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. event-related potentials measured on the two-dimensional surface of the scalp over time. Using 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% (p-values = 0.0326, FDR corrected) and an ROC analysis yielding an AUC of 0.87. Crucially, a GP regression revealed that MMN predicted global assessment of functioning (GAF) scores (correlation = 0.73, R2 = 0.53, p = 0.0006).

Grey matter biomarker identification in Schizophrenia: detecting regional alterations and their underlying substrates

“…The most commonly reported classification output amongst most previous machine learning frameworks is a voxel-wise map of inter-correlated voxel weights, showing the contribution of each voxel to the overall classification with respect to all other voxels. However, due to the inter-dependencies between voxels inherent in the model, no inference can be made either for an individual voxel independently of all others, or for the regions of interest (ROIs), or for the underlying substrate (e.g., volume, cortical thickness, gyrification) (Taylor et al 2017). In this work we showed that it is possible to identify the most relevant feature that can serve as biomarkers to classify patients with Schizophrenia from healthy controls and draw inference on the contribution of these biomarkers to the overall classification.…”

Multi-dimensional predictions of psychotic symptoms via machine learning

“…The composite score is the sum of all symptom subscales, providing an overall summary of the given category. The limited prior work on predicting schizophrenia symptoms via machine learning has thus far only been performed on the basis of composite symptoms (10,11), general functioning (12,13) and polygenic risk scores for schizophrenia (14). Other neuroimaging studies have also reported univariate correlates (15,16), or lack thereof (17,18), with symptom severity on the basis of composite summary scores rather than those of the underlying symptoms, an approach which significantly comprises aetiological specificity (19).…”

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 – 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 ].…”