student engagement with course materials to make learning more effective and products of feature engineering more explainable.Learning analytics initiatives can avoid perpetuation of systemic biases when methods prioritize theory‐informed behavioural data that reflect learning processes, sensitivity to instructional context and development of explainable predictors of success rather than relying on students' demographic characteristics as predictors.Prioritizing behaviours as predictors improves explainability in ways that can inform the redesign of courses and design of learning supports, which further informs the refinement of learning theories and their applications. [ABSTRACT FROM AUTHOR]

This study investigates the utility of machine learning (ML) in understanding and mitigating winter road risks. Despite their capability in managing complex data structures, ML models often lack interpretability. We address this issue by integrating Shapley Additive exPlanations (SHAP) with a support vector machine (SVM) model. Utilizing a comprehensive dataset of 231 snowstorm events collected in the city of Edmonton across two winter seasons, the SVM model achieved an accuracy rate of 87.2%. Following model development, a SHAP summary plot was employed to identify the contribution of individual features to collision predictions—an insight not achievable through ML alone. Next, SHAP waterfall plots were used to assess the reliability of individual predictions. The findings enhanced our understanding of the complex SVM model and provided greater insights into the diverse factors affecting winter road safety. [ABSTRACT FROM AUTHOR]

Industry 4.0 and deep learning methods have been widely used for output projection in wafer fabrication. Although such applications appeared to be effective, they were difficult to understand and/or improve. Therefore, in this study, an Industry 4.0 and explainable artificial intelligence (XAI) approach is proposed to enhance the interpretability of a deep learning application for output projection. First, a deep neural network (DNN) is constructed to estimate the output times of jobs based on real-time job, machine, and factory information collected using Industry 4.0 technologies. Then, the DNN is approximated by a random forest (RF) to generate interpretable decision rules. SHAP analysis is also performed to generate local explanations. The proposed methodology has been applied to a real case from a wafer fab. Through the synergy of Industry 4.0 and deep learning, the proposed methodology achieved a satisfactory output projection performance. The MAE was only about two wafer lots. Additionally, user communication was also facilitated since the output projection mechanism using deep learning has been explained using XAI techniques. [ABSTRACT FROM AUTHOR]

This paper evaluates the effectiveness of different decoder architectures in enhancing the reconstruction quality of Capsule Neural Networks (CapsNets), which impacts model interpretability. We compared linear, convolutional, and residual decoders to assess their performance in improving CapsNet reconstructions. Our experiments revealed that the Conditional Variational Autoencoder Capsule Network (CVAECapOSR) achieved the best reconstruction quality on the CIFAR-10 dataset, while the residual decoder outperformed others on the Brain Tumor MRI dataset. These findings highlight how improved decoder architectures can generate reconstructions of better quality, which can enhance changes by deforming output capsules, thereby making the feature extraction and classification processes within CapsNets more transparent and interpretable. Additionally, we evaluated the computational efficiency and scalability of each decoder, providing insights into their practical deployment in real-world applications such as medical diagnostics and autonomous driving. [ABSTRACT FROM AUTHOR]

Underground CO2 storage is crucial for sustainability as it reduces greenhouse gas (GHG) emissions, helping mitigate climate change and protect the environment. This research explores the use of Explainable Artificial Intelligence (XAI) to enhance the predictive modelling of CO2 solubility in brine solutions. Employing Random Forest (RF) models, the study integrates Shapley Additive exPlanations (SHAP) analysis to uncover the complex relationships between key variables, including pressure (P), temperature (T), salinity, and ionic composition. Our findings indicate that while P and T are primary factors, the contributions of salinity and specific ions, notably chloride ions (Cl−), are essential for accurate predictions. The RF model exhibited high accuracy, precision, and stability, effectively predicting CO2 solubility even for brines not included during the model training as evidenced by R2 values greater than 0.96 for the validation and testing samples. Additionally, the stability assessment showed that the Root Mean Squared Error (RMSE) spans between 8.4 and 9.0 for 100 different randomness, which shows good stability. SHAP analysis provided valuable insights into feature contributions and interactions, revealing complex dependencies, particularly between P and ionic strength. These insights offer practical guidelines for optimising CO2 storage and mitigating associated risks. By improving the accuracy and transparency of CO2 solubility predictions, this research supports more effective and sustainable CO2 storage strategies, contributing to the overall goal of reducing greenhouse gas emissions and combating climate change. [ABSTRACT FROM AUTHOR]

Visual inspection tasks often require humans to cooperate with artificial intelligence (AI)‐based image classifiers. To enhance this cooperation, explainable artificial intelligence (XAI) can highlight those image areas that have contributed to an AI decision. However, the literature on visual cueing suggests that such XAI support might come with costs of its own. To better understand how the benefits and cost of XAI depend on the accuracy of AI classifications and XAI highlights, we conducted two experiments that simulated visual quality control in a chocolate factory. Participants had to decide whether chocolate molds contained faulty bars or not, and were always informed whether the AI had classified the mold as faulty or not. In half of the experiment, they saw additional XAI highlights that justified this classification. While XAI speeded up performance, its effects on error rates were highly dependent on (X)AI accuracy. XAI benefits were observed when the system correctly detected and highlighted the fault, but XAI costs were evident for misplaced highlights that marked an intact area while the actual fault was located elsewhere. Eye movement analyses indicated that participants spent less time searching the rest of the mold and thus looked at the fault less often. However, we also observed large interindividual differences. Taken together, the results suggest that despite its potentials, XAI can discourage people from investing effort into their own information analysis. [ABSTRACT FROM AUTHOR]

Although artificial intelligence has become part of everyone's real life, a trust crisis against such systems is occurring, thus increasing the need to explain black-box predictions, especially in the military, medical, and financial domains. Modern eXplainable Artificial Intelligence (XAI) techniques focus on benchmark datasets, but the cognitive applicability of such solutions under big data settings is still unclear due to memory or computation constraints. In this paper, we extend a model-agnostic XAI methodology, named Cluster-Aided Space Transformation for Local Explanation (CASTLE), to be able to deal with high-volume datasets. CASTLE aims to explain the black-box behavior of predictive models by combining both local (i.e., based on the input sample) and global (i.e., based on the whole scope for action of the model) information. In particular, the local explanation provides a rule-based explanation for the prediction of a target instance as well as the directions to update the likelihood of the predicted class. Our extension leverages modern big data technologies (e.g., Apache Spark) to handle the high volume, variety, and velocity of huge datasets. We have evaluated the framework on five datasets, in terms of temporal efficiency, explanation quality, and model significance. Our results indicate that the proposed approach retains the high-quality explanations associated with CASTLE while efficiently handling large datasets. Importantly, it exhibits a sub-linear, rather than exponential, dependence on dataset size, making it a scalable solution for massive datasets or in any big data scenario. [ABSTRACT FROM AUTHOR]

Various industries and fields have utilized machine learning models, particularly those that demand a significant degree of accountability and transparency. With the introduction of the General Data Protection Regulation (GDPR), it has become imperative for machine learning model predictions to be both plausible and verifiable. One approach to explaining these predictions involves assigning an importance score to each input element. Another category aims to quantify the importance of human-understandable concepts to explain global and local model behaviours. The way concepts are constructed in such concept-based explanation techniques lacks inherent interpretability. Additionally, the magnitude and diversity of the discovered concepts make it difficult for machine learning practitioners to comprehend and make sense of the concept space. To this end, we introduce ConceptGlassbox, a novel local explanation framework that seeks to learn high-level transparent concept definitions. Our approach leverages human knowledge and feedback to facilitate the acquisition of concepts with minimal human labelling effort. The ConceptGlassbox learns concepts consistent with the user's understanding of a concept's meaning. It then dissects the evidence for the prediction by identifying the key concepts the black-box model uses to arrive at its decision regarding the instance being explained. Additionally, ConceptGlassbox produces counterfactual explanations, proposing the smallest changes to the instance's concept-based explanation that would result in a counterfactual decision as specified by the user. Our systematic experiments confirm that ConceptGlassbox successfully discovers relevant and comprehensible concepts that are important for neural network predictions. [ABSTRACT FROM AUTHOR]

The accuracy and flexibility of Deep Convolutional Neural Networks (DCNNs) have been highly validated over the past years. However, their intrinsic opaqueness is still affecting their reliability and limiting their application in critical production systems, where the black-box behavior is difficult to be accepted. This work proposes EBAnO, an innovative explanation framework able to analyze the decision-making process of DCNNs in image classification by providing prediction-local and class-based model-wise explanations through the unsupervised mining of knowledge contained in multiple convolutional layers. EBAnO provides detailed visual and numerical explanations thanks to two specific indexes that measure the features' influence and their influence precision in the decision-making process. The framework has been experimentally evaluated, both quantitatively and qualitatively, by (i) analyzing its explanations with four state-of-the-art DCNN architectures, (ii) comparing its results with three state-of-the-art explanation strategies and (iii) assessing its effectiveness and easiness of understanding through human judgment, by means of an online survey. EBAnO has been released as open-source code and it is freely available online. [ABSTRACT FROM AUTHOR]

In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation criteria have been developed within the research field of explainable artificial intelligence (XAI). With the amount of XAI methods vastly growing, a taxonomy of methods is needed by researchers as well as practitioners: To grasp the breadth of the topic, compare methods, and to select the right XAI method based on traits required by a specific use-case context. Many taxonomies for XAI methods of varying level of detail and depth can be found in the literature. While they often have a different focus, they also exhibit many points of overlap. This paper unifies these efforts and provides a complete taxonomy of XAI methods with respect to notions present in the current state of research. In a structured literature analysis and meta-study, we identified and reviewed more than 50 of the most cited and current surveys on XAI methods, metrics, and method traits. After summarizing them in a survey of surveys, we merge terminologies and concepts of the articles into a unified structured taxonomy. Single concepts therein are illustrated by more than 50 diverse selected example methods in total, which we categorize accordingly. The taxonomy may serve both beginners, researchers, and practitioners as a reference and wide-ranging overview of XAI method traits and aspects. Hence, it provides foundations for targeted, use-case-oriented, and context-sensitive future research. [ABSTRACT FROM AUTHOR]

With the increased availability of chemical data in public databases, innovative techniques and algorithms have emerged for the analysis, exploration, visualization, and extraction of information from these data. One such technique is chemical grouping, where chemicals with common characteristics are categorized into distinct groups based on physicochemical properties, use, biological activity, or a combination. However, existing tools for chemical grouping often require specialized programming skills or the use of commercial software packages. To address these challenges, we developed a user-friendly chemical grouping workflow implemented in KNIME, a free, open-source, low/no-code, data analytics platform. The workflow serves as an all-encompassing tool, expertly incorporating a range of processes such as molecular descriptor calculation, feature selection, dimensionality reduction, hyperparameter search, and supervised and unsupervised machine learning methods, enabling effective chemical grouping and visualization of results. Furthermore, we implemented tools for interpretation, identifying key molecular descriptors for the chemical groups, and using natural language summaries to clarify the rationale behind these groupings. The workflow was designed to run seamlessly in both the KNIME local desktop version and KNIME Server WebPortal as a web application. It incorporates interactive interfaces and guides to assist users in a step-by-step manner. We demonstrate the utility of this workflow through a case study using an eye irritation and corrosion dataset. Scientific contributions This work presents a novel, comprehensive chemical grouping workflow in KNIME, enhancing accessibility by integrating a user-friendly graphical interface that eliminates the need for extensive programming skills. This workflow uniquely combines several features such as automated molecular descriptor calculation, feature selection, dimensionality reduction, and machine learning algorithms (both supervised and unsupervised), with hyperparameter optimization to refine chemical grouping accuracy. Moreover, we have introduced an innovative interpretative step and natural language summaries to elucidate the underlying reasons for chemical groupings, significantly advancing the usability of the tool and interpretability of the results. [ABSTRACT FROM AUTHOR]

Even if the SARS-CoV-2 pandemic recedes, research regarding the effectiveness of government policies to contain the spread of the pandemic remains important. In this study, we analyze the impact of a set of epidemiological factors on the spread of SARS-CoV-2 in 30 European countries, which were applied from early 2020 up to mid-2022. We combine four data sets encompassing each country's non-pharmaceutical interventions (NPIs, including 66 government intervention types), distributions of 31 virus types, and accumulated percentage of vaccinated population (by the first five doses) as well as the reported infections, each on a daily basis. First, a Bayesian deep learning model is trained to predict the reproduction rate of the virus one month ahead of each day. Based on the trained deep learning model, the importance of relevant influencing factors and the magnitude of their effects on the outcome of the neural network model are computed by applying explainable machine learning algorithms. Second, in order to re-examine the results of the deep learning model, a Bayesian statistical analysis is implemented. In the statistical analysis, for each influencing input factor in each country, the distributions of pandemic growth rates are compared for days where the factor was active with days where the same factor was not active. The results of the deep learning model and the results of the statistical inference model coincide to a significant extent. We conclude with reflections with regard to the most influential factors on SARS-CoV-2 spread within European countries. [ABSTRACT FROM AUTHOR]

A recent global health crisis, COVID-19 is a significant global health crisis that has profoundly affected lifestyles. The detection of such diseases from similar thoracic anomalies using medical images is a challenging task. Thus, the requirement of an end-to-end automated system is vastly necessary in clinical treatments. In this way, the work proposes a Squeeze-and-Excitation Attention-based ResNet50 (SEA-ResNet50) model for detecting COVID-19 utilizing chest X-ray data. Here, the idea lies in improving the residual units of ResNet50 using the squeeze-and-excitation attention mechanism. For further enhancement, the Ranger optimizer and adaptive Mish activation function are employed to improve the feature learning of the SEA-ResNet50 model. For evaluation, two publicly available COVID-19 radiographic datasets are utilized. The chest X-ray input images are augmented during experimentation for robust evaluation against four output classes namely normal, pneumonia, lung opacity, and COVID-19. Then a comparative study is done for the SEA-ResNet50 model against VGG-16, Xception, ResNet18, ResNet50, and DenseNet121 architectures. The proposed framework of SEA-ResNet50 together with the Ranger optimizer and adaptive Mish activation provided maximum classification accuracies of 98.38% (multiclass) and 99.29% (binary classification) as compared with the existing CNN architectures. The proposed method achieved the highest Kappa validation scores of 0.975 (multiclass) and 0.98 (binary classification) over others. Furthermore, the visualization of the saliency maps of the abnormal regions is represented using the explainable artificial intelligence (XAI) model, thereby enhancing interpretability in disease diagnosis. [ABSTRACT FROM AUTHOR]

Combined pulmonary fibrosis and emphysema (CPFE) presents a unique challenge in respiratory disorders, merging features of interstitial lung disease (ILD) and chronic obstructive pulmonary disease (COPD). Using the random forest algorithm, our study thoroughly examines the molecular details of CPFE. Analyzing gene expression datasets from GSE47460 (ILD: 254, COPD: 220, control: 108), we identify key genes namely ADRB2, CDH3, IRS2, MATN3, CD38, PDIA4, VEGFC, and among twenty others, crucial in airway regulation, lung function, and apoptosis, shaping the complex pathogenesis of CPFE. Additionally, miRNAs (hsa-mir-101-3p, hsa-mir-1343-3p, hsa-mir-27a-3p, and miR-16-5p) showcase regulatory impacts on CPFE-related molecular pathways. Our machine learning model unveils these intricate interactions, offering a comprehensive insight into CPFE's molecular mechanisms. This research not only pinpoints potential therapeutic targets and biomarkers but also opens avenues for innovative approaches in managing CPFE, linking ILD and COPD within this complex respiratory condition. [ABSTRACT FROM AUTHOR]

The global prevalence of cardiovascular diseases (CVDs) as a leading cause of death highlights the imperative need for refined risk assessment and prognostication methods. The traditional approaches, including the Framingham Risk Score, blood tests, imaging techniques, and clinical assessments, although widely utilized, are hindered by limitations such as a lack of precision, the reliance on static risk variables, and the inability to adapt to new patient data, thereby necessitating the exploration of alternative strategies. In response, this study introduces CardioRiskNet, a hybrid AI-based model designed to transcend these limitations. The proposed CardioRiskNet consists of seven parts: data preprocessing, feature selection and encoding, eXplainable AI (XAI) integration, active learning, attention mechanisms, risk prediction and prognosis, evaluation and validation, and deployment and integration. At first, the patient data are preprocessed by cleaning the data, handling the missing values, applying a normalization process, and extracting the features. Next, the most informative features are selected and the categorical variables are converted into a numerical form. Distinctively, CardioRiskNet employs active learning to iteratively select informative samples, enhancing its learning efficacy, while its attention mechanism dynamically focuses on the relevant features for precise risk prediction. Additionally, the integration of XAI facilitates interpretability and transparency in the decision-making processes. According to the experimental results, CardioRiskNet demonstrates superior performance in terms of accuracy, sensitivity, specificity, and F1-Score, with values of 98.7%, 98.7%, 99%, and 98.7%, respectively. These findings show that CardioRiskNet can accurately assess and prognosticate the CVD risk, demonstrating the power of active learning and AI to surpass the conventional methods. Thus, CardioRiskNet's novel approach and high performance advance the management of CVDs and provide healthcare professionals a powerful tool for patient care. [ABSTRACT FROM AUTHOR]

Random forest is a powerful ensemble learning technique celebrated for its heightened predictive performance and robustness in handling complex datasets; nevertheless, it is criticized for its computational expense, particularly with a large number of trees in the ensemble. Moreover, the model's interpretability diminishes as the ensemble's complexity increases, presenting challenges in understanding the decision-making process. Although various pruning techniques have been proposed by researchers to tackle these issues, achieving a consensus on the optimal strategy across diverse datasets remains elusive. In response to these challenges, this paper introduces an innovative machine learning algorithm that integrates random forest with Naïve Bayes to predict student performance. The proposed method employs the Naïve Bayes formula to evaluate random forest branches, classifying data by prioritizing branches based on importance and assigning each example to a single branch for classification. The algorithm is utilized on two sets of student data and is evaluated against seven alternative machine-learning algorithms. The results confirm its strong performance, characterized by a minimal number of branches. [ABSTRACT FROM AUTHOR]

Global patterns in soil microbiomes are driven by non‐linear environmental thresholds. Fertilization is known to shape the soil microbiome of terrestrial ecosystems worldwide. Yet, whether fertilization influences global thresholds in soil microbiomes remains virtually unknown. Here, utilizing optimized machine learning models with Shapley additive explanations on a dataset of 10,907 soil samples from 24 countries, we discovered that the microbial community response to fertilization is highly dependent on environmental contexts. Furthermore, the interactions among nitrogen (N) addition, pH, and mean annual temperature contribute to non‐linear patterns in soil bacterial diversity. Specifically, we observed positive responses within a soil pH range of 5.2–6.6, with the influence of higher temperature (>15°C) on bacterial diversity being positive within this pH range but reversed in more acidic or alkaline soils. Additionally, we revealed the threshold effect of soil organic carbon and total nitrogen, demonstrating how temperature and N addition amount interacted with microbial communities within specific edaphic concentration ranges. Our findings underscore how complex environmental interactions control soil bacterial diversity under fertilization. [ABSTRACT FROM AUTHOR]

The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex correlations. Gradient-based methodologies, exemplified by Integrated Gradients (IG), effectively demonstrate the significance of these features. Nevertheless, the conversion of these explanations into images frequently yields considerable noise. Presently, we introduce GAD (Gradient Artificial Distancing) as a supportive framework for gradient-based techniques. Its primary objective is to accentuate influential regions by establishing distinctions between classes. The essence of GAD is to limit the scope of analysis during visualization and, consequently reduce image noise. Empirical investigations involving occluded images have demonstrated that the identified regions through this methodology indeed play a pivotal role in facilitating class differentiation. • We propose GAD method to simplify explanations, providing easy-to-interpret maps. • Our gradient-based method focuses on revealing feature importance in CNNs. • GAD minimizes noise in explanations compared to usual gradient-based techniques. • Class distinction is enhanced thanks to our method. • Empirical results show that GAD locates decisive image areas for classification. [ABSTRACT FROM AUTHOR]

Providing rich and accurate metadata for indexing media content is a crucial problem for all the companies offering streaming entertainment services. These metadata are commonly employed to enhance search engine results and feed recommendation algorithms to improve the matching with user interests. However, the problem of labeling multimedia content with informative tags is challenging as the labeling procedure, manually performed by domain experts, is time-consuming and prone to error. Recently, the adoption of AI-based methods has been demonstrated to be an effective approach for automating this complex process. However, developing an effective solution requires coping with different challenging issues, such as data noise and the scarcity of labeled examples during the training phase. In this work, we address these challenges by introducing a Transformer-based framework for multi-modal multi-label classification enriched with model prediction explanation capabilities. These explanations can help the domain expert to understand the system's predictions. Experimentation conducted on two real test cases demonstrates its effectiveness. [ABSTRACT FROM AUTHOR]

In the rapidly evolving field of real estate economics, the prediction of house prices continues to be a complex challenge, intricately tied to a multitude of socio-economic factors. Traditional predictive models often overlook spatial interdependencies that significantly influence housing prices. The objective of this study is to leverage Graph Neural Networks (GNNs) on open statistics knowledge graphs to model these spatial dependencies and predict house prices across Scotland's 2011 data zones. The methodology involves retrieving integrated statistical indicators from the official Scottish Open Government Data portal and applying three representative GNN algorithms: ChebNet, GCN, and GraphSAGE. These GNNs are compared against traditional models, including the tabular-based XGBoost and a simple Multi-Layer Perceptron (MLP), demonstrating superior prediction accuracy. Innovative contributions of this study include the use of GNNs to model spatial dependencies in real estate economics and the application of local and global explainability techniques to enhance transparency and trust in the predictions. The global feature importance is determined by a logistic regression surrogate model while the local, region-level understanding of the GNN predictions is achieved through the use of GNNExplainer. Explainability results are compared with those from a previous work that applied the XGBoost machine learning algorithm and the SHapley Additive exPlanations (SHAP) explainability framework on the same dataset. Interestingly, both the global surrogate model and the SHAP approach underscored the comparative illness factor, a health indicator, and the ratio of detached dwellings as the most crucial features in the global explainability. In the case of local explanations, while both methods showed similar results, the GNN approach provided a richer, more comprehensive understanding of the predictions for two specific data zones. [ABSTRACT FROM AUTHOR]

This study explores a multi-modal machine-learning-based approach to classify solitary pulmonary nodules (SPNs). Non-small cell lung cancer (NSCLC), presenting primarily as SPNs, is the leading cause of cancer-related deaths worldwide. Early detection and appropriate management of SPNs are critical to improving patient outcomes, necessitating efficient diagnostic methodologies. While CT and PET scans are pivotal in the diagnostic process, their interpretation remains prone to human error and delays in treatment implementation. This study proposes a machine-learning-based network to mitigate these concerns, integrating CT, PET, and manually extracted features in a multi-modal manner by integrating multiple image modalities and tabular features). CT and PET images are classified by a VGG19 network, while additional SPN features in combination with the outputs of VGG19 are processed by an XGBoost model to perform the ultimate diagnosis. The proposed methodology is evaluated using patient data from the Department of Nuclear Medicine of the University Hospital of Patras in Greece. We used 402 patient cases with human annotations to internally validate the model and 96 histopathological-confirmed cases for external evaluation. The model exhibited 97% agreement with the human readers and 85% diagnostic performance in the external set. It also identified the VGG19 predictions from CT and PET images, SUVmax, and diameter as key malignancy predictors. The study suggests that combining all available image modalities and SPN characteristics improves the agreement of the model with the human readers and the diagnostic efficiency. [ABSTRACT FROM AUTHOR]

Ensemble learning is a strategy commonly used to fuse different base models by creating a model ensemble that is expected more accurate on unseen data than the base models. This study describes a new cyber-threat detection method, called PANACEA, that uses ensemble learning coupled with adversarial training in deep learning, in order to gain accuracy with neural models trained in cybersecurity problems. The selection of the base models is one of the main challenges to handle, in order to train accurate ensembles. This study describes a model ensemble pruning approach based on eXplainable AI (XAI) to increase the ensemble diversity and gain accuracy in ensemble classification. We base on the idea that being able to identify base models that give relevance to different input feature sub-spaces may help in improving the accuracy of an ensemble trained to recognise different signatures of different cyber-attack patterns. To this purpose, we use a global XAI technique to measure the ensemble model diversity with respect to the effect of the input features on the accuracy of the base neural models combined in the ensemble. Experiments carried out on four benchmark cybersecurity datasets (three network intrusion detection datasets and one malware detection dataset) show the beneficial effects of the proposed combination of adversarial training, ensemble learning and XAI on the accuracy of multi-class classifications of cyber-data achieved by the neural model ensemble. [ABSTRACT FROM AUTHOR]

As engine monitoring data has become more complex with an increasing number of sensors, fault prediction based on artificial intelligence (AI) has emerged. Existing fault prediction models using AI significantly improve the accuracy of predictions by effectively handling such complex data, but at the same time, the problem arises that the AI-based models cannot explain the rationale of their predictions to users. To address this issue, we propose a time-series explanatory fault prediction framework to provide an explainability even when using AI-based fault prediction models. It consists of a data feature reduction process, a fault prediction model training process using long short-term memory, and an interpretation process of the fault prediction model via an explainable AI method. In particular, the proposed framework can explain a fault prediction based on time-series data. Therefore, it indicates which part of the data was significant for the fault prediction not only in terms of sensor type but also in terms of time. Through extensive experiments, we evaluate the proposed framework using various fault data by comparing the prediction performance of fault prediction and by assessing how well the main pre-symptoms of the fault are extracted when predicting a fault. [ABSTRACT FROM AUTHOR]

AbstractSaliency maps can explain how deep neural networks classify images. But are they actually useful for humans? The present systematic review of 68 user studies found that while saliency maps can enhance human performance, null effects or even costs are quite common. To investigate what modulates these effects, the empirical outcomes were organised along several factors related to the human tasks, AI performance, XAI methods, images to be classified, human participants and comparison conditions. In image-focused tasks, benefits were less common than in AI-focused tasks, but the effects depended on the specific cognitive requirements. AI accuracy strongly modulated the outcomes, while XAI-related factors had surprisingly little impact. The evidence was limited for image- and human-related factors and the effects were highly dependent on the comparisons. These findings may support the design of future user studies by focusing on the conditions under which saliency maps can potentially be useful. [ABSTRACT FROM AUTHOR]

Background: Tuberculosis spondylitis (TS), commonly known as Pott's disease, is a severe type of skeletal tuberculosis that typically requires surgical treatment. However, this treatment option has led to an increase in healthcare costs due to prolonged hospital stays (PLOS). Therefore, identifying risk factors associated with extended PLOS is necessary. In this research, we intended to develop an interpretable machine learning model that could predict extended PLOS, which can provide valuable insights for treatments and a web-based application was implemented. Methods: We obtained patient data from the spine surgery department at our hospital. Extended postoperative length of stay (PLOS) refers to a hospitalization duration equal to or exceeding the 75th percentile following spine surgery. To identify relevant variables, we employed several approaches, such as the least absolute shrinkage and selection operator (LASSO), recursive feature elimination (RFE) based on support vector machine classification (SVC), correlation analysis, and permutation importance value. Several models using implemented and some of them are ensembled using soft voting techniques. Models were constructed using grid search with nested cross-validation. The performance of each algorithm was assessed through various metrics, including the AUC value (area under the curve of receiver operating characteristics) and the Brier Score. Model interpretation involved utilizing methods such as Shapley additive explanations (SHAP), the Gini Impurity Index, permutation importance, and local interpretable model-agnostic explanations (LIME). Furthermore, to facilitate the practical application of the model, a web-based interface was developed and deployed. Results: The study included a cohort of 580 patients and 11 features include (CRP, transfusions, infusion volume, blood loss, X-ray bone bridge, X-ray osteophyte, CT-vertebral destruction, CT-paravertebral abscess, MRI-paravertebral abscess, MRI-epidural abscess, postoperative drainage) were selected. Most of the classifiers showed better performance, where the XGBoost model has a higher AUC value (0.86) and lower Brier Score (0.126). The XGBoost model was chosen as the optimal model. The results obtained from the calibration and decision curve analysis (DCA) plots demonstrate that XGBoost has achieved promising performance. After conducting tenfold cross-validation, the XGBoost model demonstrated a mean AUC of 0.85 ± 0.09. SHAP and LIME were used to display the variables' contributions to the predicted value. The stacked bar plots indicated that infusion volume was the primary contributor, as determined by Gini, permutation importance (PFI), and the LIME algorithm. Conclusions: Our methods not only effectively predicted extended PLOS but also identified risk factors that can be utilized for future treatments. The XGBoost model developed in this study is easily accessible through the deployed web application and can aid in clinical research. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) algorithms offer a powerful tool for capturing multifaceted relationships through inductive research to gain insights and support decision-making in practice. This study contributes to understanding the dilemma whereby the more complex ML becomes, the more its value proposition can be compromised by its opacity. Using a longitudinal dataset on voluntary employee turnover from a German federal agency, we provide evidence for the underlying trade-off between predictive performance and transparency for ML, which has not been found in similar Human Resource Management (HRM) studies using artificially simulated datasets. We then propose measures to mitigate this trade-off by demonstrating the use of post-hoc explanatory methods to extract local (employee-specific) and global (organisation-wide) predictor effects. After that, we discuss their limitations, providing a nuanced perspective on the circumstances under which the use of post-hoc explanatory methods is justified. Namely, when a 'transparency-by-design' approach with traditional linear regression is not sufficient to solve HRM prediction tasks, the translation of complex ML models into human-understandable visualisations is required. As theoretical implications, this paper suggests that we can only fully understand the multi-layered HR phenomena explained to us by real-world data if we incorporate ML-based inductive methods together with traditional deductive methods. [ABSTRACT FROM AUTHOR]

Artificial intelligence algorithms have become extensively utilized in survival analysis for high-dimensional, multi-source data. However, due to their complexity, these methods often yield poorly interpretable outcomes, posing challenges in the analysis of several conditions. One of these conditions is obstructive sleep apnea, a sleep disorder characterized by the simultaneous occurrence of comorbidities. Survival analysis provides a potential solution for assessing and categorizing the severity of obstructive sleep apnea, aiding personalized treatment strategies. Given the critical role of time in such scenarios and considering limitations in model interpretability, time-dependent explainable artificial intelligence algorithms have been developed in recent years for direct application to basic Machine Learning models, such as Cox regression and survival random forest. Our work aims to enhance model selection in OSA survival analysis using time-dependent XAI for Machine Learning and Deep Learning models. We developed an end-to-end pipeline, training several survival models and selecting the best performers. Our top models—Cox regression, Cox time, and logistic hazard—achieved good performance, with C-index scores of 0.81, 0.78, and 0.77, and Brier scores of 0.10, 0.12, and 0.11 on the test set. We applied SurvSHAP methods to Cox regression and logistic hazard to investigate their behavior. Although the models showed similar performance, our analysis established that the results of the log hazard model were more reliable and useful in clinical practice compared to those of Cox regression in OSA scenarios. [ABSTRACT FROM AUTHOR]

Our research systematically investigates the cognitive and emotional processes revealed through eye movements within the context of virtual reality (VR) environments. We assess the utility of eye-tracking data for predicting emotional states in VR, employing explainable artificial intelligence (XAI) to advance the interpretability and transparency of our findings. Utilizing the VR Eyes: Emotions dataset (VREED) alongside an extra trees classifier enhanced by SHapley Additive ExPlanations (SHAP) and local interpretable model agnostic explanations (LIME), we rigorously evaluate the importance of various eye-tracking metrics. Our results identify significant correlations between metrics such as saccades, micro-saccades, blinks, and fixations and specific emotional states. The application of SHAP and LIME elucidates these relationships, providing deeper insights into the emotional responses triggered by VR. These findings suggest that variations in eye feature patterns serve as indicators of heightened emotional arousal. Not only do these insights advance our understanding of affective computing within VR, but they also highlight the potential for developing more responsive VR systems capable of adapting to user emotions in real-time. This research contributes significantly to the fields of human-computer interaction and psychological research, showcasing how XAI can bridge the gap between complex machine-learning models and practical applications, thereby facilitating the creation of reliable, user-sensitive VR experiences. Future research may explore the integration of multiple physiological signals to enhance emotion detection and interactive dynamics in VR. [ABSTRACT FROM AUTHOR]

Inhibiting the enzymes carbonic anhydrase I (CA I) and carbonic anhydrase II (CA II) presents a potential avenue for addressing nervous system ailments such as glaucoma and Alzheimer's disease. Our study explored harnessing explainable artificial intelligence (XAI) to unveil the molecular traits inherent in CA I and CA II inhibitors. The PubChem molecular fingerprints of these inhibitors, sourced from the ChEMBL database, were subjected to detailed XAI analysis. The study encompassed training 10 regression models using IC50 values, and their efficacy was gauged using metrics including R2, RMSE, and time taken. The Decision Tree Regressor algorithm emerged as the optimal performer (R2: 0.93, RMSE: 0.43, time‐taken: 0.07). Furthermore, the PFI method unveiled key molecular features for CA I inhibitors, notably PubChemFP432 (C(O)N) and PubChemFP6978 (C(O)O). The SHAP analysis highlighted the significance of attributes like PubChemFP539 (C(O)NCC), PubChemFP601 (C(O)OCC), and PubChemFP432 (C(O)N) in CA I inhibitiotable n. Likewise, features for CA II inhibitors encompassed PubChemFP528(C(O)OCCN), PubChemFP791 (C(O)OCCC), PubChemFP696 (C(O)OCCCC), PubChemFP335 (C(O)NCCN), PubChemFP580 (C(O)NCCCN), and PubChemFP180 (C(O)NCCC), identified through SHAP analysis. The sulfonamide group (S), aromatic ring (A), and hydrogen bonding group (H) exert a substantial impact on CA I and CA II enzyme activities and IC50 values through the XAI approach. These insights into the CA I and CA II inhibitors are poised to guide future drug discovery efforts, serving as a beacon for innovative therapeutic interventions. [ABSTRACT FROM AUTHOR]

We aim to use topic modeling, an approach for discovering clusters of related words ("topics"), to predict symptom severity and therapeutic alliance in psychotherapy transcripts, while also identifying the most important topics and overarching themes for prediction. We analyzed 552 psychotherapy transcripts from 124 patients. Using BERTopic (Grootendorst, 2022), we extracted 250 topics each for patient and therapist speech. These topics were used to predict symptom severity and alliance with various competing machine-learning methods. Sensitivity analyses were calculated for a model based on 50 topics, LDA-based topic modeling, and a bigram model. Additionally, we grouped topics into themes using qualitative analysis and identified key topics and themes with eXplainable Artificial Intelligence (XAI). Symptom severity could be predicted with highest accuracy by patient topics (r =0.45, 95%-CI 0.40, 0.51), whereas alliance was better predicted by therapist topics (r =0.20, 95%-CI 0.16, 0.24). Drivers for symptom severity were themes related to health and negative experiences. Lower alliance was correlated with various themes, especially psychotherapy framework, income, and everyday life. This analysis shows the potential of using topic modeling in psychotherapy research allowing to predict several treatment-relevant metrics with reasonable accuracy. Further, the use of XAI allows for an analysis of the individual predictive value of topics and themes. Limitations entail heterogeneity across different topic modeling hyperparameters and a relatively small sample size. [ABSTRACT FROM AUTHOR]

Battery characterization and prognosis are essential for analyzing underlying electrochemical mechanisms and ensuring safe operation, especially with the assistance of superior data‐driven artificial intelligence systems. This review provides a unique perspective on recent progress in data‐driven battery characterization and prognosis methods. First, recent informative image characterization and impedance spectrum as well as high‐throughput screening approaches on revealing battery electrochemical mechanisms at multiple scales are summarized. Thereafter, battery prognosis tasks and strategies are described, with the comparison of various physics‐informed modeling strategies. Considering unlocking mechanisms from tremendous battery data, the dominant role of physics‐informed interpretable learning in accelerating energy device development is presented. Finally, challenges and prospects on data‐driven characterization and prognosis are discussed toward accelerating energy device development with much‐enhanced electrochemical transparency and generalization. This review is hoped to supply new ideas and inspirations to the next‐generation battery development. [ABSTRACT FROM AUTHOR]

Aims: Deep learning holds immense potential for histopathology, automating tasks that are simple for expert pathologists and revealing novel biology for tasks that were previously considered difficult or impossible to solve by eye alone. However, the extent to which the visual strategies learned by deep learning models in histopathological analysis are trustworthy or not has yet to be systematically analysed. Here, we systematically evaluate deep neural networks (DNNs) trained for histopathological analysis in order to understand if their learned strategies are trustworthy or deceptive. Methods and results: We trained a variety of DNNs on a novel data set of 221 whole‐slide images (WSIs) from lung adenocarcinoma patients, and evaluated their effectiveness at (1) molecular profiling of KRAS versus EGFR mutations, (2) determining the primary tissue of a tumour and (3) tumour detection. While DNNs achieved above‐chance performance on molecular profiling, they did so by exploiting correlations between histological subtypes and mutations, and failed to generalise to a challenging test set obtained through laser capture microdissection (LCM). In contrast, DNNs learned robust and trustworthy strategies for determining the primary tissue of a tumour as well as detecting and localising tumours in tissue. Conclusions: Our work demonstrates that DNNs hold immense promise for aiding pathologists in analysing tissue. However, they are also capable of achieving seemingly strong performance by learning deceptive strategies that leverage spurious correlations, and are ultimately unsuitable for research or clinical work. The framework we propose for model evaluation and interpretation is an important step towards developing reliable automated systems for histopathological analysis. [ABSTRACT FROM AUTHOR]

One important goal of cognitive science is to understand the mind in terms of its representational and computational capacities, where computational modeling plays an essential role in providing theoretical explanations and predictions of human behavior and mental phenomena. In my research, I have been using computational modeling, together with behavioral experiments and cognitive neuroscience methods, to investigate the information processing mechanisms underlying learning and visual cognition in terms of perceptual representation and attention strategy. In perceptual representation, I have used neural network models to understand how the split architecture in the human visual system influences visual cognition, and to examine perceptual representation development as the results of expertise. In attention strategy, I have developed the Eye Movement analysis with Hidden Markov Models method for quantifying eye movement pattern and consistency using both spatial and temporal information, which has led to novel findings across disciplines not discoverable using traditional methods. By integrating it with deep neural networks (DNN), I have developed DNN+HMM to account for eye movement strategy learning in human visual cognition. The understanding of the human mind through computational modeling also facilitates research on artificial intelligence's (AI) comparability with human cognition, which can in turn help explainable AI systems infer humans' belief on AI's operations and provide human‐centered explanations to enhance human−AI interaction and mutual understanding. Together, these demonstrate the essential role of computational modeling methods in providing theoretical accounts of the human mind as well as its interaction with its environment and AI systems. In this paper, I summarize my research in visual cognition, language processing, and explainable AI to demonstrate the essential role of computational modeling methods in providing theoretical accounts of the human mind as well as its interaction with its environment and AI systems. [ABSTRACT FROM AUTHOR]