Control-group feature normalization for multivariate pattern analysis of structural MRI data using the support vector machine

AbstractFunctional brain connectivity is altered in children and adults with autism spectrum disorder (ASD). Mapping pre-symptomatic functional disruptions in ASD could identify infants based on neural risk, providing a crucial opportunity to mediate outcomes before behavioral symptoms emerge.Here we quantify functional connectivity using scalable EEG measures of oscillatory phase coherence (6-12Hz). Infants at high and low familial risk for ASD (N=65) underwent an EEG recording at 3 months of age and were assessed for ASD symptoms at 18 months using the Autism Diagnostic Observation Schedule-Toddler Module. Multivariate pattern analysis was used to examine early functional patterns that are associated with later ASD symptoms.Support vector regression (SVR) algorithms accurately predicted observed ASD symptoms at 18 months from EEG data at 3 months (r=0.76, p=0.02). Specifically, lower frontal connectivity and higher right temporo-parietal connectivity predicted higher ASD symptoms. The SVR model did not predict non-verbal cognitive abilities at 18 months (r=0.15, p=0.36), suggesting specificity of these brain alterations to ASD.These data suggest that frontal and temporo-parietal dysconnectivity play important roles in the early pathophysiology of ASD. Early functional differences in ASD can be captured using EEG during infancy and may inform much-needed advancements in the early detection of ASD.

Download Full-text

25.3 IMAGING ACCELERATED AGING MACHINE-LEARNING BASED MULTIVARIATE PATTERN ANALYSIS OF STRUCTURAL MRI IN SCHIZOPHRENIA AND ULTRA-HIGH-RISK SUBJECTS

Schizophrenia Bulletin ◽

10.1093/schbul/sbz022.103 ◽

2019 ◽

Vol 45 (Supplement_2) ◽

pp. S130-S130

Author(s):

Igor Nenadic

Keyword(s):

Machine Learning ◽

High Risk ◽

Pattern Analysis ◽

Accelerated Aging ◽

Structural Mri ◽

Multivariate Pattern Analysis ◽

Ultra High Risk ◽

Multivariate Pattern

Download Full-text

Multivariate pattern analysis of brain structure predicts functional outcome after auditory-based cognitive training interventions

npj Schizophrenia ◽

10.1038/s41537-021-00165-0 ◽

2021 ◽

Vol 7 (1) ◽

Author(s):

Lana Kambeitz-Ilankovic ◽

Sophia Vinogradov ◽

Julian Wenzel ◽

Melissa Fisher ◽

Shalaila S. Haas ◽

...

Keyword(s):

Cognitive Training ◽

Cross Validation ◽

Pattern Analysis ◽

Anterior Cingulate ◽

Support Vector ◽

Single Subject ◽

Multivariate Pattern Analysis ◽

Whole Brain ◽

Training Interventions ◽

Multivariate Pattern

AbstractCognitive gains following cognitive training interventions are associated with improved functioning in people with schizophrenia (SCZ). However, considerable inter-individual variability is observed. Here, we evaluate the sensitivity of brain structural features to predict functional response to auditory-based cognitive training (ABCT) at a single-subject level. We employed whole-brain multivariate pattern analysis with support vector machine (SVM) modeling to identify gray matter (GM) patterns that predicted higher vs. lower functioning after 40 h of ABCT at the single-subject level in SCZ patients. The generalization capacity of the SVM model was evaluated by applying the original model through an out-of-sample cross-validation analysis to unseen SCZ patients from an independent validation sample who underwent 50 h of ABCT. The whole-brain GM volume-based pattern classification predicted higher vs. lower functioning at follow-up with a balanced accuracy (BAC) of 69.4% (sensitivity 72.2%, specificity 66.7%) as determined by nested cross-validation. The neuroanatomical model was generalizable to an independent cohort with a BAC of 62.1% (sensitivity 90.9%, specificity 33.3%). In particular, greater baseline GM volumes in regions within superior temporal gyrus, thalamus, anterior cingulate, and cerebellum predicted improved functioning at the single-subject level following ABCT in SCZ participants. The present findings provide a structural MRI fingerprint associated with preserved GM volumes at a single baseline timepoint, which predicted improved functioning following an ABCT intervention, and serve as a model for how to facilitate precision clinical therapies for SCZ based on imaging data, operating at the single-subject level.

Download Full-text

Diagnostic Prediction for Social Anxiety Disorder via Multivariate Pattern Analysis of the Regional Homogeneity

BioMed Research International ◽

10.1155/2015/763965 ◽

2015 ◽

Vol 2015 ◽

pp. 1-9 ◽

Cited By ~ 4

Author(s):

Wenjing Zhang ◽

Xun Yang ◽

Su Lui ◽

Yajing Meng ◽

Li Yao ◽

...

Keyword(s):

Anxiety Disorder ◽

Social Anxiety ◽

Social Anxiety Disorder ◽

Pattern Analysis ◽

Initial Step ◽

Regional Homogeneity ◽

Support Vector ◽

Multivariate Pattern Analysis ◽

Diagnostic Potential ◽

Multivariate Pattern

Although decades of efforts have been spent studying the pathogenesis of social anxiety disorder (SAD), there are still no objective biological markers that could be reliably used to identify individuals with SAD. Studies using multivariate pattern analysis have shown the potential value in clinically diagnosing psychiatric disorders with neuroimaging data. We therefore examined the diagnostic potential of regional homogeneity (ReHo) underlying neural correlates of SAD using support vector machine (SVM), which has never been studied. Forty SAD patients and pairwise matched healthy controls were recruited and scanned by resting-state fMRI. The ReHo was calculated as synchronization of fMRI signals of nearest neighboring 27 voxels. A linear SVM was then adopted and allowed the classification of the two groups with diagnostic accuracy of ReHo that was 76.25% (sensitivity = 70%, and specificity = 82.5%,P≤0.001). Regions showing different discriminating values between diagnostic groups were mainly located in default mode network, dorsal attention network, self-referential network, and sensory networks, while the left medial prefrontal cortex was identified with the highest weight. These results implicate that ReHo has good diagnostic potential in SAD, and thus may provide an initial step towards the possible use of whole brain local connectivity to inform the clinical evaluation.

Download Full-text

Multivariate pattern analysis for MEG: a comprehensive comparison of dissimilarity measures

10.1101/172619 ◽

2017 ◽

Cited By ~ 2

Author(s):

Matthias Guggenmos ◽

Philipp Sterzer ◽

Radoslaw M. Cichy

Keyword(s):

Euclidean Distance ◽

Pattern Analysis ◽

Pearson Correlation ◽

Support Vector ◽

Multivariate Pattern Analysis ◽

Linear Discriminant ◽

Dissimilarity Measures ◽

The Cross ◽

Time Courses ◽

Multivariate Pattern

Multivariate pattern analysis (MVPA) methods such as decoding and representational similarity analysis (RSA) are growing rapidly in popularity for the analysis of magnetoencephalography (MEG) data. However, little is known about the relative performance and characteristics of the specific dissimilarity measures used to describe differences between evoked activation patterns. Here we used a multisession MEG dataset to qualitatively characterize a range of dissimilarity measures and to quantitatively compare them with respect to classification accuracy (for decoding) and between-session reliability of representational dissimilarity matrices (for RSA). We tested dissimilarity measures from a range of classifiers (Linear Discriminant Analysis - LDA, Support Vector Machine - SVM, Weighted Robust Distance - WeiRD, Gaussian Naive Bayes - GNB) and distances (Euclidean distance, Pearson correlation). In addition, we evaluated three key processing choices: 1) preprocessing (noise normalisation, removal of the pattern mean), 2) weighting classification accuracies by decision values, and 3) computing distances in three different partitioning schemes (non-cross-validated, cross-validated, within-class-corrected). Four main conclusions emerged from our results. First, multivariate noise normalization dramatically improved classification accuracies and the reliability of dissimilarity measures. Second, LDA, SVM and WeiRD yielded high peak classification accuracies and nearly identical time courses. Third, while using classification accuracies for RSA was markedly less reliable than continuous distances, this disadvantage was ameliorated by decision-value-weighting of classification accuracies. Fourth, the cross-validated Euclidean distance provided unbiased distance estimates and highly replicable representational dissimilarity matrices. Overall, we strongly advice the use of multivariate noise normalisation as a general preprocessing step, recommend LDA, SVM and WeiRD as classifiers for decoding and highlight the cross-validated Euclidean distance as a reliable and unbiased default choice for RSA.

Download Full-text

Identifying Depressed Essential Tremor Using Resting-State Voxel-Wise Global Brain Connectivity: A Multivariate Pattern Analysis

Frontiers in Human Neuroscience ◽

10.3389/fnhum.2021.736155 ◽

2021 ◽

Vol 15 ◽

Author(s):

Yufen Li ◽

Li Tao ◽

Huiyue Chen ◽

Hansheng Wang ◽

Xiaoyu Zhang ◽

...

Keyword(s):

Machine Learning ◽

Prefrontal Cortex ◽

Essential Tremor ◽

Resting State ◽

Pattern Analysis ◽

Brain Connectivity ◽

Support Vector ◽

Multivariate Pattern Analysis ◽

Multivariate Pattern ◽

Global Brain

Background and Objective: Although depression is one of the most common non-motor symptoms in essential tremor (ET), its pathogenesis and diagnosis biomarker are still unknown. Recently, machine learning multivariate pattern analysis (MVPA) combined with connectivity mapping of resting-state fMRI has provided a promising way to identify patients with depressed ET at the individual level and help to reveal the brain network pathogenesis of depression in patients with ET.Methods: Based on global brain connectivity (GBC) mapping from 41 depressed ET, 49 non-depressed ET, 45 primary depression, and 43 healthy controls (HCs), multiclass Gaussian process classification (GPC) and binary support vector machine (SVM) algorithms were used to identify patients with depressed ET from non-depressed ET, primary depression, and HCs, and the accuracy and permutation tests were used to assess the classification performance.Results: While the total accuracy (40.45%) of four-class GPC was poor, the four-class GPC could discriminate depressed ET from non-depressed ET, primary depression, and HCs with a sensitivity of 70.73% (P < 0.001). At the same time, the sensitivity of using binary SVM to discriminate depressed ET from non-depressed ET, primary depression, and HCs was 73.17, 80.49, and 75.61%, respectively (P < 0.001). The significant discriminative features were mainly located in cerebellar-motor-prefrontal cortex circuits (P < 0.001), and a further correlation analysis showed that the GBC values of significant discriminative features in the right middle prefrontal gyrus, bilateral cerebellum VI, and Crus 1 were correlated with clinical depression severity in patients with depressed ET.Conclusion: Our findings demonstrated that GBC mapping combined with machine learning MVPA could be used to identify patients with depressed ET, and the GBC changes in cerebellar-prefrontal cortex circuits not only posed as the significant discriminative features but also helped to understand the network pathogenesis underlying depression in patients with ET.

Download Full-text

Multivariate pattern analysis of brain structure predicts functional outcome after auditory-based cognitive training interventions

10.1101/2020.09.06.283481 ◽

2020 ◽

Author(s):

Lana Kambeitz-Ilankovic ◽

Sophia Vinogradov ◽

Julian Wenzel ◽

Melissa Fisher ◽

Shalaila S. Haas ◽

...

Keyword(s):

Cognitive Training ◽

Cross Validation ◽

Pattern Analysis ◽

Anterior Cingulate ◽

Support Vector ◽

Single Subject ◽

Multivariate Pattern Analysis ◽

Whole Brain ◽

Training Interventions ◽

Multivariate Pattern

AbstractBackgroundCognitive gains following cognitive training interventions (CT) are associated with improved functioning in people with schizophrenia (SCZ). However, considerable inter-individual variability is observed. Here, we evaluate the sensitivity of brain structural features to predict functional response to auditory-based cognitive training (ABCT) at a single subject level.MethodsWe employed whole-brain multivariate pattern analysis (MVPA) with support vector machine (SVM) modeling to identify grey matter (GM) patterns that predicted ‘higher’ vs. ‘lower’ functioning after 40 hours of ABCT at the single subject level in SCZ patients. The generalization capacity of the SVM model was evaluated by applying the original model through an Out-Of-Sample Cross Validation analysis (OOCV) to unseen SCZ patients from an independent sample that underwent 50 hours of ABCT.ResultsThe whole-brain GM volume-based pattern classification predicted ‘higher’ vs. ‘lower’ functioning at follow-up with a balanced accuracy (BAC) of 69.4% (sensitivity 72.2%, specificity 66.7%) as determined by nested cross-validation. The neuroanatomical model was generalizable to an independent cohort with a BAC of 62.1% (sensitivity 90.9%, specificity 33.3%).ConclusionsIn particular, greater baseline GM volume in regions within superior temporal gyrus, thalamus, anterior cingulate and cerebellum -- predicted improved functioning at the single-subject level following ABCT in SCZ participants.

Download Full-text

The Decision Decoding ToolBOX (DDTBOX) – A multivariate pattern analysis toolbox for event-related potentials

10.1101/153189 ◽

2017 ◽

Cited By ~ 2

Author(s):

Stefan Bode ◽

Daniel Feuerriegel ◽

Daniel Bennett ◽

Phillip M. Alday

Keyword(s):

Open Source ◽

Pattern Analysis ◽

Event Related Potentials ◽

Event Related Potential ◽

Statistical Testing ◽

Support Vector ◽

Single Subject ◽

Multivariate Pattern Analysis ◽

Related Potentials ◽

Multivariate Pattern

AbstractIn recent years, neuroimaging research in cognitive neuroscience has increasingly used multivariate pattern analysis (MVPA) to investigate higher cognitive functions. Here we present DDTBOX, an open-source MVPA toolbox for electroencephalography (EEG) data. DDTBOX runs under MATLAB and is well integrated with the EEGLAB/ERPLAB and Fieldtrip toolboxes (Delorme and Makeig, 2004; Lopez-Calderon and Luck, 2014; Oostenveld et al. 2011). It trains support vector machines (SVMs) on patterns of event-related potential (ERP) amplitude data, following or preceding an event of interest, for classification or regression of experimental variables. These amplitude patterns can be extracted across space/electrodes (spatial decoding), time (temporal decoding), or both (spatiotemporal decoding). DDTBOX can also extract SVM feature weights, generate empirical chance distributions based on shuffled-labels decoding for group-level statistical testing, provide estimates of the prevalence of decodable information in the population, and perform a variety of corrections for multiple comparisons. It also includes plotting functions for single subject and group results. DDTBOX complements conventional analyses of ERP components, as subtle multivariate patterns can be detected that would be overlooked in standard analyses. It further allows for a more explorative search for information when no ERP component is known to be specifically linked to a cognitive process of interest. In summary, DDTBOX is an easy-to-use and open-source toolbox that allows for characterising the time-course of information related to various perceptual and cognitive processes. It can be applied to data from a large number of experimental paradigms and could therefore be a valuable tool for the neuroimaging community.

Download Full-text