Biology subjects

Sattiraju, A.

Publications and source records attributed to Sattiraju, A..

7 recordsLinked to original sources

bioRxiv2023

An Explainable and Robust Deep Learning Approach for Automated Electroencephalography-based Schizophrenia Diagnosis

Schizophrenia (SZ) is a neuropsychiatric disorder that affects millions globally. Current diagnosis of SZ is symptom-based, which poses difficulty due to the variability of symptoms across patients. To this end, many recent studies have developed deep learning methods for automated diagnosis of SZ, especially using raw EEG, which provides high temporal precision. For such methods to be productionized, they must be both explainable and robust. Explainable models are essential to identify biomarkers of SZ, and robust models are critical to learn generalizable patterns, especially amidst changes in the implementation environment. One common example is channel loss during EEG recording, which could be detrimental to classifier performance. In this study, we developed a novel channel dropout (CD) approach to increase the robustness of explainable deep learning models trained on EEG data for SZ diagnosis to channel loss. We developed a baseline convolutional neural network (CNN) architecture and implement our approach as a CD layer added to the baseline (CNN-CD). We then applied two explainability approaches to both models for insight into learned spatial and spectral features and show that the application of CD decreases model sensitivity to channel loss. The CNN and CNN-CD achieved accuracies of 81.9% and 80.9% on testing data, respectively. Furthermore, our models heavily prioritized the parietal electrodes and the -band, which is supported by existing literature. It is our hope that this study motivates the further development of explainable and robust models and bridges the transition from research to application in a clinical decision support role.

neuroscience↗

bioRxiv2023

Improving Multichannel Raw Electroencephalography-based Diagnosis of Major Depressive Disorder by Pretraining Deep Learning Models with Single Channel Sleep Stage Data

As the field of deep learning has grown in recent years, its application to the domain of raw resting-state electroencephalography (EEG) has also increased. Relative to traditional machine learning methods or deep learning methods applied to extracted features, there are fewer methods for developing deep learning models on small raw EEG datasets. One potential approach for enhancing deep learning performance in this case is the use of transfer learning. In this study, we propose a novel EEG transfer learning approach wherein we first train a model on a large publicly available sleep stage classification dataset. We then use the learned representations to develop a classifier for automated major depressive disorder diagnosis with raw multichannel EEG. We find that our approach improves model performance, and we further examine how transfer learning affected the representations learned by the model through a pair of explainability analyses. Our proposed approach represents a significant step forward for the domain raw resting-state EEG classification. Furthermore, it has the potential to expand the use of deep learning methods across more raw EEG datasets and lead to the development of more reliable EEG classifiers. Clinical RelevanceThe proposed approach takes the field of deep learning in EEG a step closer to the robustness needed for clinical implementation.

neuroscience↗

bioRxiv2023

A Framework for Systematically Evaluating the Representations Learned by A Deep Learning Classifier from Raw Multi-Channel Electroencephalogram Data

The application of deep learning methods to raw electroencephalogram (EEG) data is growing increasingly common. While these methods offer the possibility of improved performance relative to other approaches applied to manually engineered features, they also present the problem of reduced explainability. As such, a number of studies have sought to provide explainability methods uniquely adapted to the domain of deep learning-based raw EEG classification. In this study, we present a taxonomy of those methods, identifying existing approaches that provide insight into spatial, spectral, and temporal features. We then present a novel framework consisting of a series of explainability approaches for insight into classifiers trained on raw EEG data. Our framework provides spatial, spectral, and temporal explanations similar to existing approaches. However, it also, to the best of our knowledge, proposes the first explainability approaches for insight into spatial and spatio-spectral interactions in EEG. This is particularly important given the frequent use and well-characterized importance of EEG connectivity measures for neurological and neuropsychiatric disorder analysis. We demonstrate our proposed framework within the context of automated major depressive disorder (MDD) diagnosis, training a high performing one-dimensional convolutional neural network with a robust cross-validation approach on a publicly available dataset. We identify interactions between frontal and central electrodes and other electrodes and identify differences in frontal {delta}, {theta}, {beta}, and {gamma}low between healthy controls and individuals with MDD. Our study represents a significant step forward for the field of deep learning-based raw EEG classification, providing new capabilities in interaction explainability and providing direction for future innovations through our proposed taxonomy.

neuroscience↗

bioRxiv2023

Novel Approach Explains Spatio-Spectral Interactions in Raw Electroencephalogram Deep Learning Classifiers

The application of deep learning classifiers to resting-state electroencephalography (rs-EEG) data has become increasingly common. However, relative to studies using traditional machine learning methods and extracted features, deep learning methods are less explainable. A growing number of studies have presented explainability approaches for rs-EEG deep learning classifiers. However, to our knowledge, no approaches give insight into spatio-spectral interactions (i.e., how spectral activity in one channel may interact with activity in other channels). In this study, we combine gradient and perturbation-based explainability approaches to give insight into spatio-spectral interactions in rs-EEG deep learning classifiers for the first time. We present the approach within the context of major depressive disorder (MDD) diagnosis identifying differences in frontal {delta} activity and reduced interactions between frontal electrodes and other electrodes. Our approach provides novel insights and represents a significant step forward for the field of explainable EEG classification.

neuroscience↗

bioRxiv2022

Examining Reproducibility of EEG Schizophrenia Biomarkers Across Explainable Machine Learning Models

Schizophrenia (SZ) is a neuropsychiatric disorder that adversely effects millions of individuals globally. Current diagnostic efforts are symptom based and hampered due to the variability in symptom presentation across individuals and overlap of symptoms with other neuropsychiatric disorders. This spawns the need for (1) biomarkers to aid with empirical SZ diagnosis and (2) the development of automated diagnostic approaches that will eventually serve in a clinical decision support role. In this study, we train random forest (RF) and support vector machine (SVM) models to differentiate between individuals with schizophrenia and healthy controls using spectral features extracted from resting state EEG data. We then perform two explainability analyses to gain insight into key frequency bands and channels. In our explainability analyses, we examine the reproducibility of SZ biomarkers across models with the goal of identifying those that have potential clinical implications. Our model performance results are well above chance level indicating the broader utility of spectral information for SZ diagnosis. Additionally, we find that the RF prioritizes the upper {gamma}-band and is robust to loss of information from individual electrodes, while the SVM prioritizes the and {theta}-bands and P4 and T8 electrodes. It is our hope that our findings will inform future efforts towards the empirical diagnosis of SZ and towards the development of clinical decision support systems for SZ diagnosis.

bioinformatics↗

bioRxiv2022

Examining Effects of Schizophrenia on EEG with Explainable Deep Learning Models

Schizophrenia (SZ) is a mental disorder that affects millions of people globally. At this time, diagnosis of SZ is based upon symptoms, which can vary from patient to patient and create difficulty with diagnosis. To address this issue, researchers have begun to look for neurological biomarkers of SZ and develop methods for automated diagnosis. In recent years, several studies have applied deep learning to raw EEG for automated SZ diagnosis. However, the use of raw time-series data makes explainability more difficult than it is for traditional machine learning algorithms trained on manually engineered features. As such, none of these studies have sought to explain their models, which is problematic within a healthcare context where explainability is a critical component. In this study, we apply perturbation-based explainability approaches to gain insight into the spectral and spatial features learned by two distinct deep learning models trained on raw EEG for SZ diagnosis for the first time. We develop convolutional neural network (CNN) and CNN long short-term memory network (CNN-LSTM) architectures. Results show that both models prioritize the T8 and C3 electrodes and the {delta}- and {gamma}-bands, which agrees with previous literature and supports the overall utility of our models. This study represents a step forward in the implementation of deep learning models for clinical SZ diagnosis, and it is our hope that it will inspire the more widespread application of explainability methods for insight into deep learning models trained for SZ diagnosis in the future.

bioinformatics↗

bioRxiv2022

Spatial patterning and immunosuppression of glioblastoma immune contexture in hypoxic niches

Glioblastoma (GBM), a highly lethal brain cancer, is notorious for its immunosuppressive microenvironment, yet current immunotherapies are ineffective. Thus, understanding the immune contexture and governing factors of immunosuppression is crucial. Here, we identified a highly dynamic temporospatial patterning of tumor-associated macrophages (TAMs) corresponding to vascular changes in GBM: as tumor vessels transition from an initial dense regular network to later scant engorged vasculature, CD68+ TAMs shift away from perivascular regions to poorly vascularized areas. Remarkably, this process is heavily influenced by the immunocompetency of host animal, as tumor vessels in immunodeficient hosts remained dense and regular while TAMs evenly distributed. Utilizing a sensitive fluorescent reporter to track tumor hypoxia, we revealed that hypoxic niche controls immunosuppression by at least two mechanisms: first, attracting and sequestering activated TAMs in hypoxic zones, and second, reprograming entrapped TAMs towards an immunotolerant state. Indeed, entrapped TAMs also experience hypoxia and upregulate phagocytic marker Cd68 and immunotolerant genes Mrc1 and Arg1, thereby facilitating debris clearing, inflammatory containment, and immunosuppression in hypoxic zones. Mechanistically, we identified Ccl8 and IL-1{beta} as two hypoxic niche factors released by TAMs in response to cues from hypoxic GBM cells, functioning to reinforce TAM retainment. Reciprocally, niche factors also shape the transcriptional responses of hypoxic tumor cells that exhibit quiescence and mesenchymal shift. Moreover, hypoxic niche factors are highly enriched in human GBMs, particularly mesenchymal subtype, and predict poor survival. Importantly, perturbing hypoxic niches resulted in reduced TAM sequestration and better tumor control. Together, understanding the mutual influence of immune contexture and metabolic landscape has important ramifications for improving efficacy of immunotherapies against GBM.

cancer biology↗