Dzafic, I. | bioRxiv Science

bioRxiv2018

Predicting Individual Psychotic Experiences on a Continuum Using Machine Learning

Previous studies applying machine learning methods to psychosis have primarily been concerned with the binary classification of chronic schizophrenia patients and healthy controls. The aim of this study was to use electroencephalographic (EEG) data and pattern recognition to predict subclinical psychotic-like experiences on a continuum between these two extremes in otherwise healthy people. We applied two different approaches to an auditory oddball regularity learning task obtained from N = 73 participants: O_LIA feature extraction and selection routine incorporating behavioural measures, event-related potential components and effective connectivity parameters; C_LIO_LIRegularisation of spatiotemporal maps of event-related potentials. C_LI Using the latter approach, optimal performance was achieved using the response to frequent, predictable sounds. Features within the P50 and P200 time windows had the greatest contribution toward lower Prodromal Questionnaire (PQ) scores and the N100 time window contributed most to higher PQ scores. As a proof-of-concept, these findings demonstrate that EEG data alone are predictive of individual psychotic-like experiences in healthy people. Our findings are in keeping with the mounting evidence for altered sensory responses in schizophrenia, as well as the notion that psychosis may exist on a continuum expanding into the non-clinical population.

neuroscience↗

bioRxiv2018

Reduced top-down connectivity as an underlying mechanism for psychotic experiences in healthy people

Our perceptions result from the brains ability to make inferences, or predictive models, of sensory information. Recently, it has been proposed that psychotic traits may be linked to impaired predictive processes. Here, we examine the brain dynamics underlying sensory learning and inference in stable and volatile environments, in a population of healthy individuals (N=75) with a range of psychotic-like experiences. We measured prediction error responses to sound sequences with electroencephalography, gauged sensory inference explicitly by behaviourally recording sensory regularity learning errors, and used dynamic causal modelling to tap into the underlying neural circuitry. We discuss the findings that were robust to replication across the two experiments (N=31 and N=44 for the discovery and the validation datasets, respectively). First, we found that during stable conditions, participants demonstrated a stronger predictive model, reflected in a larger prediction error response to unexpected sounds, and decreased regularity learning errors. Moreover, individuals with attenuated prediction errors in stable conditions were found to make greater incorrect predictions about sensory information. Critically, we show that greater errors in sensory learning and inference are related to increased psychotic-like experiences. These findings link neurophysiology to behaviour during sensory learning and prediction formation, as well as providing further evidence for the idea of a continuum of psychosis in the healthy, non-clinical population. Significance StatementWhilst perceiving the world, we make inferences by learning the regularities present in the sensory environment. It has been argued that psychosis may emerge due to a failure to learn sensory regularities, resulting in an impaired representation of the world. Recently it has been proposed that psychosis exists on a continuum; however, there is conflicting evidence on whether sensory learning deficits align on the non-clinical end of the psychosis continuum. We found that sensory learning is associated with brain prediction errors, and critically, it is impaired in healthy people who report more psychotic-like experiences. We replicated these findings in an independent sample, demonstrating strengthened credibility to support that the continuum of psychosis extends into the non-clinical population.

neuroscience↗