2018
DOI: 10.1088/1361-6579/aadf48
|View full text |Cite
|
Sign up to set email alerts
|

Detection of atrial fibrillation from ECG recordings using decision tree ensemble with multi-level features

Abstract: The proposed algorithm may be used as a new method for AF detection.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

2
23
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 36 publications
(25 citation statements)
references
References 43 publications
2
23
0
Order By: Relevance
“…The algorithms of Zihlmann et al [26] and Xiong et al [24] were based on DNN, which is an end-to-end process without extracting hand-crafted features. Using only 30 features, our previous method [27] proposed in the Challenge achieved an overall F 1 score of 0.87 on AFDB-2017. In comparison with our previous method, the CatBoost model proposed in this work achieved an overall F 1 score of 0.91 on AFDB-2017, which increased by 0.04, while using less features.…”
Section: Discussionmentioning
confidence: 96%
See 3 more Smart Citations
“…The algorithms of Zihlmann et al [26] and Xiong et al [24] were based on DNN, which is an end-to-end process without extracting hand-crafted features. Using only 30 features, our previous method [27] proposed in the Challenge achieved an overall F 1 score of 0.87 on AFDB-2017. In comparison with our previous method, the CatBoost model proposed in this work achieved an overall F 1 score of 0.91 on AFDB-2017, which increased by 0.04, while using less features.…”
Section: Discussionmentioning
confidence: 96%
“…The system could provide instant feedback from the doctor. We also improved the performance of our previous AF classification method [27] proposed in the Challenge. A wearable ECG patch device was designed to collect single-lead ECG signals and to continuously send the collected ECG data to an Android smartphone via Bluetooth.…”
Section: Introductionmentioning
confidence: 94%
See 2 more Smart Citations
“…HRV features have been widely used in non-arrest situations to detect and predict cardiac arrhythmias [ 20 , 28 , 29 ]. They were originally designed to analyze long intervals, minutes, or even hours, in hemodynamically stable patients.…”
Section: Discussionmentioning
confidence: 99%