Associating schizophrenia with disrupted functional connectivity is a central idea in schizophrenia research. However, identifying neuroimaging-based features that can serve as reliable “statistical biomarkers” of the disease remains a challenging open problem. We argue that generalization accuracy and stability of candidate features (“biomarkers”) must be used as additional criteria on top of standard significance tests in order to discover more robust biomarkers. Generalization accuracy refers to the utility of biomarkers for making predictions about individuals, for example discriminating between patients and controls, in novel datasets. Feature stability refers to the reproducibility of the candidate features across different datasets. Here, we extracted functional connectivity network features from fMRI data at both high-resolution (voxel-level) and a spatially down-sampled lower-resolution (“supervoxel” level). At the supervoxel level, we used whole-brain network links, while at the voxel level, due to the intractably large number of features, we sampled a subset of them. We compared statistical significance, stability and discriminative utility of both feature types in a multi-site fMRI dataset, composed of schizophrenia patients and healthy controls. For both feature types, a considerable fraction of features showed significant differences between the two groups. Also, both feature types were similarly stable across multiple data subsets. However, the whole-brain supervoxel functional connectivity features showed a higher cross-validation classification accuracy of 78.7% vs. 72.4% for the voxel-level features. Cross-site variability and heterogeneity in the patient samples in the multi-site FBIRN dataset made the task more challenging compared to single-site studies. The use of the above methodology in combination with the fully data-driven approach using the whole brain information have the potential to shed light on “biomarker discovery” in schizophrenia.
The objective of this study is to investigate effects of methylphenidate on brain activity in individuals with cocaine use disorder (CUD) using functional MRI (fMRI). Methylphenidate hydrochloride (MPH) is an indirect dopamine agonist commonly used for treating attention deficit/hyperactivity disorders; it was also shown to have some positive effects on CUD subjects, such as improved stop signal reaction times associated with better control/inhibition,1 as well as normalized task-related brain activity2 and resting-state functional connectivity in specific areas.3 While prior fMRI studies of MPH in CUDs have focused on mass-univariate statistical hypothesis testing, this paper evaluates multivariate, whole-brain effects of MPH as captured by the generalization (prediction) accuracy of different classification techniques applied to features extracted from resting-state functional networks (e.g., node degrees). Our multivariate predictive results based on resting-state data from3 suggest that MPH tends to normalize network properties such as voxel degrees in CUD subjects, thus providing additional evidence for potential benefits of MPH in treating cocaine addiction.
This paper focuses on discovering statistical biomarkers (features) that are predictive of schizophrenia, with a
particular focus on topological properties of fMRI functional networks. We consider several network properties,
such as node (voxel) strength, clustering coefficients, local efficiency, as well as just a subset of pairwise correlations.
While all types of features demonstrate highly significant statistical differences in several brain areas,
and close to 80% classification accuracy, the most remarkable results of 93% accuracy are achieved by using
a small subset of only a dozen of most-informative (lowest p-value) correlation features. Our results suggest
that voxel-level correlations and functional network features derived from them are highly informative about
schizophrenia and can be used as statistical biomarkers for the disease.
One of key topics in fMRI analysis is discovery of task-related brain areas. We focus on predictive accuracy
as a better relevance measure than traditional univariate voxel activations that miss important multivariate
voxel interactions. We use sparse regression (more specifically, the Elastic Net1) to learn predictive models
simultaneously with selection of predictive voxel subsets, and to explore transition from task-relevant to task-irrelevant
areas. Exploring the space of sparse solutions reveals a much wider spread of task-relevant information
in the brain than it is typically suggested by univariate correlations. This happens for several tasks we considered,
and is most noticeable in case of complex tasks such as pain rating; however, for certain simpler tasks, a clear
separation between a small subset of relevant voxels and the rest of the brain is observed even with multivariate
approach to measuring relevance.