-

 

 

 




Optimization Online





 

Expert-Enhanced Machine Learning for Cardiac Arrhythmia Classification

Sebastian Sager (sager***at***ovgu.de)
Felix Bernhardt (felix.bernhardt***at***ovgu.de)
Florian Kehrle (florian.kehrle***at***med.uni-heidelberg.de)
Maximilian Merkert (maximilian.merkert***at***ovgu.de)
Andreas Potschka (andreas.potschka***at***iwr.uni-heidelberg.de)
Benjamin Meder (Benjamin.Meder***at***med.uni-heidelberg.de)
Hugo Katus (hugo.katus***at***med.uni-heidelberg.de)
Eberhard Scholz (eberhard.scholz***at***med.uni-heidelberg.de)

Abstract: We propose a new method for the classification task of distinguishing atrial Fibrillation (AFib) from regular atrial tachycardias including atrial Flutter (AFlu) on the basis of a surface electrocardiogram (ECG). Although recently many approaches for an automatic classification of cardiac arrhythmia were proposed, to our knowledge none of them can distinguish between these two. We discuss reasons why deep learning might not yield satisfactory results for this task. We generate new and clinically interpretable features using mathematical optimization for subsequent use within a machine learning (ML) model. These features are generated from the same input data and by solving an additional regression problem with complicated combinatorial substructures. The resulting model can thus also be seen as a completely novel ML model that incorporates expert knowledge on the pathophysiology of AFlu. Our approach achieved an unprecedented accuracy of 82.84% and an excellent area under the ROC curve of 0.9. One additional advantage of our approach is the inherent interpretability of the classification results. Our features give insight into a possibly occurring multi-level atrioventricular blocking mechanism, which might improve treatment decisions beyond the classification itself. Our research ideally complements existing cardiac arrhythmia classification methods from the literature, which can provide a preclassication, but so far left the important case AFib vs AFlu open.

Keywords: Optimization, MINLP, Machine learning, Healthcare, Decision support, Combinatorial algorithms

Category 1: Applications -- Science and Engineering (Biomedical Applications )

Category 2: Combinatorial Optimization

Citation: submitted to Artificial Intelligence in Medicine

Download: [PDF]

Entry Submitted: 10/10/2019
Entry Accepted: 10/10/2019
Entry Last Modified: 11/15/2020

Modify/Update this entry


  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository

 

Submit
Update
Policies
Coordinator's Board
Classification Scheme
Credits
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society