Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram Data
We introduce a deep-learning neural network model that uses electrocardiogram (ECG) data to predict coronary artery calcium scores, which can be useful for reliably detecting cardiovascular risk in patients. In our pre-processing method, each lead of the ECG is segmented into several waves with an i...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/23/8746 |
| _version_ | 1797545543283507200 |
|---|---|
| author | Changkyoung Eem Hyunki Hong Yoohun Noh |
| author_facet | Changkyoung Eem Hyunki Hong Yoohun Noh |
| author_sort | Changkyoung Eem |
| collection | DOAJ |
| description | We introduce a deep-learning neural network model that uses electrocardiogram (ECG) data to predict coronary artery calcium scores, which can be useful for reliably detecting cardiovascular risk in patients. In our pre-processing method, each lead of the ECG is segmented into several waves with an interval, which is determined as the period from the starting point of a P-wave to the end point of a T-wave. The number of segmented waves of one lead represents the number of heartbeats of the subject per 10 s. The segmented waves of one cycle are transformed into normalized waves with an amplitude of 0–1. Owing to the use of eight-lead ECG waves, the input ECG dataset has two dimensions. We used a convolutional neural network with 16 layers and 5 fully connected layers, comprising a one-dimensional filter to examine the normalized wave of one lead, rather than a two-dimensional filter to examine the coherence among the unit waves of eight leads. The training and testing are repeated 10 times with a randomly assigned dataset (177,547 ECGs). Our network model achieves an average area under the receiver operating characteristic curve of 0.801–0.890, and the average accuracy is in the range of 72.9–80.6%. |
| first_indexed | 2024-03-10T14:16:57Z |
| format | Article |
| id | doaj.art-cb911361c2294e9ca6502742c2ecdf28 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T14:16:57Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-cb911361c2294e9ca6502742c2ecdf282023-11-20T23:43:52ZengMDPI AGApplied Sciences2076-34172020-12-011023874610.3390/app10238746Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram DataChangkyoung Eem0Hyunki Hong1Yoohun Noh2College of Software, Chung-Ang University, Heukseok-ro 84, Dongjak-ku, Seoul 06973, KoreaCollege of Software, Chung-Ang University, Heukseok-ro 84, Dongjak-ku, Seoul 06973, KoreaFamenity Co., Ltd., D1009 Indeogwon IT Valley, 40, Imi-ro, Uiwang-si, Gyeonggi-do 16006, KoreaWe introduce a deep-learning neural network model that uses electrocardiogram (ECG) data to predict coronary artery calcium scores, which can be useful for reliably detecting cardiovascular risk in patients. In our pre-processing method, each lead of the ECG is segmented into several waves with an interval, which is determined as the period from the starting point of a P-wave to the end point of a T-wave. The number of segmented waves of one lead represents the number of heartbeats of the subject per 10 s. The segmented waves of one cycle are transformed into normalized waves with an amplitude of 0–1. Owing to the use of eight-lead ECG waves, the input ECG dataset has two dimensions. We used a convolutional neural network with 16 layers and 5 fully connected layers, comprising a one-dimensional filter to examine the normalized wave of one lead, rather than a two-dimensional filter to examine the coherence among the unit waves of eight leads. The training and testing are repeated 10 times with a randomly assigned dataset (177,547 ECGs). Our network model achieves an average area under the receiver operating characteristic curve of 0.801–0.890, and the average accuracy is in the range of 72.9–80.6%.https://www.mdpi.com/2076-3417/10/23/8746electrocardiogramcoronary artery calcium scoredeep-learning neural network modelcoronary artery disease |
| spellingShingle | Changkyoung Eem Hyunki Hong Yoohun Noh Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram Data Applied Sciences electrocardiogram coronary artery calcium score deep-learning neural network model coronary artery disease |
| title | Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram Data |
| title_full | Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram Data |
| title_fullStr | Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram Data |
| title_full_unstemmed | Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram Data |
| title_short | Deep-Learning Model to Predict Coronary Artery Calcium Scores in Humans from Electrocardiogram Data |
| title_sort | deep learning model to predict coronary artery calcium scores in humans from electrocardiogram data |
| topic | electrocardiogram coronary artery calcium score deep-learning neural network model coronary artery disease |
| url | https://www.mdpi.com/2076-3417/10/23/8746 |
| work_keys_str_mv | AT changkyoungeem deeplearningmodeltopredictcoronaryarterycalciumscoresinhumansfromelectrocardiogramdata AT hyunkihong deeplearningmodeltopredictcoronaryarterycalciumscoresinhumansfromelectrocardiogramdata AT yoohunnoh deeplearningmodeltopredictcoronaryarterycalciumscoresinhumansfromelectrocardiogramdata |