An Interpretable Machine Learning Method for the Detection of Schizophrenia Using EEG Signals

In this work we propose a machine learning (ML) method to aid in the diagnosis of schizophrenia using electroencephalograms (EEGs) as input data. The computational algorithm not only yields a proposal of diagnostic but, even more importantly, it provides additional information that admits clinical interpretation. It is based on an ML model called random forest that operates on connectivity metrics extracted from the EEG signals. Specifically, we use measures of generalized partial directed coherence (GPDC) and direct directed transfer function (dDTF) to construct the input features to the ML model. The latter allows the identification of the most performance-wise relevant features which, in turn, provide some insights about EEG signals and frequency bands that are associated with schizophrenia. Our preliminary results on real data show that signals associated with the occipital region seem to play a significant role in the diagnosis of the disease. Moreover, although every frequency band might yield useful information for the diagnosis, the beta and theta (frequency) bands provide features that are ultimately more relevant for the ML classifier that we have implemented.

Characterization of the Stages of Creative Writing With Mobile EEG Using Generalized Partial Directed Coherence

Two stages of the creative writing process were characterized through mobile scalp electroencephalography (EEG) in a 16-week creative writing workshop. Portable dry EEG systems (four channels: TP09, AF07, AF08, TP10) with synchronized head acceleration, video recordings, and journal entries, recorded mobile brain-body activity of Spanish heritage students. Each student's brain-body activity was recorded as they experienced spaces in Houston, Texas (“Preparation” stage), and while they worked on their creative texts (“Generation” stage). We used Generalized Partial Directed Coherence (gPDC) to compare the functional connectivity among both stages. There was a trend of higher gPDC in the Preparation stage from right temporo-parietal (TP10) to left anterior-frontal (AF07) brain scalp areas within 1–50 Hz, not reaching statistical significance. The opposite directionality was found for the Generation stage, with statistical significant differences (p < 0.05) restricted to the delta band (1–4 Hz). There was statistically higher gPDC observed for the inter-hemispheric connections AF07–AF08 in the delta and theta bands (1–8 Hz), and AF08 to TP09 in the alpha and beta (8–30 Hz) bands. The left anterior-frontal (AF07) recordings showed higher power localized to the gamma band (32–50 Hz) for the Generation stage. An ancillary analysis of Sample Entropy did not show significant difference. The information transfer from anterior-frontal to temporal-parietal areas of the scalp may reflect multisensory interpretation during the Preparation stage, while brain signals originating at temporal-parietal toward frontal locations during the Generation stage may reflect the final decision making process to translate the multisensory experience into a creative text.

ANALYSIS OF ELECTROENCEPHALOGRAPHIC RECORDINGS FROM EPILEPSY PATIENTS USING RESTRICTED GRANGER CAUSALITY MEASURES

Epilepsy is a chronic disorder of the brain that affects 1% of world population. The occurrence of epileptiform discharges (ED) in electroencephalographic (EEG) recordings of patients with epilepsy signifies a change in brain dynamics and particularly brain connectivity. In the last decade, many linear and nonlinear measures have been developed for the analysis of EEG recordings to detect the direct causal effects between brain regions. In many cases the number of EEG channels (the time series variables) is large and the analysis is based on short time intervals, resulting in unstable estimation of vector autoregressive models (VAR models) and subsequently unreliable Granger causality measure. For this, restricted VAR models have been proposed and in our recent study it was found that optimal restriction of VAR for the estimation of Granger causality was obtained by the backward-in-time selection method (BTS). We use the concept of restricted VAR models in measures both in time and frequency domain, namely restricted conditional Granger causality and restricted generalized partial directed coherence. We test the two measures in their ability of detecting changes in brain connectivity during an epileptiform discharge from multi-channel scalp electroencephalograms (EEG).