Conference paper Open Access

Early Parkinson's Disease Detection via Touchscreen Typing Analysis using Convolutional Neural Networks

Dimitrios Iakovakis; Stelios Hadjidimitriou; Vasileios Charisis; Sevasti Bostanjopoulou; Zoe Katsarou; Lisa Klingelhoefer; Simone Mayer; Heinz Reichmann; Sofia B. Dias; José A. Diniz; Dhaval Trivedi; Ray K. Chaudhuri; Leontios J. Hadjileontiadis


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <controlfield tag="005">20200324131812.0</controlfield>
  <controlfield tag="001">3675381</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aristotle University of Thessaloniki</subfield>
    <subfield code="a">Stelios Hadjidimitriou</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aristotle University of Thessaloniki</subfield>
    <subfield code="a">Vasileios Charisis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Department of Neurology, Hippokration Hospital</subfield>
    <subfield code="a">Sevasti Bostanjopoulou</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Department of Neurology, Hippokration Hospital Thessaloniki</subfield>
    <subfield code="a">Zoe Katsarou</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Department of Neurology Technical University Dresden</subfield>
    <subfield code="a">Lisa Klingelhoefer</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Department of Neurology Technical University Dresden</subfield>
    <subfield code="a">Simone Mayer</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Department of Neurology Technical University Dresden</subfield>
    <subfield code="a">Heinz Reichmann</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Faculdade de Motricidade Humana Universidade de Lisboa</subfield>
    <subfield code="a">Sofia B. Dias</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Faculdade de Motricidade Humana Universidade de Lisboa</subfield>
    <subfield code="a">José A. Diniz</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">International Parkinson Excellence Research Centre, King's College Hospital NHS Foundation Trust, London, United Kingdom</subfield>
    <subfield code="a">Dhaval Trivedi</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">International Parkinson Excellence Research Centre, King's College Hospital NHS Foundation Trust, London, United Kingdom</subfield>
    <subfield code="a">Ray K. Chaudhuri</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aristotle University of Thessaloniki</subfield>
    <subfield code="a">Leontios J. Hadjileontiadis</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">4982892</subfield>
    <subfield code="z">md5:5f159502f320c7eea8629c3cdaf09f3f</subfield>
    <subfield code="u">https://zenodo.org/record/3675381/files/EMBC_Keystroke_Dynamics_Final_212019.docx</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-07-28</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:3675381</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Aristotle University of Thessaloniki</subfield>
    <subfield code="0">(orcid)0000-0002-6854-5942</subfield>
    <subfield code="a">Dimitrios Iakovakis</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Early Parkinson's Disease Detection via Touchscreen Typing Analysis using Convolutional Neural Networks</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">690494</subfield>
    <subfield code="a">Intelligent Parkinson eaRly detectiOn Guiding NOvel Supportive InterventionS</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Parkinson&amp;rsquo;s Disease (PD) is the second most&amp;nbsp;common neurodegenerative disorder worldwide, causing both&amp;nbsp;motor and non-motor&amp;nbsp; symptoms. In the early stages, symptoms&amp;nbsp;are mild and patients may ignore their existence. As a result,&amp;nbsp;they do not undergo any related clinical examination; hence delaying their PD diagnosis. In an effort to remedy such delay,&amp;nbsp;analysis of data passively&amp;nbsp; captured from user&amp;rsquo;s interaction with&amp;nbsp;consumer technologies has been recently explored towards&amp;nbsp;remote screening of early PD motor signs. In the current study,&amp;nbsp;a smartphone-based method analyzing subjects&amp;rsquo; finger&amp;nbsp;interaction with the smartphone screen is developed for the&amp;nbsp;quantification of fine-motor skills decline in early PD using&amp;nbsp;Convolutional Neural Networks. Experimental results from the&amp;nbsp;analysis of keystroke typing in-the-clinic data from 18 early PD&amp;nbsp;patients and 15 healthy controls have shown a classification&lt;br&gt;
performance of 0.89 Area Under the Curve (AUC) with 0.79/0.79&amp;nbsp;sensitivity/specificity, respectively. Evaluation of the&amp;nbsp;generalization ability of the proposed approach was made by its&amp;nbsp;application on typing data arising from a separate self-reported&amp;nbsp;cohort of 27 PD patients&amp;rsquo; and 84 healthy controls&amp;rsquo; daily usage&amp;nbsp;with their personal smartphones (data in-the-wild), achieving&amp;nbsp;0.79 AUC with 0.74/0.78 sensitivity/specificity, respectively. The&amp;nbsp;results show the potentiality of the proposed approach to process&amp;nbsp;keystroke dynamics arising from users&amp;rsquo; natural typing activity&amp;nbsp;to detect PD, which contributes to the development of digital&amp;nbsp;tools for remote pathological symptom screening.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3675380</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3675381</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
69
7
views
downloads
All versions This version
Views 6969
Downloads 77
Data volume 34.9 MB34.9 MB
Unique views 6262
Unique downloads 77

Share

Cite as