Explainable Artificial Intelligence: A Comprehensive Review of Techniques, Applications, and Emerging Trends

The study examined the use of explainable artificial intelligence (XAI) methods for unmanned aerial vehicles (UAVs). The aim of the study is to make the artificial intelligence decision processes in the autonomous systems of UAVs more understandable and transparent. This requirement has gained importance as UAVs are used in increasingly complex tasks. In order to increase the reliability of UAVs especially in areas such as security, military operations and agriculture, and to reinforce users' trust in these systems, the integration of XAI methods has become critical. In the study, both model-based and post-hoc explanation methods were used. Model-based methods such as decision trees and explainable neural networks were preferred to ensure transparency of UAVs' decision-making processes. Post-hoc methods such as Local Intrepretable Model - Adnogtics Explanations (LIME) and SHapley Additive Explanations (SHAP) were used to increase the explainability of deep learning models . In the study, these techniques were evaluated to understand why UAVs make certain decisions in their complex operational processes. As a result of the study, it was observed that the integration of Explainable Artificial Intelligence (XAI) methods into UAV systems made decision processes more transparent and thus increased the reliability of UAVs. It was emphasized that this transparency, especially in terms of public safety and ethical practices, plays a critical role in expanding the use of UAVs and making them safer.

Explainable artificial intelligence received great research attention in the past few years during the widespread of Black-Box techniques in sensitive fields such as medical care, self-driving cars, etc. Artificial intelligence needs explainable methods to discover model biases. Explainable artificial intelligence will lead to obtaining fairness and Transparency in the model. Making artificial intelligence models explainable and interpretable is challenging when implementing black-box models. Because of the inherent limitations of collecting data in its raw form, data fusion has become a popular method for dealing with such data and acquiring more trustworthy, helpful, and precise insights. Compared to other, more traditional-based data fusion methods, machine learning's capacity to automatically learn from experience with nonexplicit programming significantly improves fusion's computational and predictive power. This paper comprehensively studies the most explainable artificial intelligent methods based on anomaly detection. We proposed the required criteria of the transparency model to measure the data fusion analytics techniques. Also, define the different used evaluation metrics in explainable artificial intelligence. We provide some applications for explainable artificial intelligence. We provide a case study of anomaly detection with the fusion of machine learning. Finally, we discuss the key challenges and future directions in explainable artificial intelligence.

The rapid integration of Large Language Models (LLMs) into critical societal domains, including healthcare, finance, and law, has created an urgent need for transparency and accountability. However, the inherent "black box" nature of these complex models presents a significant obstacle to understanding their decision-making processes, which can lead to issues of trust, bias, and unforeseen errors. This article provides a comprehensive review of the current state of Explainable Artificial Intelligence (XAI) for LLMs. We conduct a systematic analysis of existing XAI techniques, categorizing them into a novel taxonomy based on their underlying mechanisms: attention-based methods, feature attribution methods, mechanistic interpretability, and natural language explanations. The findings reveal the key challenges in achieving meaningful explainability, including the trade-offs between model performance and transparency, the computational cost of explanation generation, and the lack of standardized evaluation metrics. This paper introduces a conceptual framework for implementing and evaluating explainability in LLMs, offering practical guidelines for researchers and practitioners. By synthesizing the latest research, including insights into the internal mechanisms of models like Anthropic's Claude series, this article aims to bridge the gap between the demand for transparency and the technical complexities of LLM explainability, paving the way for more trustworthy and reliable AI systems.

Explanations based on Item Response Theory (eXirt): A model-specific method to explain tree-ensemble model in trust perspective

With rapid developments in big data technology and the prevalence of large-scale datasets from diverse sources, the healthcare predictive analytics (HPA) field is witnessing a dramatic surge in interest. In healthcare, it is not only important to provide accurate predictions, but also critical to provide reliable explanations to the underlying black-box models making the predictions. Such explanations can play a crucial role in not only supporting clinical decision-making but also facilitating user engagement and patient safety. If users and decision makers do not have faith in the HPA model, it is highly likely that they will reject its use. Furthermore, it is extremely risky to blindly accept and apply the results derived from black-box models, which might lead to undesirable consequences or life-threatening outcomes in domains with high stakes such as healthcare. As machine learning and artificial intelligence systems are becoming more capable and ubiquitous, explainable artificial intelligence and machine learning interpretability are garnering significant attention among practitioners and researchers. The introduction of policies such as the General Data Protection Regulation (GDPR), has amplified the need for ensuring human interpretability of prediction models. In this talk I will discuss methods and applications for developing local as well as global explanations from machine learning and the value they can provide for healthcare prediction.

As artificial intelligence (AI)[1] systems become increasingly complex and pervasive, the need for transparency and interpretability has become a critical concern. Explainable AI (XAI)[2, 3] seeks to bridge the gap between opaque machine learning models and human users by providing insights into the decision-making processes of AI systems. This editorial explores the various methods employed in XAI, the challenges faced in achieving interpretability, and potential future directions for the field. The rapid adoption of AI in critical domains such as healthcare, finance, and criminal justice has raised concerns about the "black-box" nature of many AI models[4]. While these models often achieve high accuracy, their decision-making processes remain obscure, making it difficult to diagnose errors, ensure fairness, and build user trust. Explainable AI aims to address these concerns by developing techniques that offer transparency and interpretability without compromising performance.

In today’s rapidly evolving digital landscape, cybersecurity is paramount as organizations face increasingly sophisticated attacks. Artificial intelligence (AI) has become a key tool in detecting and mitigating these threats; however, conventional AI models often operate as “black boxes,” leaving decision processes obscure. Explainable AI (XAI) emerges as a promising solution by illuminating the internal mechanisms of these models, thereby enhancing transparency and trust. This paper explores the integration of XAI into cybersecurity frameworks to improve model transparency and accountability. We examine techniques such as feature importance analysis, surrogate modeling, and visualization methods that reveal how AI systems identify anomalies and flag potential threats. Our analysis demonstrates that making AI decisions interpretable not only supports security experts in understanding and validating automated responses but also aids in regulatory compliance and ethical oversight. Furthermore, enhanced transparency helps in diagnosing biases and vulnerabilities that could be exploited by adversaries, ultimately strengthening the resilience of cybersecurity systems.

The rapid escalation of cyber threats necessitates innovative strategies to enhance cybersecurity and privacy measures. Artificial Intelligence (AI) has emerged as a promising tool poised to enhance the effectiveness of cybersecurity strategies by offering advanced capabilities for intrusion detection, malware classification, and privacy preservation. However, this work addresses the significant lack of a comprehensive synthesis of AI's use in cybersecurity and privacy across the vast literature, aiming to identify existing gaps and guide further progress. This study employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework for a comprehensive literature review, analyzing over 9,350 publications from 2004 to 2023. Utilizing BERTopic modeling, 14 key themes in AI-driven cybersecurity were identified. Topics were clustered and validated through a combination of algorithmic and expert-driven evaluations, focusing on semantic relationships and coherence scores. AI applications in cybersecurity are concentrated around intrusion detection, malware classification, federated learning in privacy, IoT security, UAV systems and DDoS mitigation. Emerging fields such as adversarial machine learning, blockchain and deep learning are gaining traction. Analysis reveals that AI's adaptability and scalability are critical for addressing evolving threats. Global trends indicate significant contributions from the US, India, UK, and China, highlighting geographical diversity in research priorities. While AI enhances cybersecurity efficacy, challenges such as computational resource demands, adversarial vulnerabilities, and ethical concerns persist. More research in trustworthy AI, standardizing AI-driven methods, legislations for robust privacy protection amongst others is emphasized. The study also highlights key current and future areas of focus, including quantum machine learning, explainable AI, integrating humanized AI and deepfakes.

Explainable Artificial Intelligence (XAI) is indeed causing an uproar in the sphere of medical image analysis. It is simply a matter of developing trust, creating transparency, and promoting clinical utilization of AI systems. This systematic review gathers the knowledge of 25 latest studies to provide us with a clear image of the current state of XAI, the issues in it, and of the possible future directions. The results demonstrate that there is a growing reliance on deep learning models that are enhanced with interpretability techniques, such as saliency maps, self-explainable architectures and ensemble techniques. The papers emphasize the need to consider clinical relevance, usability and compliance with regulatory standards, particularly in such crucial fields as breast cancer diagnosis, brain tumor classification and analysis of Alzheimer disease. Despite all this progress, there remain some large issues to address, such as the lack of standardized platforms of evaluation, the difficulties of connecting technical descriptions to clinical reasoning, and the necessity to uphold equitability and confidentiality in federated learning settings. Besides that, new solutions such as compression that protects privacy and multi-modal explanations are leading to more effective and reliable solutions. In this review, interdisciplinary teamwork, emphasis on human-centered design and standardization of benchmarks are highlighted as the necessary conditions to promote responsible and effective XAI in medical image analysis.

The rapid advancement of Artificial Intelligence (AI) and Machine Learning (ML) across healthcare domains has significantly improved diagnostic accuracy, operational efficiency, and patient outcomes (Rajkomar et al., 2019; Jiang et al., 2017). Despite these benefits, concerns regarding the lack of transparency and interpretability in AI systems remain critical, particularly in high-stakes environments such as healthcare (Doshi-Velez & Kim, 2017; Tjoa & Guan, 2020). Many AI models operate as “black boxes,” making it difficult for stakeholders to understand the rationale behind their decisions, thereby raising issues of trust, accountability, and ethical compliance (Arrieta et al., 2020; Floridi et al., 2018). Healthcare Business Process Outsourcing (BPO) organizations increasingly utilize AI-driven tools to automate medical document processing for insurance claims. These documents, including prescriptions, lab reports, and radiology records, must be classified and chronologically organized to reflect patient history. Traditional ML approaches such as Count Vectorization and TF-IDF combined with classification algorithms achieve high accuracy; however, they rely heavily on word frequency, which can introduce bias and lead to misclassification (Wang et al., 2018; Obermeyer et al., 2019). To address these limitations, Explainable Artificial Intelligence (XAI) has emerged as a promising solution that enhances transparency and interpretability in AI systems (Ribeiro et al., 2016; Lundberg & Lee, 2017). This study presents a systematic review of XAI techniques in healthcare, focusing on their application in medical document classification. It further identifies key challenges, including the lack of standardized evaluation metrics, and proposes future research directions to enhance transparency, fairness, and reliability in AI-driven healthcare systems (Arrieta et al., 2020; Tjoa & Guan, 2020).

This study aims to develop and evaluate an obesity classification model using an Artificial Neural Network (ANN) combined with Explainable Artificial Intelligence (XAI) techniques based on SHAP (SHapley Additive exPlanations). The model was trained and tested using two different optimizers, Adaptive Moment Estimation (Adam) and Stochastic Gradient Descent (SGD), across multiple train-test ratios and epoch variations. The experimental results indicate that the Adam optimizer consistently outperformed SGD in terms of accuracy, loss value, and stability of evaluation metrics. The best performance was achieved with a 90:10 train-test ratio at 100 epochs, yielding an accuracy of 94.74%, a loss of 0.1899, precision, recall, and an f1-score of 0.95. To improve interpretability, SHAP was applied to identify the most influential features in the classification process. The analysis revealed that features such as Weight, Height, Gender, and Age significantly contribute to the model's predictions. Based on the SHAP interpretation, feature selection was conducted using the top nine features with the highest SHAP values. Retraining the ANN with these selected features resulted in improved performance, achieving 98.56% accuracy, a loss of 0.0638, and a precision, recall, and F1-score of 0.99 . These findings demonstrate that integrating XAI with ANN not only enhances transparency and interpretability but also boosts classification performance and computational efficiency. This approach shows strong potential for supporting decision-making in healthcare, particularly for early detection and intervention in cases related to obesity.

Artificial Intelligence (AI) has demonstrated significant potential in revolutionizing healthcare by enhancing diagnostic accuracy, predicting patient outcomes, and optimizing treatment plans. However, the increasing reliance on complex, black-box models has raised critical concerns around transparency, trust, and accountability—particularly in high-stakes medical settings where interpretability is vital for clinical decision-making. This paper explores Explainable AI (XAI) as a solution to bridge the gap between model performance and human interpretability. We review current XAI techniques, including post-hoc methods like SHAP and LIME, and intrinsically interpretable models, assessing their applicability and limitations within healthcare contexts. Through selected case studies in radiology, oncology, and clinical decision support systems, we examine how XAI can improve clinician trust and facilitate informed decision-making without compromising predictive accuracy. Our analysis highlights persistent challenges such as balancing explanation fidelity with usability, addressing data biases, and aligning explanations with clinical reasoning. We propose a multidisciplinary framework that integrates technical, ethical, and user-centered principles to support the development of trustworthy XAI systems. Future research directions include the standardization of interpretability metrics, the co-design of models with clinicians, and regulatory considerations for deploying XAI in clinical practice. By aligning technological advances with human-centered design, XAI has the potential to transform AI into a reliable partner in healthcare delivery.

Artificial Intelligence (AI) has demonstrated superhuman capabilities in solving a significant number of tasks, leading to widespread industrial adoption. For in-field network-management application, AI-based solutions, however, have often risen skepticism among practitioners as their internal reasoning is not exposed and their decisions cannot be easily explained, preventing humans from trusting and even understanding them. To address this shortcoming, a new area in AI, called Explainable AI (XAI), is attracting the attention of both academic and industrial researchers. XAI is concerned with explaining and interpreting the internal reasoning and the outcome of AI-based models to achieve more trustable and practical deployment. In this work, we investigate the application of XAI for network management, focusing on the problem of automated failure-cause identification in microwave networks. We first introduce the concept of XAI, highlighting its advantages in the context of network management, and we discuss in detail the concept behind Shapley Additive Explanations (SHAP), the XAI framework considered in our analysis. Then, we propose a framework for a XAI-assisted ML-based automated failure-cause identification in microwave networks, spanning model’s development and deployment phases. For the development phase, we show how to exploit SHAP for feature selection and how to leverage SHAP to inspect misclassified instances during model’s development process, and how to describe model’s global behavior based on SHAP’s global explanations. For the deployment phase, we propose a framework based on predictions uncertainty to detect possibly wrong predictions that will be inspected through XAI.

Explainable Artificial Intelligence (XAI) aims to introduce transparency and intelligibility into the decision-making process of AI systems. Most often, its application concentrates on supervised machine learning problems such as classification and regression. Nevertheless, in the case of unsupervised algorithms like clustering, XAI can also bring satisfactory results. In most cases, such application is based on the transformation of an unsupervised clustering task into a supervised one and providing generalised global explanations or local explanations based on cluster centroids. However, in many cases, the global explanations are too coarse, while the centroid-based local explanations lose information about cluster shape and distribution. In this paper, we present a novel approach called CLAMP (Cluster Analysis with Multidimensional Prototypes) that aids experts in cluster analysis with human-readable rule-based explanations. The developed state-of-the-art explanation mechanism is based on cluster prototypes represented by multidimensional bounding boxes. This allows representing of arbitrary shaped clusters and combines the strengths of local explanations with the generality of global ones.We demonstrate and evaluate the use of our approach in a real-life industrial case study from the domain of steel manufacturing as well as on the benchmark datasets. The explanations generated with CLAMP were more precise than either centroid-based or global ones.

Explainable Artificial Intelligence–Assisted Exploration of Clinically Significant Diabetic Retinal Neurodegeneration on OCT Images