A Hybrid Machine Learning Method for Fusing fMRI and Genetic Data: Combining both Improves Classification of Schizophrenia
Open Access
- 1 January 2010
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Human Neuroscience
- Vol. 4, 192
- https://doi.org/10.3389/fnhum.2010.00192
Abstract
We demonstrate a hybrid machine learning method to classify schizophrenia patients and healthy controls, using functional magnetic resonance imaging (fMRI) and single nucleotide polymorphism (SNP) data. The method consists of four stages: (1) SNPs with the most discriminating information between the healthy controls and schizophrenia patients are selected to construct a support vector machine ensemble (SNP-SVME). (2) Voxels in the fMRI map contributing to classification are selected to build another SVME (Voxel-SVME). (3) Components of fMRI activation obtained with independent component analysis (ICA) are used to construct a single SVM classifier (ICA-SVMC). (4) The above three models are combined into a single module using a majority voting approach to make a final decision (Combined SNP-fMRI). The method was evaluated by a fully-validated leave-one-out method using 40 subjects (20 patients and 20 controls). The classification accuracy was: 0.74 for SNP-SVME, 0.82 for Voxel-SVME, 0.83 for ICA-SVMC, and 0.87 for Combined SNP-fMRI. Experimental results show that better classification accuracy was achieved by combining genetic and fMRI data than using either alone, indicating that genetic and brain function representing different, but partially complementary aspects, of schizophrenia etiopathology. This study suggests an effective way to reassess biological classification of individuals with schizophrenia, which is also potentially useful for identifying diagnostically important markers for the disorder.Keywords
This publication has 53 references indexed in Scilit:
- A method for accurate group difference detection by constraining the mixing coefficients in an ICA frameworkHuman Brain Mapping, 2009
- Genetic associations with schizophrenia: Meta-analyses of 12 candidate genesSchizophrenia Research, 2008
- Classification of functional brain images with a spatio-temporal dissimilarity mapNeuroImage, 2006
- Decoding mental states from brain activity in humansNature Reviews Neuroscience, 2006
- A complete genetic association scan of the 22q11 deletion region and functional evidence reveal an association between DGCR2 and schizophreniaHuman Genetics, 2006
- Association of DISC1/TRAX Haplotypes With Schizophrenia, Reduced Prefrontal Gray Matter, and Impaired Short- and Long-term MemoryArchives of General Psychiatry, 2005
- Highly Parallel SNP GenotypingCold Spring Harbor Symposia on Quantitative Biology, 2003
- Reproducibility of the hemodynamic response to auditory oddball stimuli: A six‐week test–retest studyHuman Brain Mapping, 2002
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Auditory hallucinations and smaller superior temporal gyral volume in schizophreniaAmerican Journal of Psychiatry, 1990