A two-step method for paroxysmal atrial fibrillation event detection based on machine learning
| Title: | A two-step method for paroxysmal atrial fibrillation event detection based on machine learning |
|---|---|
| Authors: | Ya'nan Wang, Sen Liu, Haijun Jia, Xintao Deng, Chunpu Li, Aiguo Wang, Cuiwei Yang |
| Source: | Mathematical Biosciences and Engineering, Vol 19, Iss 10, Pp 9877-9894 (2022) |
| Publisher Information: | AIMS Press, 2022. |
| Publication Year: | 2022 |
| Collection: | LCC:Biotechnology LCC:Mathematics |
| Subject Terms: | atrial fibrillation event detection, machine learning, phased training, two-step method, rr intervals, Biotechnology, TP248.13-248.65, Mathematics, QA1-939 |
| More Details: | Detection of atrial fibrillation (AF) events is significant for early clinical diagnosis and appropriate intervention. However, in existing detection algorithms for paroxysmal AF (AFp), the location of AF starting and ending points in AFp is not concerned. To achieve an accurate identification of AFp events in the long-term dynamic electrocardiograms (ECGs), this paper proposes a two-step method based on machine learning. In the first step, based on features extracted from the calculated R-to-R intervals (RR intervals, the cycle of heart beat), the rhythm type of the ECG signal is first classified into three classes (AFp rhythm, persistent AF (AFf) rhythm, and non-atrial fibrillation (non-AF, N) rhythm) using support vector machine (SVM). In the second step, the starting and ending points for AF episodes of AFp rhythms predicted in the first step are further located based on heartbeat classification. By training a deep convolutional neural network with phased training, the segmented beats of AFp rhythms are divided into AF beats and non-AF beats to determine the beginning and end of any AF episode. The proposed two-step method is trained and tested on the 4th China Physiological Signal Challenge 2021 databases. A final score U of 1.9310 is obtained on the unpublished test set maintained by the challenge organizers, which demonstrates the advantage of the two-step method in AFp event detection. The work is useful for assessing AF burden index for AFp patients. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 1551-0018 83310444 |
| Relation: | https://doaj.org/toc/1551-0018 |
| DOI: | 10.3934/mbe.2022460?viewType=HTML |
| DOI: | 10.3934/mbe.2022460 |
| Access URL: | https://doaj.org/article/96ed1e36197b453a947f21a833104442 |
| Accession Number: | edsdoj.96ed1e36197b453a947f21a833104442 |
| Database: | Directory of Open Access Journals |
| ISSN: | 15510018 83310444 |
|---|---|
| DOI: | 10.3934/mbe.2022460?viewType=HTML |
| Published in: | Mathematical Biosciences and Engineering |
| Language: | English |