Biology subjects

Calhoun, V. D.

Publications and source records attributed to Calhoun, V. D..

At least 55 records · Page 3Linked to original sources

bioRxiv2023

Association between the oral microbiome and brain resting state connectivity in schizophrenia

Recent microbiome-brain axis findings have shown evidence of the modulation of microbiome community as an environmental mediator in brain function and psychiatric illness. This work is focused on the role of the microbiome in understanding a rarely investigated environmental involvement in schizophrenia (SZ), especially in relation to brain circuit dysfunction. We leveraged high throughput microbial 16s rRNA sequencing and functional neuroimaging techniques to enable the delineation of microbiome-brain network links in SZ. N=213 SZ and healthy control (HC) subjects were assessed for the oral microbiome. Among them, 139 subjects were scanned by resting-state functional magnetic resonance imaging (rsfMRI) to derive brain functional connectivity. We found a significant microbiome compositional shift in SZ beta diversity (weighted UniFrac distance, p= 6x10-3; Bray-Curtis distance p = 0.021). Fourteen microbial species involving pro-inflammatory and neurotransmitter signaling and H2S production, showed significant abundance alterations in SZ. Multivariate analysis revealed one pair of microbial and functional connectivity components showing a significant correlation of 0.46. Thirty five percent of microbial species and 87.8% of brain functional network connectivity from each component also showed significant differences between SZ and HC with strong performance in classifying SZ from HC, with an area under curve (AUC) = 0.84 and 0.87, respectively. The results suggest a potential link between oral microbiome dysbiosis and brain functional connectivity alteration in relation to SZ, possibly through immunological and neurotransmitter signaling pathways and the hypothalamic-pituitary-adrenal axis, supporting for future work in characterizing the role of oral microbiome in mediating effects on SZ brain functional activity.

microbiology↗

bioRxiv2023

Evaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram Data

While deep learning methods are increasingly applied in research contexts for neuropsychiatric disorder diagnosis, small dataset size limits their potential for clinical translation. Data augmentation (DA) could address this limitation, but the utility of EEG DA methods remains relatively underexplored in neuropsychiatric disorder diagnosis. In this study, we train a model for major depressive disorder diagnosis. We then evaluate the utility of 6 EEG DA approaches. Importantly, to remove the bias that could be introduced by comparing performance for models trained on larger augmented training sets to models trained on smaller baseline sets, we also introduce a new baseline trained on duplicate training data to better. We lastly examine the effects of the DA approaches upon representations learned by the model with a pair of explainability analyses. We find that while most approaches boost model performance, they do not improve model performance beyond that of simply using a duplicate training set without DA. The exception to this is channel dropout augmentation, which does improve model performance. These findings suggest the importance of comparing EEG DA methods to a baseline with a duplicate training set of equal size to the augmented training set. We also found that some DA methods increased model robustness to frequency (Fourier transform surrogates) and channel (channel dropout) perturbation. While our findings on EEG DA efficacy are restricted to our dataset and model, we hope that future studies on deep learning for small EEG datasets and on new EEG DA methods will find our findings helpful.

neuroscience↗

bioRxiv2023

Networks extracted from nonlinear fMRI connectivity exhibit unique spatial variation and enhanced sensitivity to differences between individuals with schizophrenia and controls

Functional magnetic resonance imaging (fMRI) studies often estimate brain intrinsic connectivity networks (ICNs) from temporal relationships between hemodynamic signals using approaches such as independent component analysis (ICA). While ICNs are thought to represent functional sources that play important roles in various psychological phenomena, current approaches have been tailored to identify ICNs that mainly reflect linear statistical relationships. However, the elements comprising neural systems often exhibit remarkably complex nonlinear interactions that may be involved in cognitive operations and altered in psychiatric conditions such as schizophrenia. Consequently, there is a need to develop methods capable of effectively capturing ICNs from measures that are sensitive to nonlinear relationships. Here, we advance a novel approach to estimate ICNs from explicitly nonlinear whole-brain functional connectivity (ENL-wFC) by transforming resting-state fMRI (rsfMRI) data into the connectivity domain, allowing us to capture unique information from distance correlation patterns that would be missed by linear whole-brain functional connectivity (LIN-wFC) analysis. Our findings provide evidence that ICNs commonly extracted from linear (LIN) relationships are also reflected in explicitly nonlinear (ENL) connectivity patterns. ENL ICN estimates exhibit higher reliability and stability, highlighting our approachs ability to effectively quantify ICNs from rsfMRI data. Additionally, we observed a consistent spatial gradient pattern between LIN and ENL ICNs with higher ENL weight in core ICN regions, suggesting that ICN function may be subserved by nonlinear processes concentrated within network centers. We also found that a uniquely identified ENL ICN distinguished individuals with schizophrenia from healthy controls while a uniquely identified LIN ICN did not, emphasizing the valuable complementary information that can be gained by incorporating measures that are sensitive to nonlinearity in future analyses. Moreover, the ENL estimates of ICNs associated with auditory, linguistic, sensorimotor, and self-referential processes exhibit heightened sensitivity towards differentiating between individuals with schizophrenia and controls compared to LIN counterparts, demonstrating the translational value of our approach and of the ENL estimates of ICNs that are frequently reported as disrupted in schizophrenia. In summary, our findings underscore the tremendous potential of connectivity domain ICA and nonlinear information in resolving complex brain phenomena and revolutionizing the landscape of clinical FC analysis.

neuroscience↗

bioRxiv2023

Cross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis

Transfer learning offers a route for developing robust deep learning models on small raw electroencephalography (EEG) datasets. Nevertheless, the utility of applying representations learned from large datasets with a lower sampling rate to smaller datasets with higher sampling rates remains relatively unexplored. In this study, we transfer representations learned by a convolutional neural network on a large, publicly available sleep dataset with a 100 Hertz sampling rate to a major depressive disorder (MDD) diagnosis task at a sampling rate of 200 Hertz. Importantly, we find that the early convolutional layers contain representations that are generalizable across tasks. Moreover, our approach significantly increases mean model accuracy from 82.33% to 86.99%, increases the models use of lower frequencies, ({theta}-band), and increases its robustness to channel loss. We expect this analysis to provide useful guidance and enable more widespread use of transfer learning in EEG deep learning studies.

neuroscience↗

bioRxiv2023

A Confounder Controlled Machine Learning Approach: Group Analysis and Classification of Schizophrenia and Alzheimer's Disease using Resting-State Functional Network Connectivity

Resting-state functional magnetic resonance imaging (rs-fMRI) has increasingly been used to study both Alzheimers disease (AD) and schizophrenia (SZ). While most rs-fMRI studies being conducted in AD and SZ compare patients to healthy controls, it is also of interest to directly compare AD and SZ patients with each other to identify potential biomarkers shared between the disorders. However, comparing patient groups collected in different studies can be challenging due to potential confounds, such as differences in the patients age, scan protocols, etc. In this study, we compared and contrasted resting-state functional network connectivity (rs-FNC) of 162 patients with AD and late mild cognitive impairment (LMCI), 181 schizophrenia patients, and 315 cognitively normal (CN) subjects. We used confounder-controlled rs-FNC and applied machine learning algorithms (including support vector machine, logistic regression, random forest, and k-nearest neighbor) and deep learning models (i.e., fully-connected neural networks) to classify subjects in binary and three-class categories according to their diagnosis labels (e.g., AD, SZ, and CN). Our statistical analysis revealed that FNC between the following network pairs is stronger in AD compared to SZ: subcortical-cerebellum, subcortical-cognitive control, cognitive control-cerebellum, and visual-sensory motor networks. On the other hand, FNC is stronger in SZ than AD for the following network pairs: subcortical-visual, subcortical-auditory, subcortical-sensory motor, cerebellum-visual, sensory motor-cognitive control, and within the cerebellum networks. Furthermore, we observed that while AD and SZ disorders each have unique FNC abnormalities, they also share some common functional abnormalities that can be due to similar neurobiological mechanisms or genetic factors contributing to these disorders development. Moreover, we achieved an accuracy of 85% in classifying subjects into AD and SZ where default mode, visual, and subcortical networks contributed the most to the classification and accuracy of 68% in classifying subjects into AD, SZ, and CN with the subcortical domain appearing as the most contributing features to the three-way classification. Finally, our findings indicated that for all classification tasks, except AD vs. SZ, males are more predictable than females.

neuroscience↗

bioRxiv2023

Replication and Refinement of Brain Age Model for adolescent development.

The discrepancy between chronological age and estimated brain age, known as the brain age gap, may serve as a biomarker to reveal brain development and neuropsychiatric problems. This has motivated many studies focusing on the accurate estimation of brain age using different features and models, of which the generalizability is yet to be tested. Our recent study has demonstrated that conventional machine learning models can achieve high accuracy on brain age prediction during development using only a small set of selected features from multimodal brain imaging data. In the current study, we tested the replicability of various brain age models on the Adolescent Brain Cognitive Development (ABCD) cohort. We proposed a new refined model to improve the robustness of brain age prediction. The direct replication test for existing brain age models derived from the age range of 8-22 years onto the ABCD participants at baseline (9 to 10 years old) and year-two follow-up (11 to 12 years old) indicate that pre-trained models could capture the overall mean age failed precisely estimating brain age variation within a narrow range. The refined model, which combined broad prediction of the pre-trained model and granular information with the narrow age range, achieved the best performance with a mean absolute error of 0.49 and 0.48 years on the baseline and year-two data, respectively. The brain age gap yielded by the refined model showed significant associations with the participants information processing speed and verbal comprehension ability on baseline data.

neuroscience↗

bioRxiv2023

Spatial Dynamic Subspaces Encode Sex-Specific Schizophrenia Disruptions in Transient Network Overlap and its Links to Genetic Risk

BackgroundRecent advances in resting-state fMRI allow us to study spatial dynamics, the phenomenon of brain networks spatially evolving over time. However, most dynamic studies still use subject-specific, spatially-static nodes. As recent studies have demonstrated, incorporating time-resolved spatial properties is crucial for precise functional connectivity estimation and gaining unique insights into brain function. Nevertheless, estimating time-resolved networks poses challenges due to the low signal-to-noise ratio, limited information in short time segments, and uncertain identification of corresponding networks within and between subjects. MethodsWe adapt a reference-informed network estimation technique to capture time-resolved spatial networks and their dynamic spatial integration and segregation. We focus on time-resolved spatial functional network connectivity (spFNC), an estimate of network spatial coupling, to study sex-specific alterations in schizophrenia and their links to multi-factorial genomic data. ResultsOur findings are consistent with the dysconnectivity and neurodevelopment hypotheses and align with the cerebello-thalamo-cortical, triple-network, and frontoparietal dysconnectivity models, helping to unify them. The potential unification offers a new understanding of the underlying mechanisms. Notably, the posterior default mode/salience spFNC exhibits sex-specific schizophrenia alteration during the state with the highest global network integration and correlates with genetic risk for schizophrenia. This dysfunction is also reflected in high-dimensional (voxel-level) space in regions with weak functional connectivity to corresponding networks. ConclusionsOur method can effectively capture spatially dynamic networks, detect nuanced SZ effects, and reveal the intricate relationship of dynamic information to genomic data. The results also underscore the potential of dynamic spatial dependence and weak connectivity in the clinical landscape.

neuroscience↗

bioRxiv2023

Alterations in grey matter structure linked to frequency-specific cortico-subcortical connectivity in schizophrenia via multimodal data fusion

Schizophrenia (SZ) is a complex psychiatric disorder that is currently defined by symptomatic and behavioral, rather than biological, criteria. Neuroimaging is an appealing avenue for SZ biomarker development, as several neuroimaging-based studies comparing individuals with SZ to healthy controls (HC) have shown measurable group differences in brain structure, as well as functional brain alterations in both static and dynamic functional network connectivity (sFNC and dFNC, respectively). The recently proposed filter-banked connectivity (FBC) method extends the standard dFNC sliding-window approach to estimate FNC within an arbitrary number of distinct frequency bands. The initial implementation used a set of filters spanning the full connectivity spectral range, providing a unified approach to examine both sFNC and dFNC in a single analysis. Initial FBC results found that individuals with SZ spend more time in a less structured, more disconnected low-frequency (i.e., static) FNC state than HC, as well as preferential SZ occupancy in high-frequency connectivity states, suggesting a frequency-specific component underpinning the functional dysconnectivity observed in SZ. Building on these findings, we sought to link such frequency-specific patterns of FNC to covarying data-driven structural brain networks in the context of SZ. Specifically, we employ a multi-set canonical correlation analysis + joint independent components analysis (mCCA + jICA) data fusion framework to study the connection between grey matter volume (GMV) maps and FBC states across the full connectivity frequency spectrum. Our multimodal analysis identified two joint sources that captured co-varying patterns of frequency-specific functional connectivity and alterations in GMV with significant group differences in loading parameters between the SZ group and HC. The first joint source linked frequency-modulated connections between the subcortical and sensorimotor networks and GMV alterations in the frontal and temporal lobes, while the second joint source identified a relationship between low-frequency cerebellar-sensorimotor connectivity and structural changes in both the cerebellum and motor cortex. Together, these results show a strong connection between cortico-subcortical functional connectivity at both high and low frequencies and alterations in cortical GMV that may be relevant to the pathogenesis and pathophysiology of SZ.

neuroscience↗

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

Decentralized Mixed Effects Modeling in COINSTAC

Performing group analysis on magnetic resonance imaging (MRI) data with linear mixed-effects (LME) models is challenging due to its large dimensionality and inherent multi-level covariance structure. In addition, as large-scale collaborative projects become commonplace in neuroimaging, data must increasingly be stored and analysed at different locations. In such settings, substantial overheads occur in terms of data transfer and coordination between participating research groups. In some cases, data cannot be pooled together due to privacy or regulatory concerns. In this work, we propose a decentralized LME model to perform a large-scale analysis of data from different collaborations without sharing or pooling. This method is efficient as it overcomes the hurdles of data privacy for sharing and has lower bandwidth and memory requirements for analysis than the centralized modeling approach. We evaluate our model using features extracted from structural magnetic resonance imaging (sMRI) data. Results highlight gray matter reductions in the temporal lobe/insula and medical front regions demonstrate the correctness of decentralized LME models. Our analysis also demonstrates that decentralized LME models achieve similar performance compared to the models trained with all the data in one location. We also implement the decentralized LME approach in COINSTAC, a decentralized platform for federating neuroimaging analysis, to demonstrate its value to the neuroimaging community.

neuroscience↗

bioRxiv2023

Improving Explainability for Single-Channel EEG Deep Learning Classifiers via Interpretable Filters and Activation Analysis

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 manually engineered 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. While a number of studies have presented transfer learning approaches for manually engineered EEG features, relatively few approaches have been developed for raw resting-state EEG. In this study, we propose a novel EEG transfer learning approach wherein we first train a model on a large publicly available single-channel sleep stage classification dataset. We then use the learned representations to develop a classifier for automated major depressive disorder diagnosis with raw multichannel EEG. Statistical testing reveals that our approach significantly improves the performance of our model (p < 0.05), and we also find that the performance of our approach exceeds that of many previous studies using both engineered features and raw EEG. We further examine how transfer learning affected the representations learned by the model through a pair of explainability analyses, identifying key frequency bands and channels utilized across models. Our proposed approach represents a significant step forward for the domain of raw resting-state EEG classification and has broader implications for use with other electrophysiology and time-series modalities. Importantly, it has the potential to expand the use of deep learning methods across a greater variety of raw EEG datasets and lead to the development of more reliable EEG classifiers.

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

Pairing Explainable Deep Learning Classification with Clustering to Uncover Effects of Schizophrenia Upon Whole Brain Functional Network Connectivity Dynamics

Many studies have analyzed resting state functional magnetic resonance imaging (rs-fMRI) dynamic functional network connectivity (dFNC) data to elucidate the effects of neurological and neuropsychiatric disorders upon the interactions of brain regions over time. Existing studies often use either machine learning classification or clustering algorithms. Additionally, several studies have used clustering algorithms to extract features related to brain states trajectories that can be used to train interpretable classifiers. However, the combination of explainable dFNC classifiers followed by clustering algorithms is highly underutilized. In this study, we show how such an approach can be used to study the effects of schizophrenia (SZ) upon brain activity. Specifically, we train an explainable deep learning model to classify between individuals with SZ and healthy controls. We then cluster the resulting explanations, identifying discriminatory states of dFNC. We lastly apply several novel measures to quantify aspects of the classifier explanations and obtain additional insights into the effects of SZ upon brain network dynamics. Specifically, we uncover effects of schizophrenia upon subcortical, sensory, and cerebellar network interactions. We also find that individuals with SZ likely have reduced variability in overall brain activity and that the effects of SZ may be temporally localized. In addition to uncovering effects of SZ upon brain network dynamics, our approach could provide novel insights into a variety of neurological and neuropsychiatric disorders in future dFNC studies.

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↗

bioRxiv2023

A Novel Explainable Fuzzy Clustering Approach for fMRI Dynamic Functional Network Connectivity Analysis

Resting state functional magnetic resonance imaging (rs-fMRI) dynamic functional network connectivity (dFNC) analysis has illuminated brain network interactions across many neuropsychiatric disorders. A common analysis approach involves using hard clustering methods to identify transitory states of brain activity, and in response to this, other methods have been developed to quantify the importance of specific dFNC interactions to identified states. Some of these methods involve perturbing individual features and examining the number of samples that switch states. However, only a minority of samples switch states. As such, these methods actually identify the importance of dFNC features to the clustering of a subset of samples rather than the overall clustering. In this study, we present a novel approach that more capably identifies the importance of each feature to the overall clustering. Our approach uses fuzzy clustering to output probabilities of each sample belonging to states and then measures their Kullback-Leibler divergence after perturbation. We show the viability of our approach in the context of schizophrenia (SZ) default mode network analysis, identifying significant differences in state dynamics between individuals with SZ and healthy controls. We further compare our approach with an existing approach, showing that it captures the effects of perturbation upon most samples. We also find that interactions between the posterior cingulate cortex (PCC) and the anterior cingulate cortex and the PCC and precuneus are important across methods. We expect that our novel explainable clustering approach will enable further progress in rs-fMRI analysis and to other clustering applications.

neuroscience↗

bioRxiv2023

Bridging Big Data: Procedures for Combining Non-equivalent Cognitive Measures from the ENIGMA Consortium

Investigators in neuroscience have turned to Big Data to address replication and reliability issues by increasing sample sizes, statistical power, and representativeness of data. These efforts unveil new questions about integrating data arising from distinct sources and instruments. We focus on the most frequently assessed cognitive domain - memory testing - and demonstrate a process for reliable data harmonization across three common measures. We aggregated global raw data from 53 studies totaling N = 10,505 individuals. A mega-analysis was conducted using empirical bayes harmonization to remove site effects, followed by linear models adjusting for common covariates. A continuous item response theory (IRT) model estimated each individuals latent verbal learning ability while accounting for item difficulties. Harmonization significantly reduced inter-site variance while preserving covariate effects, and our conversion tool is freely available online. This demonstrates that large-scale data sharing and harmonization initiatives can address reproducibility and integration challenges across the behavioral sciences. TeaserWe present a global effort to devise harmonization procedures necessary to meaningfully leverage big data.

neuroscience↗

bioRxiv2022

Neuropsychiatric Disorder Subtyping Via Clustered Deep Learning Classifier Explanations

Identifying subtypes of neuropsychiatric disorders based on characteristics of their brain activity has tremendous potential to contribute to a better understanding of those disorders and to the development of new diagnostic and personalized treatment approaches. Many studies focused on neuropsychiatric disorders examine the interaction of brain networks over time using dynamic functional network connectivity (dFNC) extracted from resting-state functional magnetic resonance imaging data. Some of these studies involve the use of either deep learning classifiers or traditional clustering approaches, but usually not both. In this study, we present a novel approach for subtyping individuals with neuropsychiatric disorders within the context of schizophrenia (SZ). We train an explainable deep learning classifier to differentiate between dFNC data from individuals with SZ and controls, obtaining a test accuracy of 79%. We next make use of cross-validation to obtain robust average explanations for SZ training participants across folds, identifying 5 SZ subtypes that each differ from controls in a distinct manner and that have different degrees of symptom severity. These subtypes specifically differ from one another in their interaction between the visual network and the subcortical, sensorimotor, and auditory networks and between the cerebellar network and the cognitive control and subcortical networks. Additionally, there are statistically significant differences in negative symptom scores between the subtypes. It is our hope that the proposed novel subtyping approach will contribute to the improved understanding and characterization of SZ and other neuropsychiatric disorders.

neuroscience↗