Auditory prediction errors as individual biomarkers of schizophrenia

Abstract

Schizophrenia is a complex psychiatric disorder, typically diagnosed through symptomatic evidence collected through patient interview. We aim to develop an objective biologically-based computational tool which aids diagnosis and relies on accessible imaging technologies such as electroencephalography (EEG). To achieve this, we used machine learning techniques and a combination of paradigms designed to elicit prediction errors or Mismatch Negativity (MMN) responses. MMN, an EEG component elicited by unpredictable changes in sequences of auditory stimuli, has previously been shown to be reduced in people with schizophrenia and this is arguably one of the most reproducible neurophysiological markers of schizophrenia.EEG data were acquired from 21 patients with schizophrenia and 22 healthy controls whilst they listened to three auditory oddball paradigms comprising sequences of tones which deviated in 10% of trials from regularly occurring standard tones. Deviant tones shared the same properties as standard tones, except for one physical aspect: 1) duration -the deviant stimulus was twice the duration of the standard; 2) monaural gap -deviants had a silent interval omitted from the standard, or 3) inter-aural timing difference, which caused the deviant location to be perceived as 90° away from the standards.We used multivariate pattern analysis, a machine learning technique implemented in the Pattern Recognition for Neuroimaging Toolbox (PRoNTo) to classify images generated through statistical parametric mapping (SPM) of spatiotemporal EEG data, i.e. eventrelated potentials measured on the two-dimensional surface of the scalp over time. Using peer-reviewed) is the author/funder. All rights reserved. No reuse allowed without permission.The copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/104547 doi: bioRxiv preprint first posted online Jan. 31, 2017; support vector machine (SVM) and Gaussian processes classifiers (GPC), we were able classify individual patients and controls with balanced accuracies of up to 80.48% (pvalues = 0.0326, FDR corrected) and an ROC analysis yielding an AUC of 0.87.Crucially, a GPC regression revealed that MMN predicted global assessment of functioning (GAF) scores (correlation = 0.73, R 2 = 0.53, p = 0.0006).peer-reviewed)

Combined machine learning and functional magnetic resonance imaging allows individualized prediction of high-altitude induced psychomotor impairment: The role of neural functionality in putamen and pallidum

“…In clinical practice, the potential biomarker may be referred by physicians when they gave advices to voluntary high-altitude immigrants. In parallel, it also helps to understand the pathophysiological processes associated with these neurobehavioral alterations and provide biologicallyrelevant targets that can guide high-altitude impairment prevention and novel treatment development (4,5).…”

Neuroimaging Reveals Heterogeneous Neural Correlates of Reading Deficit in Individuals with Dyslexia Consistent with a Multiple Deficit Model

“…One important branch of neuroimaging is the search for a biomarker in neurological, neuropsychiatric and neurodevelopmental disorders (including dyslexia). For instance, promising strides here have been made using various neuroimaging techniques in Alzheimer's disease (MRI [10], fMRI [11], PET [12] and MEG [13]), schizophrenia (PET [14], EEG [15] and MEG [16]), attention deficit hyperactivity disorder (ADHD) (MEG and structural MRI [17], DKI [18], MRI and MFC [19]) and dyslexia (MEG and structural MRI [17], structural MRI [20], ERPs [21,22], MEG [23] and fMRI [24]). It should be noted that some of the above cited papers explicitly claim the search for neuroimaging biomarkers, while others do not, but the results reported can be considered as potential candidates for neuroimaging biomarkers.…”

Randomised controlled trial of Compensatory Cognitive Training and a Computerised Cognitive Remediation programme

“…There are pilot studies indicating it may be able to predict and be an objective indicator of people who would benefit from psychosocial interventions [9][10][11]. Being able to have more precise information on who would respond to interventions, especially psychosocial interventions that require a weekly commitment over months, would benefit participants and not expose people to the potentially demoralising effect of attending a therapy that they were not able to benefit from [12].…”

“…To classify the compensation and adaptation therapy responders and non-responders, class labels will be assigned to each participant. In PRoNTo, we will apply the support vector machine (SVM) and Gaussian process algorithms [24], which has shown to be effective in classifying schizophrenia patients using neuroimaging features [12]. The SVM training phase involves assigning weights to features and finding the hyperplane that maximises the margin between the groups of participants; the sign of the total feature weights multiplied by the test sample will determine the classification of participants.…”