Easy Perturbation EEG Algorithm for Spectral Importance (easyPEASI)

Nahmias, David; Kontson, Kimberly

doi:10.1145/3394486.3403289

Cited by 28 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, perturbation methods can potentially create unrealistic, out-of-distribution samples that do not accurately assess what a classifier has learned [12]. We addressed this potential problem by perturbing samples with values from within the dataset and by not assuming distribution normality like previous studies have assumed [10]. While this adaption would likely reduce the potential for out-of-distribution samples, gradient-based explainability methods avoid this problem and could potentially be applied to gain local spectral insight [20][21].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Local Explainability Approach for Spectral Insight into Raw Eeg-Based Deep Learning Classifiers

Miller

Calhoun

2021

Preprint

View full text Add to dashboard Cite

The frequency domain of electroencephalography (EEG) data has developed as a particularly important area of EEG analysis. EEG spectra have been analyzed with explainable machine learning and deep learning methods. However, as deep learning has developed, most studies use raw EEG data, which is not well-suited for traditional explainability methods. Several studies have introduced methods for spectral insight into classifiers trained on raw EEG data. These studies have provided global insight into the frequency bands that are generally important to a classifier but do not provide local insight into the frequency bands important for the classification of individual samples. This local explainability could be particularly helpful for EEG analysis domains like sleep stage classification that feature multiple evolving states. We present a novel local spectral explainability approach and use it to explain a convolutional neural network trained for automated sleep stage classification. We use our approach to show how the relative importance of different frequency bands varies over time and even within the same sleep stages. Furthermore, to better understand how our approach compares to existing methods, we compare a global estimate of spectral importance generated from our local results with an existing global spectral importance approach. We find that the δ band is most important for most sleep stages, though β is most important for the non-rapid eye movement 2 (NREM2) sleep stage. Additionally, θ is particularly important for identifying Awake and NREM1 samples. Our study represents the first approach developed for local spectral insight into deep learning classifiers trained on raw EEG time series.

show abstract

Section: Resultsmentioning

confidence: 99%

“…We show how our approach can find the importance of different frequency bands over time. Further, to evaluate our approach within the context of existing methods, we use our local approach to form a global estimate of spectral importance and compare our results to an existing global method [10].…”

Section: Introductionmentioning

confidence: 99%

A Novel Local Explainability Approach for Spectral Insight into Raw Eeg-Based Deep Learning Classifiers

Miller

Calhoun

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A few studies involving deep learning models with raw data have also used explainability methods (25,34–36). These studies typically seek to identify the spectral features (34–39) or waveforms (36,37) learned by neural networks. However, multimodal classification poses unique challenges for explainability that do not exist for unimodal classification.…”

Section: Introductionmentioning

confidence: 99%

Novel Methods for Elucidating Modality Importance in Multimodal Electrophysiology Classifiers

Ellis

Sendi

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Multimodal classification is increasingly common in biomedical informatics studies. Many such studies use deep learning classifiers with raw data, which makes explainability difficult. As such, only a few studies have applied explainability methods, and new methods are needed. In this study, we propose sleep stage classification as a testbed for method development and train a convolutional neural network with electroencephalogram (EEG), electrooculogram, and electromyogram data. We then present a global approach that is uniquely adapted for electrophysiology analysis. We further present two local approaches that can identify subject-level differences in explanations that would be obscured by global methods and that can provide insight into the effects of clinical and demographic variables upon the patterns learned by the classifier. We find that EEG is globally the most important modality for all sleep stages, except non-rapid eye movement stage 1 and that local subject-level differences in importance arise. We further show that sex, followed by medication and age had significant effects upon the patterns learned by the classifier. Our novel methods enhance explainability for the growing field of multimodal classification, provide avenues for the advancement of personalized medicine, and yield novel insights into the effects of demographic and clinical variables upon classifiers.

show abstract

“…Both global Funding for this work is from NIH grant R01EB006841. [13][15] and local approaches [16] [17] have been developed. However, these methods only provide an estimate of importance.…”

Section: Introductionmentioning

confidence: 99%

A Novel Activation Maximization-based Approach for Insight into Electrophysiology Classifiers

Ellis

Sendi

Miller

et al. 2021

Preprint

View full text Add to dashboard Cite

Spectral analysis remains a hallmark approach for gaining insight into electrophysiology modalities like electroencephalography (EEG). As the field of deep learning has progressed, more studies have begun to train deep learning classifiers on raw EEG data, which presents unique problems for explainability. A growing number of studies have presented explainability approaches that provide insight into the spectral features learned by deep learning classifiers. However, existing approaches only attribute importance to different frequency bands. Most of the methods cannot provide insight into the actual spectral values or the relationship between spectral features that models have learned. Here, we present a novel adaptation of activation maximization for electrophysiology time-series that generates samples that indicate the features learned by classifiers by optimizing their spectral content. We evaluate our approach within the context of EEG sleep stage classification with a convolutional neural network, and we find that our approach is able to identify spectral patterns known to be associated with each sleep stage. We also find surprising results suggesting that our classifier may have prioritized the use of eye and motion artifact when identifying Awake samples. Our approach is the first adaptation of activation maximization to the domain of raw electrophysiology classification. Additionally, our approach has implications for explaining any classifier trained on highly dynamic, long time-series.

show abstract

Easy Perturbation EEG Algorithm for Spectral Importance (easyPEASI)

Cited by 28 publications

References 11 publications

A Novel Local Explainability Approach for Spectral Insight into Raw Eeg-Based Deep Learning Classifiers

A Novel Local Explainability Approach for Spectral Insight into Raw Eeg-Based Deep Learning Classifiers

Novel Methods for Elucidating Modality Importance in Multimodal Electrophysiology Classifiers

A Novel Activation Maximization-based Approach for Insight into Electrophysiology Classifiers

Contact Info

Product

Resources

About