Multivariate classification of social anxiety disorder using whole brain functional connectivity
- 3.5k Downloads
Recent research has shown that social anxiety disorder (SAD) is accompanied by abnormalities in brain functional connections. However, these findings are based on group comparisons, and, therefore, little is known about whether functional connections could be used in the diagnosis of an individual patient with SAD. Here, we explored the potential of the functional connectivity to be used for SAD diagnosis. Twenty patients with SAD and 20 healthy controls were scanned using resting-state functional magnetic resonance imaging. The whole brain was divided into 116 regions based on automated anatomical labeling atlas. The functional connectivity between each pair of regions was computed using Pearson’s correlation coefficient and used as classification feature. Multivariate pattern analysis was then used to classify patients from healthy controls. The pattern classifier was designed using linear support vector machine. Experimental results showed a correct classification rate of 82.5 % (p < 0.001) with sensitivity of 85.0 % and specificity of 80.0 %, using a leave-one-out cross-validation method. It was found that the consensus connections used to distinguish SAD were largely located within or across the default mode network, visual network, sensory-motor network, affective network, and cerebellar regions. Specifically, the right orbitofrontal region exhibited the highest weight in classification. The current study demonstrated that functional connectivity had good diagnostic potential for SAD, thus providing evidence for the possible use of whole brain functional connectivity as a complementary tool in clinical diagnosis. In addition, this study confirmed previous work and described novel pathophysiological mechanisms of SAD.
KeywordsSocial anxiety disorder/social phobia Multivariate pattern analysis Support vector machine Functional connectivity Resting-state fMRI Consensus features
The authors thank the two anonymous reviewers for constructive suggestions and Kim-Han Thung for the proof-reading and valuable comments. H. Chen was supported by the 973 project (No. 2012CB517901), the Natural Science Foundation of China (Nos. 61125304 and 61035006), and the Specialized Research Fund for the Doctoral Program of Higher Education of China (No. 20120185110028). F. Liu was supported by China Scholarship Council (No. 2011607033) and the Scholarship Award for Excellent Doctoral Student granted by Ministry of Education (No. A03003023901010). L. Zeng was supported by the Natural Science Foundation of China (No. 81171406). W. Guo was supported by the Natural Science Foundation of China (Nos. 81260210 and 30900483).
Conflict of interest
All authors declare that they have no conflicts of interest.
- Anderson JS, Nielsen JA, Froehlich AL, DuBray MB, Druzgal TJ, Cariello AN, Cooperrider JR, Zielinski BA, Ravichandran C, Fletcher PT, Alexander AL, Bigler ED, Lange N, Lainhart JE (2011) Functional connectivity magnetic resonance imaging classification of autism. Brain 134:3742–3754PubMedCrossRefGoogle Scholar
- APA. Diagnostic and statistical manual of mental disorders: DSM-IV. American Psychiatric Publishing, Inc., 1994Google Scholar
- Borg C, Bedoin N, Peyron R, Bogey S, Laurent B, Thomas-Antérion C (2012) Impaired emotional processing in a patient with a left posterior insula-SII lesion. Neurocase. doi: 10.1080/13554794.2012.713491
- Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2:27Google Scholar
- Chen YW, Lin CJ (2006) Combining SVMs with various feature selection strategies. Feature Extr 207:315–324Google Scholar
- Friston KJ (2004) Functional integration in the brain. In: Human brain function, 2nd edn. Academic Press, San Diego pp 971–997Google Scholar
- Guo WB, Liu F, Xue ZM, Yu Y, Ma CQ, Tan CL, Sun XL, Chen JD, Liu ZN, Xiao CQ, Chen HF, Zhao JP (2011) Abnormal neural activities in first-episode, treatment-naive, short-illness-duration, and treatment-response patients with major depressive disorder: a resting-state fMRI study. J Affect Disord 135:326–331PubMedCrossRefGoogle Scholar
- Haker A, Aderka IM, Marom S, Hermesh H, Gilboa-Schechtman E (2013) Impression formation and revision in social anxiety disorder. J Anxiety DisordGoogle Scholar
- Hattingh CJ, Ipser J, Tromp SA, Syal S, Lochner C, Brooks SJ, Stein DJ (2012) Functional magnetic resonance imaging during emotion recognition in social anxiety disorder: an activation likelihood meta-analysis. Frontiers Hum Neurosci 6:347Google Scholar
- Jefferys D (1997) Social phobia. The most common anxiety disorder. Aust Fam Physician 26(1061):1064Google Scholar
- Liu F, Guo W, Yu D, Gao Q, Gao K, Xue Z, Du H, Zhang J, Tan C, Liu Z, Zhao J, Chen H (2012a) Classification of different therapeutic responses of major depressive disorder with multivariate pattern analysis method based on structural MR scans. PLoS ONE 7:e40968PubMedCentralPubMedCrossRefGoogle Scholar
- Liu F, Hu M, Wang S, Guo W, Zhao J, Li J, Xun G, Long Z, Zhang J, Wang Y, Zeng L, Gao Q, Wooderson SC, Chen J, Chen H (2012b) Abnormal regional spontaneous neural activity in first-episode, treatment-naive patients with late-life depression: a resting-state fMRI study. Prog Neuropsychopharmacol Biol Psychiatry 39:326–331PubMedCrossRefGoogle Scholar
- Mitchell TM (1997) Machine learning, vol 45. McGraw Hill, Burr RidgeGoogle Scholar
- Schölkopf B, Smola AJ (2001) Learning with kernels: Support vector machines, regularization, optimization, and beyond. MIT press, CambridgeGoogle Scholar
- Vapnik VN (1995) The nature of statistical learning theory. Springer, New York IncGoogle Scholar
- Wee CY, Yap PT, Zhang D, Wang L, Shen D (2013) Group-constrained sparse fMRI connectivity modeling for mild cognitive impairment identification. Brain Struct Funct. doi: 10.1007/s00429-013-0524-8
- Zhou B, Liu Y, Zhang Z, An N, Yao H, Wang P, Wang L, Zhang X, Jiang T (2013) Impaired functional connectivity of the thalamus in Alzheimer’s disease and mild cognitive impairment: a resting-state fMRI study. Curr Alzheimer Res 10:754–766Google Scholar