Refine
Language
- English (14) (remove)
Has Fulltext
- yes (14)
Is part of the Bibliography
- no (14) (remove)
Keywords
- Machine learning (2)
- fMRI (2)
- Auto-ML (1)
- Behavior (1)
- Brain size I (1)
- Classification (1)
- Depression (1)
- Employment (1)
- Face (1)
- Finance (1)
Institute
- Psychologie (9)
- Medizin (6)
Pattern recognition applied to whole-brain neuroimaging data, such as functional Magnetic Resonance Imaging (fMRI), has proved successful at discriminating psychiatric patients from healthy participants. However, predictive patterns obtained from whole-brain voxel-based features are difficult to interpret in terms of the underlying neurobiology. Many psychiatric disorders, such as depression and schizophrenia, are thought to be brain connectivity disorders. Therefore, pattern recognition based on network models might provide deeper insights and potentially more powerful predictions than whole-brain voxel-based approaches. Here, we build a novel sparse network-based discriminative modeling framework, based on Gaussian graphical models and L1-norm regularized linear Support Vector Machines (SVM). In addition, the proposed framework is optimized in terms of both predictive power and reproducibility/stability of the patterns. Our approach aims to provide better pattern interpretation than voxel-based whole-brain approaches by yielding stable brain connectivity patterns that underlie discriminative changes in brain function between the groups. We illustrate our technique by classifying patients with major depressive disorder (MDD) and healthy participants, in two (event- and block-related) fMRI datasets acquired while participants performed a gender discrimination and emotional task, respectively, during the visualization of emotional valent faces.
Functional near-infrared spectroscopy (fNIRS) is an established optical neuroimaging method for measuring functional hemodynamic responses to infer neural activation. However, the impact of individual anatomy on the sensitivity of fNIRS measuring hemodynamics within cortical gray matter is still unknown. By means of Monte Carlo simulations and structural MRI of 23 healthy subjects (mean age: (25.0 +- 2.8 years), we characterized the individual distribution of tissue-specific NIR-light absorption underneath 24 prefrontal fNIRS channels. We, thereby, investigated the impact of scalp-cortex distance (SCD), frontal sinus volume as well as sulcal morphology on gray matter volumes (V gray) traversed by NIR-light, i.e. anatomy-dependent fNIRS sensitivity. The NIR-light absorption between optodes was distributed describing a rotational ellipsoid with a mean penetration depth of (23.6 +- 0.7 mm) considering the deepest 5% of light. Of the detected photon packages scalp and bone absorbed (96.4 +- 9.7)% and absorbed (3,1 +- 1.8)% of the energy. The mean V gray volume (1.1 +- 0.4)cm 3 was negatively correlated (r = -.76) with the SCD and frontal sinus volume (r= -.57) and was reduced by in subjects with relatively large compared to small frontal sinus. Head circumference was significantly positively correlated with the mean SCD (r= .46) and the traversed frontal sinus volume (r= .43). Sulcal morphology had no significant impact on . Our findings suggest to consider individual SCD and frontal sinus volume as anatomical factors impacting fNIRS sensitivity. Head circumference may represent a practical measure to partly control for these sources of error variance.
Introduction: Affective disorders are a major global burden, with approximately 15% of people worldwide suffering from some form of affective disorder. In patients experiencing their first depressive episode, in most cases it cannot be distinguished whether this is due to bipolar disorder (BD) or major depressive disorder (MDD). Valid fluid biomarkers able to discriminate between the two disorders in a clinical setting are not yet available.
Material and Methods: Seventy depressed patients suffering from BD (bipolar I and II subtypes) and 42 patients with major MDD were recruited and blood samples were taken for proteomic analyses after 8 h fasting. Proteomic profiles were analyzed using the Multiplex Immunoassay platform from Myriad Rules Based Medicine (Myriad RBM; Austin, Texas, USA). Human DiscoveryMAPTM was used to measure the concentration of various proteins, peptides, and small molecules. A multivariate predictive model was consequently constructed to differentiate between BD and MDD.
Results: Based on the various proteomic profiles, the algorithm could discriminate depressed BD patients from MDD patients with an accuracy of 67%.
Discussion: The results of this preliminary study suggest that future discrimination between bipolar and unipolar depression in a single case could be possible, using predictive biomarker models based on blood proteomic profiling.
A positive association between brain size and intelligence is firmly established, but whether region-specific anatomical differences contribute to general intelligence remains an open question. Results from voxel-based morphometry (VBM) - one of the most widely used morphometric methods - have remained inconclusive so far. Here, we applied cross-validated machine learning-based predictive modeling to test whether out-of-sample prediction of individual intelligence scores is possible on the basis of voxel-wise gray matter volume. Features were derived from structural magnetic resonance imaging data (N = 308) using (a) a purely data-driven method (principal component analysis) and (b) a domain knowledge-based approach (atlas parcellation). When using relative gray matter (corrected for total brain size), only the atlas-based approach provided significant prediction, while absolute gray matter (uncorrected) allowed for above-chance prediction with both approaches. Importantly, in all significant predictions, the absolute error was relatively high, i.e., greater than ten IQ points, and in the atlas-based models, the predicted IQ scores varied closely around the sample mean. This renders the practical value even of statistically significant prediction results questionable. Analyses based on the gray matter of functional brain networks yielded significant predictions for the fronto-parietal network and the cerebellum. However, the mean absolute errors were not reduced in contrast to the global models, suggesting that general intelligence may be related more to global than region-specific differences in gray matter volume. More generally, our study highlights the importance of predictive statistical analysis approaches for clarifying the neurobiological bases of intelligence and provides important suggestions for future research using predictive modeling.
Graph data is an omnipresent way to represent information in machine learning. Especially, in neuroscience research, data from Diffusion-Tensor Imaging (DTI) and functional Magnetic Resonance Imaging (fMRI) is commonly represented as graphs. Exploiting the graph structure of these modalities using graph-specific machine learning applications is currently hampered by the lack of easy-to-use software. PHOTONAI Graph aims to close the gap between domain experts of machine learning, graph experts and neuroscientists. Leveraging the rapid machine learning model development features of the Python machine learning API PHOTONAI, PHOTONAI Graph enables the design, optimization, and evaluation of reliable graph machine learning models for practitioners. As such, it provides easy access to custom graph machine learning pipelines including, hyperparameter optimization and algorithm evaluation ensuring reproducibility and valid performance estimates. Integrating established algorithms such as graph neural networks, graph embeddings and graph kernels, it allows researchers without significant coding experience to build and optimize complex graph machine learning models within a few lines of code. We showcase the versatility of this toolbox by building pipelines for both resting–state fMRI and DTI data in the hope that it will increase the adoption of graph-specific machine learning algorithms in neuroscience research.
Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers.
The extinction of conditioned fear depends on an efficient interplay between the amygdala and the medial prefrontal cortex (mPFC). In rats, high-frequency electrical mPFC stimulation has been shown to improve extinction by means of a reduction of amygdala activity. However, so far it is unclear whether stimulation of homologues regions in humans might have similar beneficial effects. Healthy volunteers received one session of either active or sham repetitive transcranial magnetic stimulation (rTMS) covering the mPFC while undergoing a 2-day fear conditioning and extinction paradigm. Repetitive TMS was applied offline after fear acquisition in which one of two faces (CS+ but not CS−) was associated with an aversive scream (UCS). Immediate extinction learning (day 1) and extinction recall (day 2) were conducted without UCS delivery. Conditioned responses (CR) were assessed in a multimodal approach using fear-potentiated startle (FPS), skin conductance responses (SCR), functional near-infrared spectroscopy (fNIRS), and self-report scales. Consistent with the hypothesis of a modulated processing of conditioned fear after high-frequency rTMS, the active group showed a reduced CS+/CS− discrimination during extinction learning as evident in FPS as well as in SCR and arousal ratings. FPS responses to CS+ further showed a linear decrement throughout both extinction sessions. This study describes the first experimental approach of influencing conditioned fear by using rTMS and can thus be a basis for future studies investigating a complementation of mPFC stimulation to cognitive behavioral therapy (CBT).
Mapping cortical brain asymmetry in 17,141 healthy individuals worldwide via the ENIGMA Consortium
(2017)
The Behavioral Inhibition System (BIS) as defined within the Reinforcement Sensitivity Theory (RST) modulates reactions to stimuli indicating aversive events. Gray’s trait Anxiety determines the extent to which stimuli activate the BIS. While studies have identified the amygdala-septo-hippocampal circuit as the key-neural substrate of this system in recent years and measures of resting-state dynamics such as randomness and local synchronization of spontaneous BOLD fluctuations have recently been linked to personality traits, the relation between resting-state dynamics and the BIS remains unexplored. In the present study, we thus examined the local synchronization of spontaneous fMRI BOLD fluctuations as measured by Regional Homogeneity (ReHo) in the hippocampus and the amygdala in twenty-seven healthy subjects. Correlation analyses showed that Gray’s trait Anxiety was significantly associated with mean ReHo in both the amygdala and the hippocampus. Specifically, Gray’s trait Anxiety explained 23% and 17% of resting-state ReHo variance in the left amygdala and the left hippocampus, respectively. In summary, we found individual differences in Gray’s trait Anxiety to be associated with ReHo in areas previously associated with BIS functioning. Specifically, higher ReHo in resting-state neural dynamics corresponded to lower sensitivity to punishment scores both in the amygdala and the hippocampus. These findings corroborate and extend recent findings relating resting-state dynamics and personality while providing first evidence linking properties of resting-state fluctuations to Gray’s BIS.
Reciprocal exchanges can be understood as the updating of an initial belief about a partner. This initial level of trust is essential when it comes to establishing cooperation with an unknown partner, as cooperation cannot arise without a minimum of trust not justified by previous successful exchanges with this partner. Here we demonstrate the existence of a representation of the initial trust level before an exchange with a partner has occurred. Specifically, we can predict the Investor’s initial investment—i.e. his initial level of trust toward the unknown trustee in Round 1 of a standard 10-round Trust Game—from resting-state functional connectivity data acquired several minutes before the start of the Trust Game. Resting-state functional connectivity is, however, not significantly associated with the level of trust in later rounds, potentially mirroring the updating of the initial belief about the partner. Our results shed light on how the initial level of trust is represented. In particular, we show that a person’s initial level of trust is, at least in part, determined by brain electrical activity acquired well before the beginning of an exchange.