Application of machine learning and complex network measures to an EEG dataset from ayahuasca experiments

Abstract

Ayahuasca is made from a mixture of Amazonian herbs and has been used for a few hundred years by the people of this region for traditional medicine. In addition, this plant has been shown to be a potential treatment for various neurological and psychiatric disorders.EEG experiments have found specific brain regions that changed significantly due to ayahuasca. Here, we used an EEG dataset to investigate the ability to automatically detect changes in brain activity using machine learning and complex networks. Machine learning was applied at three different levels of data abstraction: (A) the raw EEG time series, (B) the correlation of the EEG time series, and (C) the complex network measures calculated from (B).As a result, the machine learning method was able to automatically detect changes in brain activity, with case (B) showing the highest accuracy (92%), followed by (A) (88%) and (C) (83%), indicating that connectivity changes between brain regions are more important than connectivity changes within brain regions. The most activated areas were the frontal and temporal lobe, which is consistent with the literature.In terms of brain connections, the correlation between F3 and PO4 was the most important. This connection may point to a cognitive process similar to face recognition in individuals during ayahuasca-mediated visual hallucinations.Furthermore, closeness centrality and assortativity were the most important complex network measures. These two measures are also associated with diseases such as Alzheimer’s disease, indicating a possible therapeutic mechanism.Overall, our results showed that machine learning methods were able to automatically detect changes in brain activity during ayahuasca consumption. The results also suggest that the application of machine learning and complex network measurements are useful methods to study the effects of ayahuasca on brain activity and medical use.