Decoding negative affect personality trait from patterns of brain activation to threat stimuli

Fernandes, Orlando; Portugal, Liana Catarina Lima; Alves, Rita de Cássia; Sanchez, Tiago Arruda; Rao, Anil; Volchan, Eliane; Pereira, Mirtes Garcia; Oliveira, Letícia; Mourão-Miranda, Janaı́na

doi:10.1016/j.neuroimage.2015.12.050

Cited by 30 publications

(28 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NA trait has been also associated with poor prognosis [72] and predictive of onset of major depression [73]. Furthermore, a recent study showed that it is possible to decode individuals NA trait from patterns of brain activation to threat stimuli in a sample of healthy subject [74]. Our results, corroborate with these previous studies and support the evidence that Negative Affect trait might 755 have important clinical implications for depression.…”

supporting

confidence: 89%

Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important

Donini

Monteiro

Pontil

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Combining neuroimaging and clinical information for diagnosis, as for example behavioral tasks and genetics characteristics, is potentially beneficial but presents challenges in terms of finding the best data representation for the different sources of information. Their simple combination usually does not provide an improvement if compared with using the best source alone. In this paper, we proposed a framework based on a recent multiple kernel learning algorithm called EasyMKL and we investigated the benefits of this approach for diagnosing two different mental health diseases. The well known Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset tackling the Alzheimer Disease (AD) patients versus healthy controls classification task, and a second dataset tack- * Corresponding author Email address: michele.donini@iit.it (Michele Donini) † Data used in preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_ Acknowledgement_List.pdf ling the task of classifying an heterogeneous group of depressed patients versus healthy controls. We used EasyMKL to combine a huge amount of basic kernels alongside a feature selection methodology, pursuing an optimal and sparse solution to facilitate interpretability. Our results show that the proposed approach, called EasyMKLFS, outperforms baselines (e.g. SVM and SimpleMKL), state-of-the-art random forests (RF) and feature selection (FS) methods.nitive decline in older adults. In this case, the authors use the 2 -MKL with two Gaussian kernels, one for the MRI features and one for the clinical measurements. These kernels have two different hyper-parameters which were fixed by using a heuristic method. They claim that, by using only the MRI information or the clinical measurements alone, the kernels do not carry sufficient 50 information to predict cognitive decline. On the other hand, using the kernel ob-65 approach [10]). In both studies, [8] and [9], the feature selection is applied before the generation of the kernels. Moreover, the brute force selection for the kernels weights, performed by using a grid search approach, is able to combine only few kernels and often finds a sub-optimal solution due to the manual selection of the search grid. In this sense, a MKL approach is more robust and theoretically 70 grounded. A recent paper by Xing Meng et al. [11] proposes a framework to predict clinical measures by using a multi-step approach. The authors combine three different neuroimaging modalities: resting-state functional Magnetic Resonance Image (fMRI), structural Magnetic Resonance Image (sMRI) and Diffusion Ten-75 sor Imaging (DTI). After a feature selection step within each of the single modalities, a selecti...

show abstract

supporting

confidence: 89%

Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important

Donini

Monteiro

Pontil

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The analysis aimed to test whether participants' diffusion of responsibility could be decoded from resting‐state connectivity patterns of dACC and putamen [Fernandes et al, ]. This complemented the univariate correlational analysis by providing two primary advantages: (i) the multivariate nature of the analysis enabled the detection of subtle and spatially distributed effects and (ii) the analysis allowed for predicting unseen participants, offering information at the individual rather than at the group level.…”

Section: Methodsmentioning

confidence: 99%

“…The pattern regression analysis was implemented in PRoNTo (http://www.mlnl.cs.ucl.ac.uk/pronto/) and included the following steps [Fernandes et al, ; Schrouff et al, ]: (1) The resting‐state connectivity of dACC and putamen as seeding regions was derived from the seed‐to‐voxel connectivity analysis. (2) The whole brain was split into 116 anatomical regions according to the aal atlas.…”

Section: Methodsmentioning

confidence: 99%

“…Given the sparse nature of the MKL implemented in PRoNTo, only a subset of the regions would be selected in the regression analysis. (5) Both leave‐one‐subject‐out cross‐validation (LOSOCV) and 10‐fold cross‐validation procedures were employed to train and examine the performance of the model [Cui et al, ; Fernandes et al, ]. (6) The performance was assessed by measuring the consistency between the predicted and actual values, using Pearson's correlation coefficient ( r ).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Neural substrates of context‐ and person‐dependent altruistic punishment

Wang

et al. 2017

Human Brain Mapping

View full text Add to dashboard Cite

Human altruistic behaviors are heterogeneous across both contexts and people, whereas the neural signatures underlying the heterogeneity remain to be elucidated. To address this issue, we examined the neural signatures underlying the context- and person-dependent altruistic punishment, conjoining event-related fMRI with both task-based and resting-state functional connectivity (RSFC). Acting as an impartial third party, participants decided how to punish norm violators either alone or in the presence of putative others. We found that the presence of others decreased altruistic punishment due to diffusion of responsibility. Those behavioral effects paralleled altered neural responses in the dorsal anterior cingulate cortex (dACC) and putamen. Further, we identified modulation of responsibility diffusion on task-based functional connectivity of dACC with the brain regions implicated in reward processing (i.e., posterior cingulate cortex and amygdala/orbital frontal cortex). Finally, the RSFC results revealed that (i) increased intrinsic connectivity strengths of the putamen with temporoparietal junction and dorsolateral PFC were associated with attenuated responsibility diffusion in altruistic punishment and (ii) increased putamen-dorsomedial PFC connectivity strengths were associated with reduced responsibility diffusion in self-reported responsibility. Taken together, our findings elucidate the context- and person-dependent altruistic behaviors as well as associated neural substrates and thus provide a potential neurocognitive mechanism of heterogeneous human altruistic behaviors. Hum Brain Mapp 38:5535-5550, 2017. © 2017 Wiley Periodicals, Inc.

show abstract

“…MKL allows to account for brain anatomy (determined by a brain atlas, see section 2.7) and different modalities (such as anatomical/functional data or in the current approach: conditions) during the model estimation by considering each brain region and modality as separate kernels. This approach allows determining the contribution of each brain region (region weights) and condition (condition weights) to the final decision function of the model in a hierarchical manner by simultaneously learning and combining the different linear kernels that are based on support vector machines (SVM) (Rakotomamonjy et al, 2008;Fernandes et al, 2017;Schrouff et al, 2018). Compared to conventional MVPA methods based on whole-brain voxel weight maps, this procedure provides a straight-forward approach to draw inferences on the region level without the need for multiple comparison correction (Schrouff et al, 2018).…”

Section: Multivariate Pattern Analysis (Mvpa)mentioning

confidence: 99%

Pain-related fear – Dissociable neural sources of different fear constructs

Meier

Humphreys

Vrana

et al. 2018

Preprint

View full text Add to dashboard Cite

The ability to infer emotional states through self-reports is often limited. Their measurement becomes even more challenging when considering emotional phenomena such as pain-related fear where different associated fear constructs have been proposed. Demonstrating significant predictive value regarding disability in patients with persistent musculoskeletal pain, pain-related fear is often assessed by questionnaires focusing on either fear of movement/(re)injury/kinesiophobia, fear avoidance beliefs or pain anxiety. Furthermore, the relationship of general anxiety measures such as trait anxiety to pain-related fear remains ambiguous. Advances in neuroimaging might help to support potential commonalities or differences across psychological constructs using appropriate machine learning techniques with the ability to reveal predictive relationships between neural information and questionnaire scores.Here, we applied a pattern regression approach using functional magnetic resonance imaging data of 20 non-specific chronic low back pain (LBP) patients. More specifically, we applied a novel approach using Multiple Kernel Learning that allows investigating the contribution of experimental conditions and regional neural information to a prediction model. We hypothesized to find evidence for or against a common fear construct by computing and comparing the prediction model of each questionnaire according to the contribution of fear-related neural information and conditions. The current results underpin the diversity of fear constructs among self-report measures of pain-related fear by demonstrating evidence of non-overlapping and differentially contributing neural sources within fear processing regions. Thus, the current approach might ultimately help to further understand and dissect the fear constructs captured by the various pain-related fear questionnaires. Significance. CC-BY-NC-ND 4.0 International license peer-reviewed) is the author/funder. It is made available under aThe copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/251751 doi: bioRxiv preprint first posted online Jan. 25, 2018; Pain-related fear, often assessed through self-reports such as questionnaires, has shown prognostic value and clinical utility for a variety of musculoskeletal pain disorders. However, it remains difficult to determine a common underlying fear construct of pain-related fear due to several proposed constructs among questionnaires. The current study describes a novel neuroscientific approach using machine learning of neural patterns within the fear network of chronic LBP patients that might have the potential to identify neural commonalities or differences among the various fear constructs. Ultimately, this approach might afford a deeper understanding of the suggested fear constructs of pain-related fear and might be also applied to other domains where ambiguity exists between emotional phenomena and underlying psychological constructs.

show abstract

Decoding negative affect personality trait from patterns of brain activation to threat stimuli

Cited by 30 publications

References 89 publications

Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important

Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important

Neural substrates of context‐ and person‐dependent altruistic punishment

Pain-related fear – Dissociable neural sources of different fear constructs

Contact Info

Product

Resources

About