An official website of the United States government
Objectives: We set out to develop a machine learning model capable of distinguishing patients presenting with ischemic stroke from a healthy cohort of subjects. The model relies on a 3-min resting electroencephalogram (EEG) recording from which features can be computed. Materials and methods: Using a large-scale, retrospective database of EEG recordings and matching clinical reports, we were able to construct a dataset of 1385 healthy subjects and 374 stroke patients. With subjects often producing more than one recording per session, the final dataset consisted of 2401 EEG recordings (63% healthy, 37% stroke). Results: Using a rich set of features encompassing both the spectral and temporal domains, our model yielded an AUC of 0.95, with a sensitivity and specificity of 93% and 86%, respectively. Allowing for multiple recordings per subject in the training set boosted sensitivity by 7%, attributable to a more balanced dataset. Conclusions: Our work demonstrates strong potential for the use of EEG in conjunction with machine learning methods to distinguish stroke patients from healthy subjects. Our approach provides a solution that is not only timely (3-minutes recording time) but also highly precise and accurate (AUC: 0.95). Keywords: Electroencephalogram (EEG); Feature engineering; Ischemic stroke; Large vessel occlusion; Machine learning; Prehospital stroke scale.
more »
« less
A Systematic Approach for Explaining Time and Frequency Features Extracted by Convolutional Neural Networks From Raw Electroencephalography Data
In recent years, the use of convolutional neural networks (CNNs) for raw resting-state electroencephalography (EEG) analysis has grown increasingly common. However, relative to earlier machine learning and deep learning methods with manually extracted features, CNNs for raw EEG analysis present unique problems for explainability. As such, a growing group of methods have been developed that provide insight into the spectral features learned by CNNs. However, spectral power is not the only important form of information within EEG, and the capacity to understand the roles of specific multispectral waveforms identified by CNNs could be very helpful. In this study, we present a novel model visualization-based approach that adapts the traditional CNN architecture to increase interpretability and combines that inherent interpretability with a systematic evaluation of the modelviaa series of novel explainability methods. Our approach evaluates the importance of spectrally distinct first-layer clusters of filters before examining the contributions of identified waveforms and spectra to cluster importance. We evaluate our approach within the context of automated sleep stage classification and find that, for the most part, our explainability results are highly consistent with clinical guidelines. Our approach is the first to systematically evaluate both waveform and spectral feature importance in CNNs trained on resting-state EEG data.
more »
« less
- Award ID(s):
- 2112455
- PAR ID:
- 10569577
- Publisher / Repository:
- Frontiers Media SA
- Date Published:
- Journal Name:
- Frontiers in Neuroinformatics
- Volume:
- 16
- ISSN:
- 1662-5196
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Natural selection leaves detectable patterns of altered spatial diversity within genomes, and identifying affected regions is crucial for understanding species evolution. Recently, machine learning approaches applied to raw population genomic data have been developed to uncover these adaptive signatures. Convolutional neural networks (CNNs) are particularly effective for this task, as they handle large data arrays while maintaining element correlations. However, shallow CNNs may miss complex patterns due to their limited capacity, while deep CNNs can capture these patterns but require extensive data and computational power. Transfer learning addresses these challenges by utilizing a deep CNN pretrained on a large dataset as a feature extraction tool for downstream classification and evolutionary parameter prediction. This approach reduces extensive training data generation requirements and computational needs while maintaining high performance. In this study, we developed TrIdent, a tool that uses transfer learning to enhance detection of adaptive genomic regions from image representations of multilocus variation. We evaluated TrIdent across various genetic, demographic, and adaptive settings, in addition to unphased data and other confounding factors. TrIdent demonstrated improved detection of adaptive regions compared to recent methods using similar data representations. We further explored model interpretability through class activation maps and adapted TrIdent to infer selection parameters for identified adaptive candidates. Using whole-genome haplotype data from European and African populations, TrIdent effectively recapitulated known sweep candidates and identified novel cancer, and other disease-associated genes as potential sweeps.more » « less
-
Abstract With increasing interest in explaining machine learning (ML) models, this paper synthesizes many topics related to ML explainability. We distinguish explainability from interpretability, local from global explainability, and feature importance versus feature relevance. We demonstrate and visualize different explanation methods, how to interpret them, and provide a complete Python package (scikit-explain) to allow future researchers and model developers to explore these explainability methods. The explainability methods include Shapley additive explanations (SHAP), Shapley additive global explanation (SAGE), and accumulated local effects (ALE). Our focus is primarily on Shapley-based techniques, which serve as a unifying framework for various existing methods to enhance model explainability. For example, SHAP unifies methods like local interpretable model-agnostic explanations (LIME) and tree interpreter for local explainability, while SAGE unifies the different variations of permutation importance for global explainability. We provide a short tutorial for explaining ML models using three disparate datasets: a convection-allowing model dataset for severe weather prediction, a nowcasting dataset for subfreezing road surface prediction, and satellite-based data for lightning prediction. In addition, we showcase the adverse effects that correlated features can have on the explainability of a model. Finally, we demonstrate the notion of evaluating model impacts of feature groups instead of individual features. Evaluating the feature groups mitigates the impacts of feature correlations and can provide a more holistic understanding of the model. All code, models, and data used in this study are freely available to accelerate the adoption of machine learning explainability in the atmospheric and other environmental sciences.more » « less
-
null (Ed.)OBJECTIVES/GOALS: Spinal cord stimulation (SCS) is an intervention for patients with chronic back pain. Technological advances have led to renewed optimism in the field, but mechanisms of action in the brain remain poorly understood. We hypothesize that SCS outcomes will be associated with changes in neural oscillations. METHODS/STUDY POPULATION: The goal of our team project is to test patients who receive SCS at 3 times points: baseline, at day 7 during the trial period, and day 180 after a permanent system has been implanted. At each time point participants will complete 10 minutes of eyes closed, resting electroencephalography (EEG). EEG will be collected with the ActiveTwo system, a 128-electrode cap, and a 256 channel AD box from BioSemi. Traditional machine learning methods such as support vector machine and more complex models including deep learning will be used to generate interpretable features within resting EEG signals. RESULTS/ANTICIPATED RESULTS: Through machine learning, we anticipate that SCS will have a significant effect on resting alpha and beta power in sensorimotor cortex. DISCUSSION/SIGNIFICANCE OF IMPACT: This collaborative project will further the application of machine learning in cognitive neuroscience and allow us to better understand how therapies for chronic pain alter resting brain activity.more » « less
-
critical to reveal a blackbox model’s decision-making process from raw data to prediction. In this article, we use two real datasets, the MNIST handwritten digits and MIT-BIH Electrocardiogram (ECG) signals, to motivate key characteristics of discriminative features, namely adaptiveness, predictive importance and effectiveness. Then, we develop a localization framework based on adversarial attacks to effectively localize discriminative features. In contrast to existing heuristic methods, we also provide a statistically guaranteed interpretability of the localized features by measuring a generalized partial R2. We apply the proposed method to the MNIST dataset and the MIT-BIH dataset with a convolutional auto-encoder. In the first, the compact image regions localized by the proposed method are visually appealing. Similarly, in the second, the identified ECG features are biologically plausible and consistent with cardiac electrophysiological principles while locating subtle anomalies in a QRS complex that may not be discernible by the naked eye. Overall, the proposed method compares favorably with state-of-the-art competitors. Accompanying this paper is a Python library dnn-locate that implements the proposed approach.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/fninf.2022.872035
