mlsanityData to 7 Oct 2026

Explainable artificial intelligence approaches for brain-computer interfaces: a review and design space

arXiv 2312.13033 ↗First posted 20 Dec 2023cs.HC cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

This review paper provides an integrated perspective of Explainable Artificial Intelligence techniques applied to Brain-Computer Interfaces. BCIs use predictive models to interpret brain signals for various high-stake applications. However, achieving explainability in these complex models is challenging as it compromises accuracy. The field of XAI has emerged to address the need for explainability across various stakeholders, but there is a lack of an integrated perspective in XAI for BCI (XAI4BCI) literature. It is necessary to differentiate key concepts like explainability, interpretability, and understanding in this context and formulate a comprehensive framework. To understand the need of XAI for BCI, we pose six key research questions for a systematic review and meta-analysis, encompassing its purposes, applications, usability, and technical feasibility. We employ the PRISMA methodology -- preferred reporting items for systematic reviews and meta-analyses to review (n=1246) and analyze (n=84) studies published in 2015 and onwards for key insights. The results highlight that current research primarily focuses on interpretability for developers and researchers, aiming to justify outcomes and enhance model performance. We discuss the unique approaches, advantages, and limitations of XAI4BCI from the literature. We draw insights from philosophy, psychology, and social sciences. We propose a design space for XAI4BCI, considering the evolving need to visualize and investigate predictive model outcomes customised for various stakeholders in the BCI development and deployment lifecycle. This paper is the first to focus solely on reviewing XAI4BCI research articles. This systematic review and meta-analysis findings with the proposed design space prompt important discussions on establishing standards for BCI explanations, highlighting current limitations, and guiding the future of XAI in BCI.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 42 of its 164 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

42 of 164 references.

References · 42

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  6. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  9. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  10. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 616
  11. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  12. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
30 more
  1. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  2. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  3. 2019Explanations can be manipulated and geometry is to blamecited by 215
  4. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  5. 2020Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthycited by 182
  6. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  7. 2019What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Usecited by 134
  8. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  9. 2020The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategiescited by 91
  10. 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
  11. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  12. 2020Fairwashing Explanations with Off-Manifold Detergentcited by 71
  13. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  14. 2021Explainability Pitfalls: Beyond Dark Patterns in Explainable AIcited by 36
  15. 2019What it Thinks is Important is Important: Robustness Transfers through Input Gradientscited by 34
  16. 2016Interpretable Deep Neural Networks for Single-Trial EEG Classificationcited by 24
  17. 2023Feature Importance: A Closer Look at Shapley Values and LOCOcited by 23
  18. 2021EEG-based Cross-Subject Driver Drowsiness Recognition with an Interpretable Convolutional Neural Networkcited by 22
  19. 2020Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellerscited by 14
  20. 2021Robust learning from corrupted EEG with dynamic spatial filteringcited by 14
  21. 2021A Compact and Interpretable Convolutional Neural Network for Cross-Subject Driver Drowsiness Detection from Single-Channel EEGcited by 12
  22. 2022EEG-ITNet: An Explainable Inception Temporal Convolutional Network for Motor Imagery Classificationcited by 11
  23. 2023Interpretable and Robust AI in EEG Systems: A Surveycited by 10
  24. 2020Interpreting Deep Learning Models for Epileptic Seizure Detection on EEG signalscited by 8
  25. 2021On the interpretation of linear Riemannian tangent space model parameters in M/EEGcited by 8
  26. 2022Toward the application of XAI methods in EEG-based systemscited by 6
  27. 2020Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervalscited by 4
  28. 2019Tangent space spatial filters for interpretable and efficient Riemannian classificationcited by 3
  29. 2015Unsupervised decoding of long-term, naturalistic human neural recordings with automated video and audio annotationscited by 2
  30. 2021Interpretable Convolutional Neural Networks for Subject-Independent Motor Imagery Classificationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2025Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologiescited by 5
  2. 2024Quantifying Spatial Domain Explanations in BCI using Earth Mover's Distancecited by 1
  3. 2026AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Mapscited by 0
  4. 2026From Dyad to Triad: Eliciting XAI Requirements in Stroke Rehabilitationcited by 0
  5. 2026iFuzz-Meta: An Interpretable Fuzzy Learning Framework Bridging Top-Down and Bottom-Up Knowledge Integrationcited by 0