Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification
Implantable Cardiac Monitor (ICM) devices are demonstrating, as of today, the fastest-growing market for implantable cardiac devices. As such, they are becoming increasingly common in patients for measuring heart electrical activity. ICMs constantly monitor and record a patient’s heart rhythm, and w...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/5/4/77 |
| _version_ | 1797380268930105344 |
|---|---|
| author | Amnon Bleich Antje Linnemann Benjamin Jaidi Björn H. Diem Tim O. F. Conrad |
| author_facet | Amnon Bleich Antje Linnemann Benjamin Jaidi Björn H. Diem Tim O. F. Conrad |
| author_sort | Amnon Bleich |
| collection | DOAJ |
| description | Implantable Cardiac Monitor (ICM) devices are demonstrating, as of today, the fastest-growing market for implantable cardiac devices. As such, they are becoming increasingly common in patients for measuring heart electrical activity. ICMs constantly monitor and record a patient’s heart rhythm, and when triggered, send it to a secure server where health care professionals (HCPs) can review it. These devices employ a relatively simplistic rule-based algorithm (due to energy consumption constraints) to make alerts for abnormal heart rhythms. This algorithm is usually parameterized to an over-sensitive mode in order to not miss a case (resulting in a relatively high false-positive rate), and this, combined with the device’s nature of constantly monitoring the heart rhythm and its growing popularity, results in HCPs having to analyze and diagnose an increasingly growing number of data. In order to reduce the load on the latter, automated methods for ECG analysis are nowadays becoming a great tool to assist HCPs in their analysis. While state-of-the-art algorithms are data-driven rather than rule-based, training data for ICMs often consist of specific characteristics that make their analysis unique and particularly challenging. This study presents the challenges and solutions in automatically analyzing ICM data and introduces a method for its classification that outperforms existing methods on such data. It carries this out by combining high-frequency noise detection (which often occurs in ICM data) with a semi-supervised learning pipeline that allows for the re-labeling of training episodes and by using segmentation and dimension-reduction techniques that are robust to morphology variations of the sECG signal (which are typical to ICM data). As a result, it performs better than state-of-the-art techniques on such data with, e.g., an F1 score of 0.51 vs. 0.38 of our baseline state-of-the-art technique in correctly calling atrial fibrillation in ICM data. As such, it could be used in numerous ways, such as aiding HCPs in the analysis of ECGs originating from ICMs by, e.g., suggesting a rhythm type. |
| first_indexed | 2024-03-08T20:34:59Z |
| format | Article |
| id | doaj.art-8926f171dd224c9db357d48613252da7 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-03-08T20:34:59Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-8926f171dd224c9db357d48613252da72023-12-22T14:22:10ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902023-10-01541539155610.3390/make5040077Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label ClassificationAmnon Bleich0Antje Linnemann1Benjamin Jaidi2Björn H. Diem3Tim O. F. Conrad4Visual and Data-Centric Computing Department, Zuse Institute Berlin, Takustraße 7, 14195 Berlin, GermanyBIOTRONIK SE & Co., KG, Woermannkehre 1, 12359 Berlin, GermanyBIOTRONIK SE & Co., KG, Woermannkehre 1, 12359 Berlin, GermanyBIOTRONIK SE & Co., KG, Woermannkehre 1, 12359 Berlin, GermanyVisual and Data-Centric Computing Department, Zuse Institute Berlin, Takustraße 7, 14195 Berlin, GermanyImplantable Cardiac Monitor (ICM) devices are demonstrating, as of today, the fastest-growing market for implantable cardiac devices. As such, they are becoming increasingly common in patients for measuring heart electrical activity. ICMs constantly monitor and record a patient’s heart rhythm, and when triggered, send it to a secure server where health care professionals (HCPs) can review it. These devices employ a relatively simplistic rule-based algorithm (due to energy consumption constraints) to make alerts for abnormal heart rhythms. This algorithm is usually parameterized to an over-sensitive mode in order to not miss a case (resulting in a relatively high false-positive rate), and this, combined with the device’s nature of constantly monitoring the heart rhythm and its growing popularity, results in HCPs having to analyze and diagnose an increasingly growing number of data. In order to reduce the load on the latter, automated methods for ECG analysis are nowadays becoming a great tool to assist HCPs in their analysis. While state-of-the-art algorithms are data-driven rather than rule-based, training data for ICMs often consist of specific characteristics that make their analysis unique and particularly challenging. This study presents the challenges and solutions in automatically analyzing ICM data and introduces a method for its classification that outperforms existing methods on such data. It carries this out by combining high-frequency noise detection (which often occurs in ICM data) with a semi-supervised learning pipeline that allows for the re-labeling of training episodes and by using segmentation and dimension-reduction techniques that are robust to morphology variations of the sECG signal (which are typical to ICM data). As a result, it performs better than state-of-the-art techniques on such data with, e.g., an F1 score of 0.51 vs. 0.38 of our baseline state-of-the-art technique in correctly calling atrial fibrillation in ICM data. As such, it could be used in numerous ways, such as aiding HCPs in the analysis of ECGs originating from ICMs by, e.g., suggesting a rhythm type.https://www.mdpi.com/2504-4990/5/4/77ECGICMclassificationsemi-supervised-learning |
| spellingShingle | Amnon Bleich Antje Linnemann Benjamin Jaidi Björn H. Diem Tim O. F. Conrad Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification Machine Learning and Knowledge Extraction ECG ICM classification semi-supervised-learning |
| title | Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification |
| title_full | Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification |
| title_fullStr | Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification |
| title_full_unstemmed | Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification |
| title_short | Enhancing Electrocardiogram (ECG) Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification |
| title_sort | enhancing electrocardiogram ecg analysis of implantable cardiac monitor data an efficient pipeline for multi label classification |
| topic | ECG ICM classification semi-supervised-learning |
| url | https://www.mdpi.com/2504-4990/5/4/77 |
| work_keys_str_mv | AT amnonbleich enhancingelectrocardiogramecganalysisofimplantablecardiacmonitordataanefficientpipelineformultilabelclassification AT antjelinnemann enhancingelectrocardiogramecganalysisofimplantablecardiacmonitordataanefficientpipelineformultilabelclassification AT benjaminjaidi enhancingelectrocardiogramecganalysisofimplantablecardiacmonitordataanefficientpipelineformultilabelclassification AT bjornhdiem enhancingelectrocardiogramecganalysisofimplantablecardiacmonitordataanefficientpipelineformultilabelclassification AT timofconrad enhancingelectrocardiogramecganalysisofimplantablecardiacmonitordataanefficientpipelineformultilabelclassification |