<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>2072</id>
    <completedYear>2022</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1</pageFirst>
    <pageLast>26</pageLast>
    <pageNumber/>
    <edition/>
    <issue>12</issue>
    <volume>2022</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-12-16</completedDate>
    <publishedDate>2022-12-16</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Application of machine learning and complex network measures to an EEG dataset from ayahuasca experiments</title>
    <abstract language="eng">Ayahuasca is a blend of Amazonian plants that has been used for traditional medicine by&#13;
the inhabitants of this region for hundreds of years. Furthermore, this plant has been demon� strated to be a viable therapy for a variety of neurological and mental diseases. EEG experi� ments have found specific brain regions that changed significantly due to ayahuasca. Here,&#13;
we used an EEG dataset to investigate the ability to automatically detect changes in brain&#13;
activity using machine learning and complex networks. Machine learning was applied at&#13;
three different levels of data abstraction: (A) the raw EEG time series, (B) the correlation of&#13;
the EEG time series, and (C) the complex network measures calculated from (B). Further, at&#13;
the abstraction level of (C), we developed new measures of complex networks relating to&#13;
community detection. As a result, the machine learning method was able to automatically&#13;
detect changes in brain activity, with case (B) showing the highest accuracy (92%), followed&#13;
by (A) (88%) and (C) (83%), indicating that connectivity changes between brain regions are&#13;
more important for the detection of ayahuasca. The most activated areas were the frontal&#13;
and temporal lobe, which is consistent with the literature. F3 and PO4 were the most impor� tant brain connections, a significant new discovery for psychedelic literature. This connec� tion may point to a cognitive process akin to face recognition in individuals during&#13;
ayahuasca-mediated visual hallucinations. Furthermore, closeness centrality and assorta� tivity were the most important complex network measures. These two measures are also&#13;
associated with diseases such as Alzheimer’s disease, indicating a possible therapeutic&#13;
mechanism. Moreover, the new measures were crucial to the predictive model and sug� gested larger brain communities associated with the use of ayahuasca. This suggests that&#13;
the dissemination of information in functional brain networks is slower when this drug is&#13;
present. Overall, our methodology was able to automatically detect changes in brain activity&#13;
during ayahuasca consumption and interpret how these psychedelics alter brain networks,&#13;
as well as provide insights into their mechanisms of action</abstract>
    <parentTitle language="eng">PLOS ONE</parentTitle>
    <identifier type="doi">https://doi.org/10.1371/journal. pone.0277257</identifier>
    <enrichment key="copyright">1</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Caroline L. Alves</author>
    <author>Rubens G. Cury</author>
    <author>Kirstin Roster</author>
    <author>Aruane M. Pineda</author>
    <author>Francisco A. Rodrigues</author>
    <author>Christiane Thielemann</author>
    <author>Manuel Ciba</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Ayahuasca</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Elektroencephalographie</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Alzheimerkrankheit</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Gehirn</value>
    </subject>
    <collection role="institutes" number="">BIOMEMS Lab</collection>
    <collection role="forschungsschwerpunkte" number="">Artifical Intelligence and Data Science</collection>
    <file>https://opus4.kobv.de/opus4-h-ab/files/2072/journal.pone.0277257.pdf</file>
  </doc>
  <doc>
    <id>2060</id>
    <completedYear>2022</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1</pageFirst>
    <pageLast>13</pageLast>
    <pageNumber/>
    <edition/>
    <issue>3</issue>
    <volume>2022</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-11-17</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">EEG functional connectivity and deep learning for automatic diagnosis of brain disorders: Alzheimer’s disease and schizophrenia</title>
    <abstract language="eng">Mental disorders are among the leading causes of disability worldwide. The first step in treating&#13;
these conditions is to obtain an accurate diagnosis. Machine learning algorithms can provide a&#13;
possible solution to this problem, as we describe in this work. We present a method for the&#13;
automatic diagnosis of mental disorders based on the matrix of connections obtained from EEG&#13;
time series and deep learning. We show that our approach can classify patients with Alzheimer’s&#13;
disease and schizophrenia with a high level of accuracy. The comparison with the traditional cases,&#13;
that use raw EEG time series, shows that our method provides the highest precision. Therefore, the&#13;
application of deep neural networks on data from brain connections is a very promising method&#13;
for the diagnosis of neurological disorders.</abstract>
    <parentTitle language="eng">Journal of Physics: complexity</parentTitle>
    <identifier type="doi">DOI 10.1088/2632-072X/ac5f8d</identifier>
    <enrichment key="copyright">0</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Caroline L. Alves</author>
    <author>Aruane M. Pineda</author>
    <author>Kirstin Roster</author>
    <author>Christiane Thielemann</author>
    <author>Francisco A. Rodrigues</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>complex networks</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Machine learning</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Hirnfunktionsstörung</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Alzheimerkrankheit</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Schizophrenie</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Elektroencephalographie</value>
    </subject>
    <collection role="institutes" number="">BIOMEMS Lab</collection>
    <collection role="forschungsschwerpunkte" number="">Artifical Intelligence and Data Science</collection>
  </doc>
</export-example>
