Local Interpretable Model-agnostic Explanations Research Articles

Susceptibility Modeling and Potential Risk Analysis of Thermokarst Hazard in Qinghai–Tibet Plateau Permafrost Landscapes Using a New Interpretable Ensemble Learning Method

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

Integrating Structural Causal Model Ontologies with LIME for Fair Machine Learning Explanations in Educational Admissions

This study employed knowledge discovery in databases (KDD) to extract and discover knowledge from the Benue State Polytechnic (Benpoly) admission database and used a structural causal model (SCM) ontological framework to represent the admission process in the Nigerian polytechnic education system. The SCM ontology identified important causal relations in features needed to model the admission process and was validated using the conditional independence test (CIT) criteria. The SCM ontology was further employed to identify and constrain input features causing bias in the local interpretable model-agnostic explanations (LIME) framework applied to machine learning (ML) black-box predictions. The ablation process produced more stable LIME explanations devoid of fairness bias compared to LIME without ablation, with higher prediction accuracy (91% vs. 89%) and F1 scores (95% vs. 94%). The study also compared the performance of different ML models, including Gaussian Naïve Bayes, Decision Trees, and Logistic Regression, before and after ablation. The limitation is that the SCM ontology is qualitative and context-specific, so the fair-LIME framework can only be extrapolated to similar contexts. Future work could compare other explanation frameworks like Shapley on the same dataset. Overall, this study demonstrates a novel approach to enforcing fairness in ML explanations by integrating qualitative SCM ontologies with quantitative ML/LIME methods.

Development of an ensemble CNN model with explainable AI for the classification of gastrointestinal cancer.

The implementation of AI assisted cancer detection systems in clinical environments has faced numerous hurdles, mainly because of the restricted explainability of their elemental mechanisms, even though such detection systems have proven to be highly effective. Medical practitioners are skeptical about adopting AI assisted diagnoses as due to the latter's inability to be transparent about decision making processes. In this respect, explainable artificial intelligence (XAI) has emerged to provide explanations for model predictions, thereby overcoming the computational black box problem associated with AI systems. In this particular research, the focal point has been the exploration of the Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) approaches which enable model prediction explanations. This study used an ensemble model consisting of three convolutional neural networks(CNN): InceptionV3, InceptionResNetV2 and VGG16, which was based on averaging techniques and by combining their respective predictions. These models were trained on the Kvasir dataset, which consists of pathological findings related to gastrointestinal cancer. An accuracy of 96.89% and F1-scores of 96.877% were attained by our ensemble model. Following the training of the ensemble model, we employed SHAP and LIME to analyze images from the three classes, aiming to provide explanations regarding the deterministic features influencing the model's predictions. The results obtained from this analysis demonstrated a positive and encouraging advancement in the exploration of XAI approaches, specifically in the context of gastrointestinal cancer detection within the healthcare domain.

Skin-CAD: Explainable deep learning classification of skin cancer from dermoscopic images by feature selection of dual high-level CNNs features and transfer learning

Skin cancer (SC) significantly impacts many individuals' health all over the globe. Hence, it is imperative to promptly identify and diagnose such conditions at their earliest stages using dermoscopic imaging. Computer-aided diagnosis (CAD) methods relying on deep learning techniques especially convolutional neural networks (CNN) can effectively address this issue with outstanding outcomes. Nevertheless, such black box methodologies lead to a deficiency in confidence as dermatologists are incapable of comprehending and verifying the predictions that were made by these models. This article presents an advanced an explainable artificial intelligence (XAI) based CAD system named “Skin-CAD” which is utilized for the classification of dermoscopic photographs of SC. The system accurately categorises the photographs into two categories: benign or malignant, and further classifies them into seven subclasses of SC. Skin-CAD employs four CNNs of different topologies and deep layers. It gathers features out of a pair of deep layers of every CNN, particularly the final pooling and fully connected layers, rather than merely depending on attributes from a single deep layer. Skin-CAD applies the principal component analysis (PCA) dimensionality reduction approach to minimise the dimensions of pooling layer features. This also reduces the complexity of the training procedure compared to using deep features from a CNN that has a substantial size. Furthermore, it combines the reduced pooling features with the fully connected features of each CNN. Additionally, Skin-CAD integrates the dual-layer features of the four CNNs instead of entirely depending on the features of a single CNN architecture. In the end, it utilizes a feature selection step to determine the most important deep attributes. This helps to decrease the general size of the feature set and streamline the classification process. Predictions are analysed in more depth using the local interpretable model-agnostic explanations (LIME) approach. This method is used to create visual interpretations that align with an already existing viewpoint and adhere to recommended standards for general clarifications. Two benchmark datasets are employed to validate the efficiency of Skin-CAD which are the Skin Cancer: Malignant vs. Benign and HAM10000 datasets. The maximum accuracy achieved using Skin-CAD is 97.2 % and 96.5 % for the Skin Cancer: Malignant vs. Benign and HAM10000 datasets respectively. The findings of Skin-CAD demonstrate its potential to assist professional dermatologists in detecting and classifying SC precisely and quickly.

Explainable artificial intelligence in deep learning–based detection of aortic elongation on chest X-ray images

Abstract Aims Aortic elongation can result from age-related changes, congenital factors, aneurysms, or conditions affecting blood vessel elasticity. It is associated with cardiovascular diseases and severe complications like aortic aneurysms and dissection. We assess qualitatively and quantitatively explainable methods to understand the decisions of a deep learning model for detecting aortic elongation using chest X-ray (CXR) images. Methods and results In this study, we evaluated the performance of deep learning models (DenseNet and EfficientNet) for detecting aortic elongation using transfer learning and fine-tuning techniques with CXR images as input. EfficientNet achieved higher accuracy (86.7% ± 2.1), precision (82.7% ± 2.7), specificity (89.4% ± 1.7), F1 score (82.5% ± 2.9), and area under the receiver operating characteristic (92.7% ± 0.6) but lower sensitivity (82.3% ± 3.2) compared with DenseNet. To gain insights into the decision-making process of these models, we employed gradient-weighted class activation mapping and local interpretable model-agnostic explanations explainability methods, which enabled us to identify the expected location of aortic elongation in CXR images. Additionally, we used the pixel-flipping method to quantitatively assess the model interpretations, providing valuable insights into model behaviour. Conclusion Our study presents a comprehensive strategy for analysing CXR images by integrating aortic elongation detection models with explainable artificial intelligence techniques. By enhancing the interpretability and understanding of the models’ decisions, this approach holds promise for aiding clinicians in timely and accurate diagnosis, potentially improving patient outcomes in clinical practice.

Leveraging explainable AI for informed building retrofit decisions: Insights from a survey

Accurate predictions of building energy consumption are essential for reducing the energy performance gap. While data-driven energy quantification methods based on machine learning deliver promising results, the lack of Explainability prevents their widespread application. To overcome this, Explainable Artificial Intelligence (XAI) was introduced. However, to this point, no research has examined how effective these explanations are concerning decision-makers, i.e., property owners. To address this, we implement three transparent models (Linear Regression, Decision Tree, QLattice) and apply four XAI methods (Partial Dependency Plots, Accumulated Local Effects, Local Interpretable Model-Agnostic Explanations, Shapley Additive Explanations) to an Artificial Neural Network using a real-world dataset of 25,000 residential buildings. We evaluate their Prediction Accuracy and Explainability through a survey with 137 participants considering the human-centered dimensions of explanation satisfaction and perceived fidelity. The results quantify the Explainability-Accuracy trade-off in building energy consumption forecasting and how it can be counteracted by choosing the right XAI method to foster informed retrofit decisions. For research, we set the foundation for further increasing the Explainability of data-driven energy quantification methods and their human-centered evaluation. For practice, we encourage using XAI to reduce the acceptance gap of data-driven methods, whereby the XAI method should be selected carefully, as the Explainability within the methods varies by up to 10 %.

An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease

BackgroundThere is no individualized prediction model for intensive care unit (ICU) admission on patients with community-acquired pneumonia (CAP) and connective tissue disease (CTD) so far. In this study, we aimed to establish a machine learning-based model for predicting the need for ICU admission among those patients.MethodsThis was a retrospective study on patients admitted into a University Hospital in China between November 2008 and November 2021. Patients were included if they were diagnosed with CAP and CTD during admission and hospitalization. Data related to demographics, CTD types, comorbidities, vital signs and laboratory results during the first 24 h of hospitalization were collected. The baseline variables were screened to identify potential predictors via three methods, including univariate analysis, least absolute shrinkage and selection operator (Lasso) regression and Boruta algorithm. Nine supervised machine learning algorithms were used to build prediction models. We evaluated the performances of differentiation, calibration, and clinical utility of all models to determine the optimal model. The Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) techniques were performed to interpret the optimal model.ResultsThe included patients were randomly divided into the training set (1070 patients) and the testing set (459 patients) at a ratio of 70:30. The intersection results of three feature selection approaches yielded 16 predictors. The eXtreme gradient boosting (XGBoost) model achieved the highest area under the receiver operating characteristic curve (AUC) (0.941) and accuracy (0.913) among various models. The calibration curve and decision curve analysis (DCA) both suggested that the XGBoost model outperformed other models. The SHAP summary plots illustrated the top 6 features with the greatest importance, including higher N-terminal pro-B-type natriuretic peptide (NT-proBNP) and C-reactive protein (CRP), lower level of CD4 + T cell, lymphocyte and serum sodium, and positive serum (1,3)-β-D-glucan test (G test).ConclusionWe successfully developed, evaluated and explained a machine learning-based model for predicting ICU admission in patients with CAP and CTD. The XGBoost model could be clinical referenced after external validation and improvement.

Responsible AI for cardiovascular disease detection: Towards a privacy-preserving and interpretable model

Background and objectiveCardiovascular disease (CD) is a major global health concern, affecting millions with symptoms like fatigue and chest discomfort. Timely identification is crucial due to its significant contribution to global mortality. In healthcare, artificial intelligence (AI) holds promise for advancing disease risk assessment and treatment outcome prediction. However, machine learning (ML) evolution raises concerns about data privacy and biases, especially in sensitive healthcare applications. The objective is to develop and implement a responsible AI model for CD prediction that prioritize patient privacy, security, ensuring transparency, explainability, fairness, and ethical adherence in healthcare applications. MethodsTo predict CD while prioritizing patient privacy, our study employed data anonymization involved adding Laplace noise to sensitive features like age and gender. The anonymized dataset underwent analysis using a differential privacy (DP) framework to preserve data privacy. DP ensured confidentiality while extracting insights. Compared with Logistic Regression (LR), Gaussian Naïve Bayes (GNB), and Random Forest (RF), the methodology integrated feature selection, statistical analysis, and SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) for interpretability. This approach facilitates transparent and interpretable AI decision-making, aligning with responsible AI development principles. Overall, it combines privacy preservation, interpretability, and ethical considerations for accurate CD predictions. ResultsOur investigations from the DP framework with LR were promising, with an area under curve (AUC) of 0.848 ± 0.03, an accuracy of 0.797 ± 0.02, precision at 0.789 ± 0.02, recall at 0.797 ± 0.02, and an F1 score of 0.787 ± 0.02, with a comparable performance with the non-privacy framework. The SHAP and LIME based results support clinical findings, show a commitment to transparent and interpretable AI decision-making, and aligns with the principles of responsible AI development. ConclusionsOur study endorses a novel approach in predicting CD, amalgamating data anonymization, privacy-preserving methods, interpretability tools SHAP, LIME, and ethical considerations. This responsible AI framework ensures accurate predictions, privacy preservation, and user trust, underscoring the significance of comprehensive and transparent ML models in healthcare. Therefore, this research empowers the ability to forecast CD, providing a vital lifeline to millions of CD patients globally and potentially preventing numerous fatalities.

A Deep Intelligent Hybrid Intrusion Detection Framework with LIME

Network security has grown to be a major issue as a result of the development of Internet of Things (IoT) devices. Attacks known as Distributed Denial of Service (DDoS) can overwhelm and impair networks. In order to identify DDoS and other network intrusion threats in real-time, accurately, and with justification, this study suggests a unique deep learning-driven fog computing architecture named as Deep Intelligent Hybrid Intrusion Detection Framework with LIME (DIHIF-LIME). The main advancement is the creation of a hybrid intrusion detection system that integrates randomness measurements taken from network traffic with a K-Nearest Neighbor (KNN) machine learning classifier. The justification for predictions is explained using Local Interpretable Model-Agnostic Explanations (LIME), which promotes explainability. Using datasets including network assaults, Long-Short-Term Memory (LSTM) neural networks are created and compared. Utilizing 5-fold cross-validation, LSTM outperformed benchmarks with the maximum accuracy of 99.97%. In conclusion, the proposed fog computing intrusion detection framework with LIME explainability offers a rapid, precise, scalable, and interpretable end-to-end solution from IoT devices to the cloud. A thorough test shows that the method is effective in protecting IoT networks from DDoS and other assaults. The two main advances th­­at are presented are hybrid detection and LIME explainability.

Interpretability-based machine learning for predicting the risk of death from pulmonary inflammation in Chinese intensive care unit patients.

The objective of this research was to create a machine learning predictive model that could be easily interpreted in order to precisely determine the risk of premature death in patients receiving intensive care after pulmonary inflammation. In this study, information from the China intensive care units (ICU) Open Source database was used to examine data from 2790 patients who had infections between January 2019 and December 2020. A 7:3 ratio was used to randomly assign the whole patient population to training and validation groups. This study used six machine learning techniques: logistic regression, random forest, gradient boosting tree, extreme gradient boosting tree (XGBoost), multilayer perceptron, and K-nearest neighbor. A cross-validation grid search method was used to search the parameters in each model. Eight metrics were used to assess the models' performance: accuracy, precision, recall, F1 score, area under the curve (AUC) value, Brier score, Jordon's index, and calibration slope. The machine methods were ranked based on how well they performed in each of these metrics. The best-performing models were selected for interpretation using both the Shapley Additive exPlanations (SHAP) and Local interpretable model-agnostic explanations (LIME) interpretable techniques. A subset of the study cohort's patients (120/1668, or 7.19%) died in the hospital following screening for inclusion and exclusion criteria. Using a cross-validated grid search to evaluate the six machine learning techniques, XGBoost showed good discriminative ability, achieving an accuracy score of 0.889 (0.874-0.904), precision score of 0.871 (0.849-0.893), recall score of 0.913 (0.890-0.936), F1 score of 0.891 (0.876-0.906), and AUC of 0.956 (0.939-0.973). Additionally, XGBoost exhibited excellent performance with a Brier score of 0.050, Jordon index of 0.947, and calibration slope of 1.074. It was also possible to create an interactive internet page using the XGBoost model. By identifying patients at higher risk of early mortality, machine learning-based mortality risk prediction models have the potential to significantly improve patient care by directing clinical decision making and enabling early detection of survival and mortality issues in patients with pulmonary inflammation disease.

Interpretable machine learning model for predicting acute kidney injury in critically ill patients

BackgroundThis study aimed to create a method for promptly predicting acute kidney injury (AKI) in intensive care patients by applying interpretable, explainable artificial intelligence techniques.MethodsPopulation data regarding intensive care patients were derived from the Medical Information Mart for Intensive Care IV database from 2008 to 2019. Machine learning (ML) techniques with six methods were created to construct the predicted models for AKI. The performance of each ML model was evaluated by comparing the areas under the curve (AUC). Local Interpretable Model-Agnostic Explanations (LIME) method and Shapley Additive exPlanation values were used to decipher the best model.ResultsAccording to inclusion and exclusion criteria, 53,150 severely sick individuals were included in the present study, of which 42,520 (80%) were assigned to the training group, and 10,630 (20%) were allocated to the validation group. Compared to the other five ML models, the eXtreme Gradient Boosting (XGBoost) model greatly predicted AKI following ICU admission, with an AUC of 0.816. The top four contributing variables of the XGBoost model were SOFA score, weight, mechanical ventilation, and the Simplified Acute Physiology Score II. An AKI and Non-AKI cases were predicted separately using the LIME algorithm.ConclusionOverall, the constructed clinical feature-based ML models are excellent in predicting AKI in intensive care patients. It would be constructive for physicians to provide early support and timely intervention measures to intensive care patients at risk of AKI.

Classification of Caries Based on CBCT: A Deep Learning Network Interpretability Study.

This study aimed to create a caries classification scheme based on cone-beam computed tomography (CBCT) and develop two deep learning models to improve caries classification accuracy. A total of 2713 axial slices were obtained from CBCT images of 204 carious teeth. Both classification models were trained and tested using the same pretrained classification networks on the dataset, including ResNet50_vd, MobileNetV3_large_ssld, and ResNet50_vd_ssld. The first model was used directly to classify the original images (direct classification model). The second model incorporated a presegmentation step for interpretation (interpretable classification model). Performance evaluation metrics including accuracy, precision, recall, and F1 score were calculated. The Local Interpretable Model-agnostic Explanations (LIME) method was employed to elucidate the decision-making process of the two models. In addition, a minimum distance between caries and pulp was introduced for determining the treatment strategies for type II carious teeth. The direct model that utilized the ResNet50_vd_ssld network achieved top accuracy, precision, recall, and F1 score of 0.700, 0.786, 0.606, and 0.616, respectively. Conversely, the interpretable model consistently yielded metrics surpassing 0.917, irrespective of the network employed. The LIME algorithm confirmed the interpretability of the classification models by identifying key image features for caries classification. Evaluation of treatment strategies for type II carious teeth revealed a significant negative correlation (p < 0.01) with the minimum distance. These results demonstrated that the CBCT-based caries classification scheme and the two classification models appeared to be acceptable tools for the diagnosis and categorization of dental caries.

Creating and validating the Fine-Grained Question Subjectivity Dataset (FQSD): A new benchmark for enhanced automatic subjective question answering systems.

In the domain of question subjectivity classification, there exists a need for detailed datasets that can foster advancements in Automatic Subjective Question Answering (ASQA) systems. Addressing the prevailing research gaps, this paper introduces the Fine-Grained Question Subjectivity Dataset (FQSD), which comprises 10,000 questions. The dataset distinguishes between subjective and objective questions and offers additional categorizations such as Subjective-types (Target, Attitude, Reason, Yes/No, None) and Comparison-form (Single, Comparative). Annotation reliability was confirmed via robust evaluation techniques, yielding a Fleiss's Kappa score of 0.76 and Pearson correlation values up to 0.80 among three annotators. We benchmarked FQSD against existing datasets such as (Yu, Zha, and Chua 2012), SubjQA (Bjerva 2020), and ConvEx-DS (Hernandez-Bocanegra 2021). Our dataset excelled in scale, linguistic diversity, and syntactic complexity, establishing a new standard for future research. We employed visual methodologies to provide a nuanced understanding of the dataset and its classes. Utilizing transformer-based models like BERT, XLNET, and RoBERTa for validation, RoBERTa achieved an outstanding F1-score of 97%, confirming the dataset's efficacy for the advanced subjectivity classification task. Furthermore, we utilized Local Interpretable Model-agnostic Explanations (LIME) to elucidate model decision-making, ensuring transparent and reliable model predictions in subjectivity classification tasks.

Assessment of Hydrological and Meteorological Composite Drought Characteristics Based on Baseflow and Precipitation

Traditional univariate drought indices may not be sufficient to reflect comprehensive information on drought. Therefore, this paper proposes a new composite drought index that can comprehensively characterize meteorological and hydrological drought. In this study, the new drought index was established by combining the standardized precipitation index (SPI) and the standardized baseflow index (SBI) for the Jiaojiang River Basin (JRB) using the copula function. The prediction model was established by training random forests on past data, and the driving force behind the combined drought index was explored through the LIME algorithm. The results show that the established composite drought index combines the advantages of SPI and SBI in drought forecasting. The monthly and annual droughts in the JRB showed an increasing trend from 1991 to 2020, but the temporal characteristics of the changes in each subregion were different. The accuracies of the trained random forest model for heavy drought in Baizhiao (BZA) and Shaduan (SD) stations were 83% and 88%, respectively. Furthermore, the Local Interpretable Model-Agnostic Explanations (LIME) interpretation identified the essential precipitation, baseflow, and evapotranspiration features that affect drought. This study provides reliable and valid multivariate indicators for drought monitoring and can be applied to drought prediction in other regions.

Predicting cervical cancer risk probabilities using advanced H20 AutoML and local interpretable model-agnostic explanation techniques

Background Cancer is positioned as a major disease, particularly for middle-aged people, which remains a global concern that can develop in the form of abnormal growth of body cells at any place in the human body. Cervical cancer, often known as cervix cancer, is cancer present in the female cervix. In the area where the endocervix (upper two-thirds of the cervix) and ectocervix (lower third of the cervix) meet, the majority of cervical cancers begin. Despite an influx of people entering the healthcare industry, the demand for machine learning (ML) specialists has recently outpaced the supply. To close the gap, user-friendly applications, such as H2O, have made significant progress these days. However, traditional ML techniques handle each stage of the process separately; whereas H2O AutoML can automate a major portion of the ML workflow, such as automatic training and tuning of multiple models within a user-defined timeframe. Methods Thus, novel H2O AutoML with local interpretable model-agnostic explanations (LIME) techniques have been proposed in this research work that enhance the predictability of an ML model in a user-defined timeframe. We herein collected the cervical cancer dataset from the freely available Kaggle repository for our research work. The Stacked Ensembles approach, on the other hand, will automatically train H2O models to create a highly predictive ensemble model that will outperform the AutoML Leaderboard in most instances. The novelty of this research is aimed at training the best model using the AutoML technique that helps in reducing the human effort over traditional ML techniques in less amount of time. Additionally, LIME has been implemented over the H2O AutoML model, to uncover black boxes and to explain every individual prediction in our model. We have evaluated our model performance using the findprediction() function on three different idx values (i.e., 100, 120, and 150) to find the prediction probabilities of two classes for each feature. These experiments have been done in Lenovo core i7 NVidia GeForce 860M GPU laptop in Windows 10 operating system using Python 3.8.3 software on Jupyter 6.4.3 platform. Results The proposed model resulted in the prediction probabilities depending on the features as 87%, 95%, and 87% for class ‘0’ and 13%, 5%, and 13% for class ‘1’ when idx_value=100, 120, and 150 for the first case; 100% for class ‘0’ and 0% for class ‘1’, when idx_value= 10, 12, and 15 respectively. Additionally, a comparative analysis has been drawn where our proposed model outperforms previous results found in cervical cancer research.

Explainable AI: Machine Learning Interpretation in Blackcurrant Powders.

Recently, explainability in machine and deep learning has become an important area in the field of research as well as interest, both due to the increasing use of artificial intelligence (AI) methods and understanding of the decisions made by models. The explainability of artificial intelligence (XAI) is due to the increasing consciousness in, among other things, data mining, error elimination, and learning performance by various AI algorithms. Moreover, XAI will allow the decisions made by models in problems to be more transparent as well as effective. In this study, models from the 'glass box' group of Decision Tree, among others, and the 'black box' group of Random Forest, among others, were proposed to understand the identification of selected types of currant powders. The learning process of these models was carried out to determine accuracy indicators such as accuracy, precision, recall, and F1-score. It was visualized using Local Interpretable Model Agnostic Explanations (LIMEs) to predict the effectiveness of identifying specific types of blackcurrant powders based on texture descriptors such as entropy, contrast, correlation, dissimilarity, and homogeneity. Bagging (Bagging_100), Decision Tree (DT0), and Random Forest (RF7_gini) proved to be the most effective models in the framework of currant powder interpretability. The measures of classifier performance in terms of accuracy, precision, recall, and F1-score for Bagging_100, respectively, reached values of approximately 0.979. In comparison, DT0 reached values of 0.968, 0.972, 0.968, and 0.969, and RF7_gini reached values of 0.963, 0.964, 0.963, and 0.963. These models achieved classifier performance measures of greater than 96%. In the future, XAI using agnostic models can be an additional important tool to help analyze data, including food products, even online.

Explainable Artificial Intelligence in Quantifying Breast Cancer Factors: Saudi Arabia Context.

Breast cancer represents a significant health concern, particularly in Saudi Arabia, where it ranks as the most prevalent cancer type among women. This study focuses on leveraging eXplainable Artificial Intelligence (XAI) techniques to predict benign and malignant breast cancer cases using various clinical and pathological features specific to Saudi Arabian patients. Six distinct models were trained and evaluated based on common performance metrics such as accuracy, precision, recall, F1 score, and AUC-ROC score. To enhance interpretability, Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) were applied. The analysis identified the Random Forest model as the top performer, achieving an accuracy of 0.72, along with robust precision, recall, F1 score, and AUC-ROC score values. Conversely, the Support Vector Machine model exhibited the poorest performance metrics, indicating its limited predictive capability. Notably, the XAI approaches unveiled variations in the feature importance rankings across models, underscoring the need for further investigation. These findings offer valuable insights into breast cancer diagnosis and machine learning interpretation, aiding healthcare providers in understanding and potentially integrating such technologies into clinical practices.

Explainable machine learning models for defects detection in industrial processes

Machine learning algorithms in non-linear pattern recognition for defect detection in manufacturing processes are increasingly prevalent in the context of Industry 4.0. This scenario enables factories to develop methodologies for monitoring and controlling the quality of their products, obtaining better operational efficiency indicators, and offering increasingly competitive products in the market. Explainable Artificial Intelligence can facilitate understanding how the models make decisions and assist in tracking anomaly points. This paper proposes an explainability framework for machine learning models in defect detection. This work applied the multinational industry’s approach to the tire manufacturing process. Models such as random forest, gradient boosting decision tree, light gradient boosting machine, logistic regression, support vector machine, and multi-layer perceptron were considered to evaluate the performance of tires in compliance with production standards. Statistical methodologies had to be adopted to deal with the small number of samples training the machine learning models. The random forest and logistic regression models achieved the best performances with an accuracy of 92% and 96%, respectively. The Local Interpretable Model-Agnostic Explanations and SHapley Additive exPlanations methods were used to identify the relevant process variables. The approach presents the global and local interpretations of the results, allowing for a deeper understanding of how process variables discriminate the fault. The proposed framework determines reference values for each selected process variable for tire manufacturing in compliance with quality standards. This approach provides a relevant tool for quality control management in tire manufacturing industries.

An Interpretable Transformer Model for Operational Flare Forecasting

Interpretable machine learning tools including LIME (Local Interpretable Model-agnostic Explanations) and ALE (Accumulated Local Effects) are incorporated into a transformer-based deep learning model, named SolarFlareNet, to interpret the predictions made by the model. SolarFlareNet is implemented into an operational flare forecasting system to predict whether an active region on the surface of the Sun would produce a &gt;=M class flare within the next 24 hours. LIME determines the ranking of the features used by SolarFlareNet. 2D ALE plots identify the interaction effects of two features on the predictions. Together, these tools help scientists better understand which features are crucial for SolarFlareNet to make its predictions. Experiments show that the tools can explain the internal workings of SolarFlareNet while maintaining its accuracy.

Transferring Black-Box Decision Making to a White-Box Model

In the rapidly evolving realm of artificial intelligence (AI), black-box algorithms have exhibited outstanding performance. However, their opaque nature poses challenges in fields like medicine, where the clarity of the decision-making processes is crucial for ensuring trust. Addressing this need, the study aimed to augment these algorithms with explainable AI (XAI) features to enhance transparency. A novel approach was employed, contrasting the decision-making patterns of black-box and white-box models. Where discrepancies were noted, training data were refined to align a white-box model’s decisions closer to its black-box counterpart. Testing this methodology on three distinct medical datasets revealed consistent correlations between the adapted white-box models and their black-box analogs. Notably, integrating this strategy with established methods like local interpretable model-agnostic explanations (LIMEs) and SHapley Additive exPlanations (SHAPs) further enhanced transparency, underscoring the potential value of decision trees as a favored white-box algorithm in medicine due to its inherent explanatory capabilities. The findings highlight a promising path for the integration of the performance of black-box algorithms with the necessity for transparency in critical decision-making domains.