Skip to content
Log in

Similar papers

Review Open access Aug 2026

Explainable Artificial Intelligence (XAI): Techniques, Applications, Challenges and Future Directions - A Review

It is concluded that explainability is a necessary, though not sufficient, condition for trustworthy Al, and concrete directions for future research are outlined, including standardised benchmarks, human-centred evaluation, and explainability for large generative models.

Afna Ashraff M, Archana K, Buthaina Buthaina et al. · 0 citations
#artificial intelligence Review Aug 2026

Explainable Artificial Intelligence (XAI) in Computational Pathology: Definitions, Taxonomy, and Recommendations

Computational pathology (CompPath) is transforming medicine by leveraging artificial intelligence (AI) algorithms to support diagnosis, prognosis, and treatment prediction from gigapixel whole-slide images. Clinical adoption is progressing, but is constrained by concerns about safety, accountability, and regulatory oversight in high-stakes clinical environments. Explainable AI (XAI) systems hold promise for building trust and enabling verification, yet the literature remains fragmented due to inconsistent terminology, overlapping methodological families, ad hoc validation, and current reviews. This review aims to formalize XAI methods in CompPath through the: i) introduction of a pathology-centric vocabulary comprising seven core terms; ii) development of a taxonomy across methodological families and three orthogonal axes (stage, type, scope); and iii) establishment of a task-driven framework that maps five clinical questions to recommended methods, method evaluation, and deployment context. Five key gaps between current XAI capabilities and clinical deployment are identified, and actionable steps are proposed to advance XAI for CompPath.

S. Innani, Suhang You, A. Shephard et al. · 0 citations
Review Open access 2026

Explainable Artificial Intelligence (XAI) for Transparent Decision Systems

Explainable Artificial Intelligence (XAI) has become a key research focus nowadays due to the growing use of more intricate machine learning and deep learning systems in high-stakes systems. Although contemporary artificial intelligence (AI) methods show impressive prediction accuracy, the lack of transparency, a characteristic of their opaque (black-box) essence, presents serious forestalling issues in the areas of transparency, trust, accountability, and regulatory compliance. This interpretability is a disadvantage as numerous areas, like healthcare, finance, autonomous systems, and governance of the people, need AI systems to be applied in areas that are sensitive and require decision-making in a way that is comprehensible and explainable to human participants. XAI aims to solve these dilemmas by creating approaches and systems that allow human operators to comprehend, trust, and be able to handle AI-motivated decisions. XAI is not only aimed at providing explanations, but also at making these explanations meaningful, faithful to underlying model and applicable by various groups of users such as domain experts, developers, and policymakers. Enabling transparency, XAI leads to ethical AI, reduces bias and enhances debugging and model checking, and enables compliance with the developing regulatory frameworks like the General Data Protection Regulation (GDPR). This paper constitutes a thorough discussion of the XAI, as applied on transparent decision systems. It starts with a general introduction to motivation and the conceptualization of explainability in AI and goes on to provide a comprehensive literature review of model-specific and model-agnostic explainability algorithms. The suggested methodology combines both local and global explanatory approaches and transparency leadership framework. Experimental findings show the effectiveness of XAI techniques to enhance interpretability without causing a major loss in predictive accuracy. Lastly, the paper provides the practical implications, limitations, and research directions on the future of explainable and trustworthy AI systems.

Unknown authors · 0 citations
Review Open access Jul 2026

A scoping review of explainable artificial intelligence for medical multimodal data.

Multimodal Artificial Intelligence (AI) models-integrating diverse data such as imaging and clinical records-are advancing rapidly in healthcare, yet a significant disconnection persists between these complex predictive architectures and the explainable AI (XAI) techniques used to interpret them. We conducted a scoping review over 4 bibliographic databases to investigate the use of explainability methods in cross-modal medical AI studies. From 82 included studies, we found that the landscape remains dominated by independent feature attribution (assigning importance scores to individual modality in isolation), with the majority of studies relying on post-hoc methods (applied after a model decision is reached) that treat the model as a 'black box'. While emerging trends like visual grounding (linking textual justifications directly to specific image regions) and model reasoning show promise, a critical gap remains in explaining the underlying reasoning process. Standardised evaluation is missing in the majority of studies relying solely on qualitative measures. Only a minority of studies achieve good reproducibility with public codebase. We provide suggestions for the field to transition from individual and post-hoc XAIs toward intrinsically explainable designs where the reasoning logic is built directly into the model architecture to ensure that AI outputs align with human-centric clinical workflows and applications.

Kai Hu, Xing-Yue Fu, Yupeng Zhang et al. · 0 citations
Review 2026

An Overview of Explainable Artificial Intelligence (XAI) and Its Application

XAI provides a powerful framework for responsible AI development, challenges such as the performance-interpretability trade-off, lack of standardized evaluation metrics, and potential for human misinterpretation remain areas of active research.

P. Pradhan, Amol Rajmane, C. patil · 0 citations
Review Open access Aug 2026

Explainable artificial intelligence in medical imaging: how to interpret, evaluate, and use artificial intelligence explanations.

Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions. This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs. In this educational and practical review, we provide an accessible overview of XAI tailored for practicing radiologists and physicians. We cover the major categories of explanation methods, including saliency maps, perturbation-based and feature-attribution approaches, concept- based methods, and example-based reasoning, as well as uncertainty quantification as a complementary approach for assessing prediction reliability, along with common misconceptions and emerging regulatory obligations. We aim to make XAI easier for healthcare professionals to understand, as effective oversight of AI tools has become a core competency for the modern radiologist.

Gorkem Durak, H. Aktas, Tugba Akinci D’Antonoli et al. · 0 citations