# Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection

arXiv: https://arxiv.org/abs/2605.28977 · HTML: https://mlsanity.com/paper/2605.28977/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 60 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 16 of 16)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [A Survey on the Explainability of Supervised Machine Learning](https://mlsanity.com/paper/2011.07876/) (2020)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Self-explaining AI as an alternative to interpretable AI](https://mlsanity.com/paper/2002.05149/) (2020)
- [A study of resting-state EEG biomarkers for depression recognition](https://mlsanity.com/paper/2002.11039/) (2020)
- [Are EEG Sequences Time Series? EEG Classification with Time Series Models and Joint Subject Training](https://mlsanity.com/paper/2404.06966/) (2024)
- [Ensemble approach for detection of depression using EEG features](https://mlsanity.com/paper/2103.08467/) (2021)
- [Sequential rank agreement methods for comparison of ranked lists](https://mlsanity.com/paper/1508.06803/) (2015)
- [Nonlinear analysis of EEG complexity in episode and remission phase of recurrent depression](https://mlsanity.com/paper/1811.04489/) (2018)

## Abstract (arXiv)

Recent advances in deep learning have enabled increasingly accurate electroencephalography (EEG)-based classification of Major Depressive Disorder (MDD), but the decision-making processes of high-capacity models remain difficult to interpret. This study investigates multiple post-hoc explainability methods applied to an InceptionTime architecture trained for EEG-based MDD detection. The analysis includes Shapley-based, gradient-based, and perturbation-based attribution approaches: DeepSHAP, Integrated Gradients, GradCAM, Occlusion, and Permutation Feature Importance. Explainability analysis was performed within a subject-level stratified 5-fold cross-validation framework using global attribution aggregation across EEG segments and subjects. The evaluated methods revealed partially convergent attribution patterns, with recurring emphasis on frontal, temporal, and posterior EEG regions, particularly in the right hemisphere. Quantitative comparison demonstrated substantial agreement between gradient- and perturbation-based approaches, while DeepSHAP produced comparatively distinct attribution distributions. At the same time, variability between explainability methods highlighted the influence of methodological assumptions on the resulting explanations. Overall, the results suggest that different post-hoc explainability approaches capture partially overlapping relevance structures in EEG-based deep learning models for depression detection. Although the observed attribution patterns are broadly consistent with several previous EEG studies of MDD, the analysis should be interpreted as exploratory rather than evidence of definitive neurophysiological biomarkers or clinical applicability. The study highlights both the usefulness and limitations of post-hoc explainability for interpreting black-box EEG classifiers in psychiatric applications.