A novel approach to probabilistic biomarker-based classification using functional near-infrared spectroscopy

Pattern recognition approaches to the analysis of neuroimaging data have brought new applications such as the classification of patients and healthy controls within reach. In our view, the reliance on expensive neuroimag
Pattern recognition approaches to the analysis of neuroimaging data have brought new applications such as the classification of patients and healthy controls within reach. In our view, the reliance on expensive neuroimaging techniques which are not well tolerated by many patient groups and the inability of most current biomarker algorithms to accommodate information about prior class frequencies (such as a disorder's prevalence in the general population) are key factors limiting practical application. To overcome both limitations, we propose a probabilistic pattern recognition approach based on cheap and easy-to-use multi-channel near-infrared spectroscopy (fNIRS) measurements. We show the validity of our method by applying it to data from healthy controls (n = 14) enabling differentiation between the conditions of a visual checkerboard task. Second, we show that high-accuracy single subject classification of patients with schizophrenia (n = 40) and healthy controls (n = 40) is possible based on temporal patterns of fNIRS data measured during a working memory task. For classification, we integrate spatial and temporal information at each channel to estimate overall classification accuracy. This yields an overall accuracy of 76% which is comparable to the highest ever achieved in biomarker-based classification of patients with schizophrenia. In summary, the proposed algorithm in combination with fNIRS measurements enables the analysis of sub-second, multivariate temporal patterns of BOLD responses and high-accuracy predictions based on low-cost, easy-to-use fNIRS patterns. In addition, our approach can easily compensate for variable class priors, which is highly advantageous in making predictions in a wide range of clinical neuroimaging applications. Hum Brain Mapp, 2013. © 2012 Wiley Periodicals, Inc.
show moreshow less

Download full text files

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

    Share in Twitter Search Google Scholar
Metadaten
Author:Tim Hahn, Andre F. Marquand, Michael M. Plichta, Ann-Christine Ehlis, Martin W. Schecklmann, Thomas Dresler, Tomasz A. Jarczok, Elisa Eirich, Christine Leonhard, Andreas Reif, Klaus-Peter Lesch, Michael J. Brammer, Janaina Mourao-Miranda, Andreas Jochen Fallgatter
URN:urn:nbn:de:hebis:30:3-317022
DOI:http://dx.doi.org/10.1002/hbm.21497
ISSN:1097-0193
ISSN:1065-9471
Pubmed Id:http://www.ncbi.nlm.nih.gov/pubmed?term=22965654
Parent Title (English):Human brain mapping
Publisher:Wiley-Liss
Place of publication:New York, NY
Document Type:Article
Language:English
Date of Publication (online):2012/01/16
Date of first Publication:2012/01/16
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2013/10/01
Tag:disease prevalence; schizophrenia; single subject classification; temporal classification
Volume:34
Pagenumber:13
First Page:1102
Last Page:1114
Note:
Copyright © 2012 Wiley Periodicals, Inc. Re-use of this article is permitted in accordance with the Creative Commons Deed, Attribution 2.5, which does not permit commercial exploitation.
HeBIS PPN:353298611
Institutes:Psychologie
Dewey Decimal Classification:150 Psychologie
Sammlungen:Universitätspublikationen
Licence (German):License LogoCreative Commons - Namensnennung-Nicht kommerziell 2.0

$Rev: 11761 $