Expert-enhanced machine learning for cardiac arrhythmia classification
We propose a new method for the classification task of distinguishing atrial fibrillation (AFib) from regular atrial tachycardias including atrial flutter (AFlu) based on a surface electrocardiogram (ECG). Recently, many approaches for an automatic classification of cardiac arrhythmia were proposed...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
December 23, 2021
|
| In: |
PLOS ONE
Year: 2021, Jahrgang: 16, Heft: 12, Pages: 1-22 |
| ISSN: | 1932-6203 |
| DOI: | 10.1371/journal.pone.0261571 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1371/journal.pone.0261571 Verlag, lizenzpflichtig, Volltext: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0261571 
|
| Verfasserangaben: | Sebastian Sager, Felix Bernhardt, Florian Kehrle, Maximilian Merkert, Andreas Potschka, Benjamin Meder, Hugo Katus, Eberhard Scholz |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1796151556 | ||
| 003 | DE-627 | ||
| 005 | 20220820150753.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 220321s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1371/journal.pone.0261571 |2 doi | |
| 035 | |a (DE-627)1796151556 | ||
| 035 | |a (DE-599)KXP1796151556 | ||
| 035 | |a (OCoLC)1341453594 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 30 |2 sdnb | ||
| 100 | 1 | |a Sager, Sebastian |d 1975- |e VerfasserIn |0 (DE-588)134228650 |0 (DE-627)563402520 |0 (DE-576)300389973 |4 aut | |
| 245 | 1 | 0 | |a Expert-enhanced machine learning for cardiac arrhythmia classification |c Sebastian Sager, Felix Bernhardt, Florian Kehrle, Maximilian Merkert, Andreas Potschka, Benjamin Meder, Hugo Katus, Eberhard Scholz |
| 264 | 1 | |c December 23, 2021 | |
| 300 | |a 22 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 22.03.2022 | ||
| 520 | |a We propose a new method for the classification task of distinguishing atrial fibrillation (AFib) from regular atrial tachycardias including atrial flutter (AFlu) based on a surface electrocardiogram (ECG). Recently, many approaches for an automatic classification of cardiac arrhythmia were proposed and to our knowledge none of them can distinguish between these two. We discuss reasons why deep learning may 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 by solving an additional regression problem with complicated combinatorial substructures. The resultant can be seen as a novel machine learning model that incorporates expert knowledge on the pathophysiology of atrial flutter. Our approach achieves an unprecedented accuracy of 82.84% and an area under the receiver operating characteristic (ROC) curve of 0.9, which classifies as “excellent” according to the classification indicator of diagnostic tests. One additional advantage of our approach is the inherent interpretability of the classification results. Our features give insight into a possibly occurring multilevel atrioventricular blocking mechanism, which may improve treatment decisions beyond the classification itself. Our research ideally complements existing textbook cardiac arrhythmia classification methods, which cannot provide a classification for the important case of AFib↔AFlu. The main contribution is the successful use of a novel mathematical model for multilevel atrioventricular block and optimization-driven inverse simulation to enhance machine learning for classification of the arguably most difficult cases in cardiac arrhythmia. A tailored Branch-and-Bound algorithm was implemented for the domain knowledge part, while standard algorithms such as Adam could be used for training. | ||
| 650 | 4 | |a Arrhythmia | |
| 650 | 4 | |a Atrial fibrillation | |
| 650 | 4 | |a Electrocardiography | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Machine learning algorithms | |
| 650 | 4 | |a Mathematical models | |
| 650 | 4 | |a Neural networks | |
| 650 | 4 | |a Optimization | |
| 700 | 1 | |a Bernhardt, Felix |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kehrle, Florian |d 1984- |e VerfasserIn |0 (DE-588)116049598X |0 (DE-627)1023734397 |0 (DE-576)505953021 |4 aut | |
| 700 | 1 | |a Merkert, Maximilian |e VerfasserIn |0 (DE-588)1020268476 |0 (DE-627)68810973X |0 (DE-576)360008976 |4 aut | |
| 700 | 1 | |a Potschka, Andreas |d 1980- |e VerfasserIn |0 (DE-588)1019443391 |0 (DE-627)685041166 |0 (DE-576)358073995 |4 aut | |
| 700 | 1 | |a Meder, Benjamin |e VerfasserIn |0 (DE-588)135821630 |0 (DE-627)571676316 |0 (DE-576)300664745 |4 aut | |
| 700 | 1 | |a Katus, Hugo |d 1951- |e VerfasserIn |0 (DE-588)108916618 |0 (DE-627)577155040 |0 (DE-576)289625076 |4 aut | |
| 700 | 1 | |a Scholz, Eberhard P. |d 1978- |e VerfasserIn |0 (DE-588)13163660X |0 (DE-627)512033994 |0 (DE-576)298640589 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t PLOS ONE |d San Francisco, California, US : PLOS, 2006 |g 16(2021), 12, Artikel-ID e0261571, Seite 1-22 |h Online-Ressource |w (DE-627)523574592 |w (DE-600)2267670-3 |w (DE-576)281331979 |x 1932-6203 |7 nnas |a Expert-enhanced machine learning for cardiac arrhythmia classification |
| 773 | 1 | 8 | |g volume:16 |g year:2021 |g number:12 |g elocationid:e0261571 |g pages:1-22 |g extent:22 |a Expert-enhanced machine learning for cardiac arrhythmia classification |
| 856 | 4 | 0 | |u https://doi.org/10.1371/journal.pone.0261571 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0261571 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20220321 | ||
| 993 | |a Article | ||
| 994 | |a 2021 | ||
| 998 | |g 13163660X |a Scholz, Eberhard P. |m 13163660X:Scholz, Eberhard P. |d 50000 |e 50000PS13163660X |k 0/50000/ |p 8 |y j | ||
| 998 | |g 108916618 |a Katus, Hugo |m 108916618:Katus, Hugo |d 910000 |d 910100 |d 50000 |e 910000PK108916618 |e 910100PK108916618 |e 50000PK108916618 |k 0/910000/ |k 1/910000/910100/ |k 0/50000/ |p 7 | ||
| 998 | |g 135821630 |a Meder, Benjamin |m 135821630:Meder, Benjamin |d 910000 |d 910100 |d 50000 |e 910000PM135821630 |e 910100PM135821630 |e 50000PM135821630 |k 0/910000/ |k 1/910000/910100/ |k 0/50000/ |p 6 | ||
| 998 | |g 1019443391 |a Potschka, Andreas |m 1019443391:Potschka, Andreas |d 110000 |e 110000PP1019443391 |k 0/110000/ |p 5 | ||
| 998 | |g 116049598X |a Kehrle, Florian |m 116049598X:Kehrle, Florian |d 910000 |d 910100 |e 910000PK116049598X |e 910100PK116049598X |k 0/910000/ |k 1/910000/910100/ |p 3 | ||
| 998 | |g 134228650 |a Sager, Sebastian |m 134228650:Sager, Sebastian |p 1 |x j | ||
| 999 | |a KXP-PPN1796151556 |e 4097000772 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"note":["Gesehen am 22.03.2022"],"recId":"1796151556","person":[{"family":"Sager","role":"aut","display":"Sager, Sebastian","given":"Sebastian"},{"family":"Bernhardt","role":"aut","display":"Bernhardt, Felix","given":"Felix"},{"family":"Kehrle","role":"aut","display":"Kehrle, Florian","given":"Florian"},{"role":"aut","family":"Merkert","given":"Maximilian","display":"Merkert, Maximilian"},{"family":"Potschka","role":"aut","display":"Potschka, Andreas","given":"Andreas"},{"given":"Benjamin","display":"Meder, Benjamin","family":"Meder","role":"aut"},{"family":"Katus","role":"aut","given":"Hugo","display":"Katus, Hugo"},{"family":"Scholz","role":"aut","display":"Scholz, Eberhard P.","given":"Eberhard P."}],"name":{"displayForm":["Sebastian Sager, Felix Bernhardt, Florian Kehrle, Maximilian Merkert, Andreas Potschka, Benjamin Meder, Hugo Katus, Eberhard Scholz"]},"language":["eng"],"origin":[{"dateIssuedDisp":"December 23, 2021","dateIssuedKey":"2021"}],"relHost":[{"recId":"523574592","name":{"displayForm":["Public Library of Science"]},"origin":[{"publisher":"PLOS ; PLoS","dateIssuedDisp":"2006-","dateIssuedKey":"2006","publisherPlace":"San Francisco, California, US ; Lawrence, Kan."}],"id":{"zdb":["2267670-3"],"issn":["1932-6203"],"eki":["523574592"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"PLOS ONE","title":"PLOS ONE"}],"note":["Schreibweise des Titels bis 2012: PLoS ONE","Gesehen am 20.03.19"],"pubHistory":["1.2006 -"],"part":{"volume":"16","year":"2021","issue":"12","extent":"22","pages":"1-22","text":"16(2021), 12, Artikel-ID e0261571, Seite 1-22"},"language":["eng"],"disp":"Expert-enhanced machine learning for cardiac arrhythmia classificationPLOS ONE","type":{"media":"Online-Ressource","bibl":"periodical"},"corporate":[{"display":"Public Library of Science","role":"isb"}]}],"id":{"eki":["1796151556"],"doi":["10.1371/journal.pone.0261571"]},"physDesc":[{"extent":"22 S."}],"title":[{"title_sort":"Expert-enhanced machine learning for cardiac arrhythmia classification","title":"Expert-enhanced machine learning for cardiac arrhythmia classification"}],"type":{"bibl":"article-journal","media":"Online-Ressource"}} | ||
| SRT | |a SAGERSEBASEXPERTENHA2320 | ||