Discrimination of Schizophrenia Auditory Hallucinators by Machine Learning of Resting-State Functional MRI

Auditory hallucinations (AH) are a symptom that is most often associated with schizophrenia, but patients with other neuropsychiatric conditions, and even a small percentage of healthy individuals, may also experience AH. Elucidating the neural mechanisms underlying AH in schizophrenia may offer insight into the pathophysiology associated with AH more broadly across multiple neuropsychiatric disease conditions. In this paper, we address the problem of classifying schizophrenia patients with and without a history of AH, and healthy control (HC) subjects. To this end, we performed feature extraction from resting state functional magnetic resonance imaging (rsfMRI) data and applied machine learning classifiers, testing two kinds of neuroimaging features: (a) functional connectivity (FC) measures computed by lattice auto-associative memories (LAAM), and (b) local activity (LA) measures, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF). We show that it is possible to perform classification within each pair of subject groups with high accuracy. Discrimination between patients with and without lifetime AH was highest, while discrimination between schizophrenia patients and HC participants was worst, suggesting that classification according to the symptom dimension of AH may be more valid than discrimination on the basis of traditional diagnostic categories. FC measures seeded in right Heschl's gyrus (RHG) consistently showed stronger discriminative power than those seeded in left Heschl's gyrus (LHG), a finding that appears to support AH models focusing on right hemisphere abnormalities. The cortical brain localizations derived from the features with strong classification performance are consistent with proposed AH models, and include left inferior frontal gyrus (IFG), parahippocampal gyri, the cingulate cortex, as well as several temporal and prefrontal cortical brain regions. Overall, the observed findings suggest that computational intelligence approaches can provide robust tools for uncovering subtleties in complex neuroimaging data, and have the potential to advance the search for more neuroscience-based criteria for classifying mental illness in psychiatry research.

[1]  R. Kahn,et al.  Aberrations in the arcuate fasciculus are associated with auditory verbal hallucinations in psychotic and in non‐psychotic individuals , 2011, Human brain mapping.

[2]  Rutger Goekoop,et al.  Deactivation of the parahippocampal gyrus preceding auditory hallucinations in schizophrenia. , 2010, The American journal of psychiatry.

[3]  Angelo Gemignani,et al.  Singular Spectrum Analysis and Adaptive Filtering Enhance the Functional connectivity Analysis of resting State fMRI Data , 2014, Int. J. Neural Syst..

[4]  Peter Sussner,et al.  Gray-scale morphological associative memories , 2006, IEEE Transactions on Neural Networks.

[5]  A. Aleman,et al.  Abnormal connectivity between attentional, language and auditory networks in schizophrenia , 2012, Schizophrenia Research.

[6]  G. Egan,et al.  Reduced connectivity of the auditory cortex in patients with auditory hallucinations: a resting state functional magnetic resonance imaging study , 2009, Psychological Medicine.

[7]  Hojjat Adeli,et al.  Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems , 1994 .

[8]  Weidong Zhou,et al.  Epileptic EEG Classification Based on Kernel Sparse Representation , 2014, Int. J. Neural Syst..

[9]  D. Prvulovic,et al.  Reduced functional connectivity and asymmetry of the planum temporale in patients with schizophrenia and first-degree relatives , 2013, Schizophrenia Research.

[10]  Angelo Gemignani,et al.  Adaptive Filtering and Random Variables coefficient for Analyzing Functional Magnetic Resonance Imaging Data , 2013, Int. J. Neural Syst..

[11]  Bogdan Raducanu,et al.  Morphological Scale Spaces and Associative Morphological Memories: Results on Robustness and Practical Applications , 2004, Journal of Mathematical Imaging and Vision.

[12]  Bartosz Krawczyk,et al.  Improved Adaptive Splitting and Selection: the Hybrid Training Method of a Classifier Based on a Feature Space Partitioning , 2014, Int. J. Neural Syst..

[13]  W. Singer,et al.  Activation of Heschl’s Gyrus during Auditory Hallucinations , 1999, Neuron.

[14]  Philip K. McGuire,et al.  The hallucinating brain: A review of structural and functional neuroimaging studies of hallucinations , 2008, Neuroscience & Biobehavioral Reviews.

[15]  Yong He,et al.  Altered baseline brain activity in children with ADHD revealed by resting-state functional MRI. , 2007, Brain & development.

[16]  A. Tien,et al.  Distributions of hallucinations in the population. , 1991, Social psychiatry and psychiatric epidemiology.

[17]  Nazmul Siddique,et al.  Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing , 2013 .

[18]  Manuel Graña,et al.  Hybrid multivariate morphology using lattice auto-associative memories for resting-state fMRI network discovery , 2012, 2012 12th International Conference on Hybrid Intelligent Systems (HIS).

[19]  C M McKay,et al.  Central auditory processing in patients with auditory hallucinations. , 2000, The American journal of psychiatry.

[20]  Manuel Graña,et al.  Lattice computing in hybrid intelligent systems , 2012, 2012 12th International Conference on Hybrid Intelligent Systems (HIS).

[21]  Peter Sussner,et al.  Morphological bidirectional associative memories , 1999, Neural Networks.

[22]  Arkady Borisov,et al.  Ranking-Based Kernels in Applied Biomedical Diagnostics Using a Support Vector Machine , 2011, Int. J. Neural Syst..

[23]  J. Cutting.  The right cerebral hemisphere and psychiatric disorders , 1990 .

[24]  Jonathan D. Power,et al.  Prediction of Individual Brain Maturity Using fMRI , 2010, Science.

[25]  Marisa O. Hollinshead,et al.  The organization of the human cerebral cortex estimated by intrinsic functional connectivity. , 2011, Journal of neurophysiology.

[26]  P. McGuire,et al.  Neuroanatomy of auditory verbal hallucinations in schizophrenia: A quantitative meta-analysis of voxel-based morphometry studies , 2013, Cortex.

[27]  Ezequiel López-Rubio,et al.  Bregman Divergences for Growing Hierarchical Self-Organizing Networks , 2014, Int. J. Neural Syst..

[28]  Peter F. Liddle,et al.  Structural correlates of auditory hallucinations in schizophrenia: A meta-analysis , 2012, Schizophrenia Research.

[29]  Tianzi Jiang,et al.  Regional homogeneity, functional connectivity and imaging markers of Alzheimer's disease: A review of resting-state fMRI studies , 2008, Neuropsychologia.

[30]  K. Hugdahl,et al.  Auditory Hallucinations and Reduced Language Lateralization in Schizophrenia: A Meta-analysis of Dichotic Listening Studies , 2013, Journal of the International Neuropsychological Society.

[31]  I Feinberg,et al.  Efference copy and corollary discharge: implications for thinking and its disorders. , 1978, Schizophrenia bulletin.

[32]  Georg Northoff,et al.  The brain and its resting state activity—Experimental and methodological implications , 2010, Progress in Neurobiology.

[33]  Judith M Ford,et al.  Electrophysiological evidence of corollary discharge dysfunction in schizophrenia during talking and thinking. , 2004, Journal of psychiatric research.

[34]  Feng Chu,et al.  Applications of support vector machines to cancer classification with microarray data , 2005, Int. J. Neural Syst..

[35]  Y. Zang,et al.  Altered baseline brain activity in children with ADHD revealed by resting-state functional MRI , 2007, Brain and Development.

[36]  J. Gabrieli,et al.  Hyperactivity and hyperconnectivity of the default network in schizophrenia and in first-degree relatives of persons with schizophrenia , 2009, Proceedings of the National Academy of Sciences.

[37]  Justin T. Baker,et al.  Functional connectivity of left Heschl's gyrus in vulnerability to auditory hallucinations in schizophrenia , 2013, Schizophrenia Research.

[38]  Erik D. Goodman,et al.  Integrating a statistical background- foreground extraction algorithm and SVM classifier for pedestrian detection and tracking , 2013, Integr. Comput. Aided Eng..

[39]  Haruhiko Nishimura,et al.  Modeling fluctuations in Default-Mode Brain Network Using a Spiking Neural Network , 2012, Int. J. Neural Syst..

[40]  Yingli Lu,et al.  Regional homogeneity approach to fMRI data analysis , 2004, NeuroImage.

[41]  Liang Tian,et al.  A novel approach for short-term load forecasting using support vector machines , 2004, Int. J. Neural Syst..

[42]  R. Bentall,et al.  Reality testing and auditory hallucinations: a signal detection analysis. , 1985, The British journal of clinical psychology.

[43]  Paul D. Gader,et al.  Fixed Points of Lattice Transforms and Lattice Associative Memories , 2006 .

[44]  T. Insel,et al.  Wesleyan University From the SelectedWorks of Charles A . Sanislow , Ph . D . 2010 Research Domain Criteria ( RDoC ) : Toward a New Classification Framework for Research on Mental Disorders , 2018 .

[45]  Thomas Martinetz,et al.  Model-Free Functional MRI Analysis Using Topographic Independent Component Analysis , 2004, ESANN.

[46]  A. Tien.  Distribution of hallucinations in the population , 1991, Social Psychiatry and Psychiatric Epidemiology.

[47]  Michelle Hampson,et al.  Elevated Functional Connectivity Along a Corticostriatal Loop and the Mechanism of Auditory/Verbal Hallucinations in Patients with Schizophrenia , 2011, Biological Psychiatry.

[48]  Tom M. Mitchell,et al.  Machine learning classifiers and fMRI: A tutorial overview , 2009, NeuroImage.

[49]  Manuel Graña,et al.  Lattice independent component analysis for functional magnetic resonance imaging , 2011, Inf. Sci..

[50]  D. Rangaprakash,et al.  Phase Synchronization in Brain Networks derived from Correlation between Probabilities of Recurrences in Functional MRI Data , 2013, Int. J. Neural Syst..

[51]  Irwin Feinberg,et al.  Corollary discharge, hallucinations, and dreaming. , 2011, Schizophrenia bulletin.

[52]  Ryali Srikanth,et al.  Wavelet-based Estimation of Hemodynamic Response Function from Fmri Data , 2006, Int. J. Neural Syst..

[53]  Klaus-Robert Müller,et al.  Introduction to machine learning for brain imaging , 2011, NeuroImage.

[54]  Ze D Jiang,et al.  Distortion product otoacoustic emissions during the first year in term infants: A longitudinal study , 2007, Brain and Development.

[55]  Charles Fernyhough,et al.  Auditory hallucinations in schizophrenia and nonschizophrenia populations: a review and integrated model of cognitive mechanisms. , 2012, Schizophrenia bulletin.

[56]  Simon B. Eickhoff,et al.  Resting State Functional Connectivity in Patients with Chronic Hallucinations , 2012, PloS one.

[57]  Todd S. Woodward,et al.  Aberrant connectivity during self–other source monitoring in schizophrenia , 2011, Schizophrenia Research.

[58]  Fabio Sambataro,et al.  Source-based morphometry of gray matter volume in patients with schizophrenia who have persistent auditory verbal hallucinations , 2014, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[59]  Manuel Graña,et al.  Two lattice computing approaches for the unsupervised segmentation of hyperspectral images , 2009, Neurocomputing.

[60]  S. Eickhoff,et al.  Aberrant connectivity of areas for decoding degraded speech in patients with auditory verbal hallucinations , 2013, Brain Structure and Function.

[61]  Jussi Tohka,et al.  Automated diagnosis of brain tumours astrocytomas using probabilistic neural network clustering and support vector machines , 2005, Int. J. Neural Syst..

[62]  Peter G. Morris,et al.  The functional anatomy of auditory hallucinations in schizophrenia , 2000, Psychiatry Research: Neuroimaging.

[63]  Georg Northoff,et al.  How can the brain's resting state activity generate hallucinations? A ‘resting state hypothesis’ of auditory verbal hallucinations , 2011, Schizophrenia Research.

[64]  Gerd Wagner,et al.  ALTERED DEFAULT-MODE NETWORK ACTIVITY IN SCHIZOPHRENIA: A RESTING STATE FMRI STUDY , 2010, Schizophrenia Research.

[65]  Athanasios Kehagias,et al.  Fuzzy Inference System (FIS) Extensions Based on the Lattice Theory , 2014, IEEE Transactions on Fuzzy Systems.

[66]  Gaojun Teng,et al.  Regional homogeneity in depression and its relationship with separate depressive symptom clusters: a resting-state fMRI study. , 2009, Journal of affective disorders.

[67]  Ann K. Shinn,et al.  Default mode network abnormalities in bipolar disorder and schizophrenia , 2010, Psychiatry Research: Neuroimaging.

[68]  Karl J. Friston.  Functional and effective connectivity in neuroimaging: A synthesis , 1994 .

[69]  Larry D. Olson,et al.  Localization of epileptic foci using Multimodality neuroimaging , 2013, Int. J. Neural Syst..

[70]  Emilio Corchado,et al.  The S2-Ensemble Fusion Algorithm , 2011, Int. J. Neural Syst..

[71]  N. Tarrier,et al.  Scales to measure dimensions of hallucinations and delusions: the psychotic symptom rating scales (PSYRATS) , 1999, Psychological Medicine.

[72]  G. Glover,et al.  Resting-State Functional Connectivity in Major Depression: Abnormally Increased Contributions from Subgenual Cingulate Cortex and Thalamus , 2007, Biological Psychiatry.

[73]  Richard S. J. Frackowiak,et al.  Human Primary Auditory Cortex Follows the Shape of Heschl's Gyrus , 2011, The Journal of Neuroscience.

[74]  P. Woodruff,et al.  Auditory hallucinations: expectation-perception model. , 2012, Medical hypotheses.

[75]  K. Vogeley,et al.  Resting-state functional network correlates of psychotic symptoms in schizophrenia , 2010, Schizophrenia Research.

[76]  André Aleman,et al.  Auditory Hallucinations in Schizophrenia Are Associated with Reduced Functional Connectivity of the Temporo-Parietal Area , 2010, Biological Psychiatry.

[77]  Sue Gordon,et al.  Avoiding False Negatives: Are Some Auditory Hallucinations an Evolved Design Flaw? , 2009, Behavioural and Cognitive Psychotherapy.

[78]  S. Kühn,et al.  Quantitative meta-analysis on state and trait aspects of auditory verbal hallucinations in schizophrenia. , 2012, Schizophrenia bulletin.

[79]  Peter Sussner,et al.  Morphological associative memories , 1998, IEEE Trans. Neural Networks.

[80]  Bharat B. Biswal,et al.  The oscillating brain: Complex and reliable , 2010, NeuroImage.

[81]  Manuel Graña,et al.  Discrimination of Resting-State fMRI for Schizophrenia Patients with Lattice Computing Based Features , 2013, HAIS.

[82]  Paul Allen,et al.  Misattribution of speech and impaired connectivity in patients with auditory verbal hallucinations , 2007, Human brain mapping.

[83]  T. Ditman,et al.  A Source‐Monitoring Account of Auditory Verbal Hallucinations in Patients with Schizophrenia , 2005, Harvard review of psychiatry.

[84]  Peter B. Jones,et al.  Spatial and temporal mapping of neural activity associated with auditory hallucinations , 1999, The Lancet.

[85]  R. Bentall,et al.  The metacognitive beliefs account of hallucinatory experiences: a literature review and meta-analysis. , 2011, Clinical psychology review.

[86]  Patricia T Michie,et al.  Auditory hallucinations in schizophrenia: Intrusive thoughts and forgotten memories , 2006, Cognitive neuropsychiatry.

[87]  B. Biswal,et al.  Functional connectivity in the motor cortex of resting human brain using echo‐planar mri , 1995, Magnetic resonance in medicine.

[88]  V. van de Ven,et al.  Reduced Laterality as a Trait Marker ofSchizophrenia—Evidence from Structural and Functional Neuroimaging , 2010, The Journal of Neuroscience.

[89]  George A. Papakostas,et al.  Lattice Computing Extension of the FAM Neural Classifier for Human Facial Expression Recognition , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[90]  K. Diederen,et al.  Dissecting Auditory Verbal Hallucinations into Two Components: Audibility (Gedankenlautwerden) and Alienation (Thought Insertion) , 2010, Psychopathology.

[91]  Kenneth Hugdahl,et al.  "Hearing voices": auditory hallucinations as failure of top-down control of bottom-up perceptual processes. , 2009, Scandinavian journal of psychology.

[92]  T. Insel.  The NIMH Research Domain Criteria (RDoC) Project: precision medicine for psychiatry. , 2014, The American journal of psychiatry.

[93]  K. Diederen,et al.  Healthy individuals with auditory verbal hallucinations; who are they? Psychiatric assessments of a selected sample of 103 subjects. , 2010, Schizophrenia bulletin.

[94]  Huaien Luo,et al.  Spatio-temporal Modeling and Analysis of Fmri Data Using Narx Neural Network , 2006, Int. J. Neural Syst..

[95]  Charles Fernyhough,et al.  Neural correlates of inner speech and auditory verbal hallucinations: a critical review and theoretical integration. , 2007, Clinical psychology review.

[96]  A. Anderson,et al.  Time course of regional brain activation associated with onset of auditory/verbal hallucinations , 2008, British Journal of Psychiatry.

[97]  YANG YANG,et al.  Protein Subcellular Multi-Localization Prediction Using a Min-Max Modular Support Vector Machine , 2010, Int. J. Neural Syst..

[98]  Chunshui Yu,et al.  Altered resting-state functional connectivity and anatomical connectivity of hippocampus in schizophrenia , 2008, Schizophrenia Research.

[99]  Kaspar Anton Schindler,et al.  Common mechanisms of auditory hallucinations–perfusion studies in epilepsy , 2013, Psychiatry Research: Neuroimaging.

[100]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[101]  Yuan Zhou,et al.  Functional dysconnectivity of the dorsolateral prefrontal cortex in first-episode schizophrenia using resting-state fMRI , 2007, Neuroscience Letters.

[102]  Renaud Jardri,et al.  Cortical activations during auditory verbal hallucinations in schizophrenia: a coordinate-based meta-analysis. , 2011, The American journal of psychiatry.

[103]  J. Blom,et al.  Auditory hallucinations. , 2015, Handbook of clinical neurology.

[104]  Chaozhe Zhu,et al.  An improved approach to detection of amplitude of low-frequency fluctuation (ALFF) for resting-state fMRI: Fractional ALFF , 2008, Journal of Neuroscience Methods.

[105]  C. Schönfeldt-Lecuona,et al.  Dysconnectivity of multiple resting-state networks in patients with schizophrenia who have persistent auditory verbal hallucinations. , 2011, Journal of psychiatry & neuroscience : JPN.

[106]  Marcia K. Johnson,et al.  Source monitoring. , 1993, Psychological bulletin.