Improving the analysis of near-infrared spectroscopy data with multivariate classification of hemodynamic patterns: a theoretical formulation and validation

dc.contributor.authorGemignani, Jessica
dc.contributor.authorMiddell, Eike
dc.contributor.authorBarbour, Randall L.
dc.contributor.authorGraber, Harry L.
dc.contributor.authorBlankertz, Benjamin
dc.date.accessioned2019-10-04T08:16:09Z
dc.date.available2019-10-04T08:16:09Z
dc.date.issued2018-05-09
dc.description.abstractObjective. The statistical analysis of functional near infrared spectroscopy (fNIRS) data based on the general linear model (GLM) is often made difficult by serial correlations, high inter-subject variability of the hemodynamic response, and the presence of motion artifacts. In this work we propose to extract information on the pattern of hemodynamic activations without using any a priori model for the data, by classifying the channels as 'active' or 'not active' with a multivariate classifier based on linear discriminant analysis (LDA). Approach. This work is developed in two steps. First we compared the performance of the two analyses, using a synthetic approach in which simulated hemodynamic activations were combined with either simulated or real resting-state fNIRS data. This procedure allowed for exact quantification of the classification accuracies of GLM and LDA. In the case of real resting-state data, the correlations between classification accuracy and demographic characteristics were investigated by means of a Linear Mixed Model. In the second step, to further characterize the reliability of the newly proposed analysis method, we conducted an experiment in which participants had to perform a simple motor task and data were analyzed with the LDA-based classifier as well as with the standard GLM analysis. Main results. The results of the simulation study show that the LDA-based method achieves higher classification accuracies than the GLM analysis, and that the LDA results are more uniform across different subjects and, in contrast to the accuracies achieved by the GLM analysis, have no significant correlations with any of the demographic characteristics. Findings from the real-data experiment are consistent with the results of the real-plus-simulation study, in that the GLM-analysis results show greater inter-subject variability than do the corresponding LDA results. Significance. The results obtained suggest that the outcome of GLM analysis is highly vulnerable to violations of theoretical assumptions, and that therefore a data-driven approach such as that provided by the proposed LDA-based method is to be favored.en
dc.description.sponsorshipEC/H2020/641858/EU/Understanding and predicting developmental language abilities and disorders in multilingual Europe/PREDICTABLEen
dc.identifier.eissn1741-2552
dc.identifier.issn1741-2560
dc.identifier.pmid29616976
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/10061
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-9052
dc.language.isoenen
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/3.0/en
dc.subject.ddc006 Spezielle Computerverfahrende
dc.subject.ddc612 Humanphysiologiede
dc.subject.otherfunctional Near Infrared Spectroscopyen
dc.subject.otherGeneral Linear Modelen
dc.subject.otherLinear Discriminant Analysisen
dc.subject.otherfNIRSen
dc.subject.otherGLMen
dc.subject.otherLDAen
dc.subject.otherhemodynamicen
dc.subject.otherHRFen
dc.titleImproving the analysis of near-infrared spectroscopy data with multivariate classification of hemodynamic patterns: a theoretical formulation and validationen
dc.typeArticleen
dc.type.versionacceptedVersionen
dcterms.bibliographicCitation.articlenumber045001en
dcterms.bibliographicCitation.doi10.1088/1741-2552/aabb7cen
dcterms.bibliographicCitation.issue4en
dcterms.bibliographicCitation.journaltitleJournal of Neural Engineeringen
dcterms.bibliographicCitation.originalpublishernameInstitute of Physics Publishing (IOP)en
dcterms.bibliographicCitation.originalpublisherplaceBristolen
dcterms.bibliographicCitation.volume15en
tub.accessrights.dnbfreeen
tub.affiliationFak. 4 Elektrotechnik und Informatik::Inst. Softwaretechnik und Theoretische Informatik::FG Neurotechnologiede
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Neurotechnologiede
tub.affiliation.instituteInst. Softwaretechnik und Theoretische Informatikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen

Files

Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
gemignani_etal_2018.pdf
Size:
1.97 MB
Format:
Adobe Portable Document Format
Description:
Final draft
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.9 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections