Thesis Open Access

Development of an embedded device for real-time detection of atrial fibrillation and atrial flutter in single-channel ECG, using optimised classification based on a large training corpus

Auer, Eric


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Auer, Eric</dc:creator>
  <dc:date>2020-12-27</dc:date>
  <dc:description>Atrial fibrillation (A-Fib) and atrial flutter are widespread medical conditions of the heart. Loss of coordination between atrial and ventricular activities affects the smooth circulation of blood, causing an increased risk of blood clotting, which in turn elevates risk of pulmonary embolisms and cerebral infarction. However, the condition is not necessarily noticed by patients, for example through palpitations or tachycardia.

A custom embedded device developed for this master's thesis helps people to evaluate whether they are experiencing atrial fibrillation at a specific moment. The device measures single-channel ECG for less than one minute and instantly classifies it as either A-Fib, normal sinus rhythm (NSR) or undecided (low measurement quality or atypical ECG).

Building on an earlier proof of concept project work by the author, this thesis presents a fully integrated, custom device, using an advanced classification algorithm trained on thousands of short, annotated ECG fragments from the PTB-XL corpus. The algorithm uses morphological analysis of the averaged ECG shape, properties of the R/R interval distribution and spectral analysis of the ECG to create a feature vector used for classification. Analysis and raw ECG data can be transferred via Bluetooth at the user's discretion.
 </dc:description>
  <dc:description>Master's Thesis, Neural Engineering, University of Applied Sciences Saarbrücken (htwsaar)
Supervisors: Prof. Dr. Oliver Scholz, Prof. Dr. rer. nat. Dr. rer. med. habil. Daniel J. Strauss</dc:description>
  <dc:identifier>https://zenodo.org/record/4560151</dc:identifier>
  <dc:identifier>10.5281/zenodo.4560151</dc:identifier>
  <dc:identifier>oai:zenodo.org:4560151</dc:identifier>
  <dc:language>eng</dc:language>
  <dc:relation>doi:10.5281/zenodo.4560322</dc:relation>
  <dc:relation>doi:10.5281/zenodo.4560352</dc:relation>
  <dc:relation>doi:10.5281/zenodo.4311642</dc:relation>
  <dc:relation>doi:10.13026/x4td-x982</dc:relation>
  <dc:relation>doi:10.1038/s41597-020-0495-6</dc:relation>
  <dc:relation>doi:10.5281/zenodo.4560150</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:subject>ecg</dc:subject>
  <dc:subject>atrial fibrillation</dc:subject>
  <dc:subject>esp32</dc:subject>
  <dc:subject>embedded system</dc:subject>
  <dc:subject>medical engineering</dc:subject>
  <dc:subject>open hardware</dc:subject>
  <dc:subject>open source</dc:subject>
  <dc:title>Development of an embedded device for real-time detection of atrial fibrillation and atrial flutter in single-channel ECG, using optimised classification based on a large training corpus</dc:title>
  <dc:type>info:eu-repo/semantics/doctoralThesis</dc:type>
  <dc:type>publication-thesis</dc:type>
</oai_dc:dc>
85
69
views
downloads
All versions This version
Views 8585
Downloads 6969
Data volume 502.1 MB502.1 MB
Unique views 6666
Unique downloads 5151

Share

Cite as