Discrimination of schizophrenia auditory hallucinators by machine learning of resting-state functional MRI

Abstract

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.

Keywords: Resting state fMRI; Schizophrenia; feature selection; functional connectivity; lattice auto-associative memories; lattice computing; machine learning.

Fig. 1

Analysis pipeline for the background/foreground (BF)-lattice auto associative memory (LAAM)-based functional connectivity approach. (1) RsfMRI data were preprocessed, and time series extracted from the specific background (CSF) and foreground (right or left Heschl’s gyrus) regions of interest. (2) We then performed dimensionality reduction, reducing the high dimensionality time series data into LAAM-based functional connectivity measures. (3) We performed feature selection and extraction, using the Pearson’s correlation coefficient (r) between the voxel value across subjects and the class label as a saliency measure to select the voxel sites with the greatest discriminative power. (4) We performed classification using support vector machines (SVM), and generate spatial maps showing the voxel sites with the features that are most highly discriminative.

Fig. 2

The ROIs used for lattice auto-associative memory (LAAM) based connectivity analysis. The fMRI time series from left Heschl’s gyrus (LHG; 10mm, MNI coordinates [−42, −26,10]) (a) and right Heschl’s gyrus (RHG; 10mm, MNI coordinates [46, −20, 8]) (b) were used to compute the left and right one-sided (OS)-LAAM h-functions, respectively. We also computed the background/foreground (BF)-LAAM h-functions, where the fMRI time series from the cerebrospinal fluid (CSF; 10mm, MNI coordinates [−15, −26, 10]) (c) was set as the background training dataset and the fMRI time series from the LHG (a) or RHG (b) were set as the foreground training dataset.

Fig. 3

Localization of feature voxel sites selected from the BF-LAAM h-function map with foreground seed extracted from the LHG ROI, when discriminating SZAH from SZnAH populations. Colorbar is proportional to voxel saliency.

Fig. 4

Localization of feature voxel sites selected from the BF-LAAM h-function map with foreground seed extracted from the RHG ROI, when discriminating SZAH from SZnAH populations. Colorbar is proportional to voxel saliency.

Fig. 5

Localization of feature voxel sites selected from the ReHo, when discriminating SZAH from SZnAH populations. Colorbar is proportional to voxel saliency.

Fig. 6

Localization of feature voxel sites selected from the fALFF, when discriminating SZAH from SZnAH populations. Colorbar is proportional to voxel saliency.