Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography
In this study, we present a non-invasive solution to identify patients with coronary artery disease (CAD) defined as ⩾50% stenosis in at least one coronary artery. The solution is based on the analysis of linear acceleration (seismocardiogram, SCG) and angular velocity (gyrocardiogram, GCG) of the h...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-12-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2021.758727/full |
| _version_ | 1818401133525204992 |
|---|---|
| author | Parastoo Dehkordi Erwin P. Bauer Kouhyar Tavakolian Kouhyar Tavakolian Zhen G. Xiao Andrew P. Blaber Farzad Khosrow-Khavar |
| author_facet | Parastoo Dehkordi Erwin P. Bauer Kouhyar Tavakolian Kouhyar Tavakolian Zhen G. Xiao Andrew P. Blaber Farzad Khosrow-Khavar |
| author_sort | Parastoo Dehkordi |
| collection | DOAJ |
| description | In this study, we present a non-invasive solution to identify patients with coronary artery disease (CAD) defined as ⩾50% stenosis in at least one coronary artery. The solution is based on the analysis of linear acceleration (seismocardiogram, SCG) and angular velocity (gyrocardiogram, GCG) of the heart recorded in the x, y, and z directional axes from an accelerometer/gyroscope sensor mounted on the sternum. The database was collected from 310 individuals through a multicenter study. The time-frequency features extracted from each SCG and GCG data channel were fed to a one-dimensional Convolutional Neural Network (1D CNN) to train six separate classifiers. The results from different classifiers were later fused to estimate the CAD risk for each participant. The predicted CAD risk was validated against related results from angiography. The SCG z and SCG y classifiers showed better performance relative to the other models (p < 0.05) with the area under the curve (AUC) of 91%. The sensitivity range for CAD detection was 92–94% for the SCG models and 73–87% for the GCG models. Based on our findings, the SCG models achieved better performance in predicting the CAD risk compared to the GCG models; the model based on the combination of all SCG and GCG classifiers did not achieve higher performance relative to the other models. Moreover, these findings showed that the performance of the proposed 3-axial SCG/GCG solution based on recordings obtained during rest was comparable, or better than stress ECG. These data may indicate that 3-axial SCG/GCG could be used as a portable at-home CAD screening tool. |
| first_indexed | 2024-12-14T07:47:37Z |
| format | Article |
| id | doaj.art-495f35068fd64be0beee717123307109 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-12-14T07:47:37Z |
| publishDate | 2021-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-495f35068fd64be0beee7171233071092022-12-21T23:10:50ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2021-12-011210.3389/fphys.2021.758727758727Detecting Coronary Artery Disease Using Rest Seismocardiography and GyrocardiographyParastoo Dehkordi0Erwin P. Bauer1Kouhyar Tavakolian2Kouhyar Tavakolian3Zhen G. Xiao4Andrew P. Blaber5Farzad Khosrow-Khavar6Heart Force Medical Inc., Vancouver, BC, CanadaHeart Force Medical Inc., Vancouver, BC, CanadaSchool of Electrical Engineering and Computer Science, University of North Dakota, Grand Forks, ND, United StatesBiomedical Physiology and Kinesiology Department, Simon Fraser University, Vancouver, BC, CanadaHeart Force Medical Inc., Vancouver, BC, CanadaBiomedical Physiology and Kinesiology Department, Simon Fraser University, Vancouver, BC, CanadaHeart Force Medical Inc., Vancouver, BC, CanadaIn this study, we present a non-invasive solution to identify patients with coronary artery disease (CAD) defined as ⩾50% stenosis in at least one coronary artery. The solution is based on the analysis of linear acceleration (seismocardiogram, SCG) and angular velocity (gyrocardiogram, GCG) of the heart recorded in the x, y, and z directional axes from an accelerometer/gyroscope sensor mounted on the sternum. The database was collected from 310 individuals through a multicenter study. The time-frequency features extracted from each SCG and GCG data channel were fed to a one-dimensional Convolutional Neural Network (1D CNN) to train six separate classifiers. The results from different classifiers were later fused to estimate the CAD risk for each participant. The predicted CAD risk was validated against related results from angiography. The SCG z and SCG y classifiers showed better performance relative to the other models (p < 0.05) with the area under the curve (AUC) of 91%. The sensitivity range for CAD detection was 92–94% for the SCG models and 73–87% for the GCG models. Based on our findings, the SCG models achieved better performance in predicting the CAD risk compared to the GCG models; the model based on the combination of all SCG and GCG classifiers did not achieve higher performance relative to the other models. Moreover, these findings showed that the performance of the proposed 3-axial SCG/GCG solution based on recordings obtained during rest was comparable, or better than stress ECG. These data may indicate that 3-axial SCG/GCG could be used as a portable at-home CAD screening tool.https://www.frontiersin.org/articles/10.3389/fphys.2021.758727/fullseismocardiographygyrocardiographycoronary artery disease (CAD)cardiac mechanical activityangiography |
| spellingShingle | Parastoo Dehkordi Erwin P. Bauer Kouhyar Tavakolian Kouhyar Tavakolian Zhen G. Xiao Andrew P. Blaber Farzad Khosrow-Khavar Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography Frontiers in Physiology seismocardiography gyrocardiography coronary artery disease (CAD) cardiac mechanical activity angiography |
| title | Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography |
| title_full | Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography |
| title_fullStr | Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography |
| title_full_unstemmed | Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography |
| title_short | Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography |
| title_sort | detecting coronary artery disease using rest seismocardiography and gyrocardiography |
| topic | seismocardiography gyrocardiography coronary artery disease (CAD) cardiac mechanical activity angiography |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2021.758727/full |
| work_keys_str_mv | AT parastoodehkordi detectingcoronaryarterydiseaseusingrestseismocardiographyandgyrocardiography AT erwinpbauer detectingcoronaryarterydiseaseusingrestseismocardiographyandgyrocardiography AT kouhyartavakolian detectingcoronaryarterydiseaseusingrestseismocardiographyandgyrocardiography AT kouhyartavakolian detectingcoronaryarterydiseaseusingrestseismocardiographyandgyrocardiography AT zhengxiao detectingcoronaryarterydiseaseusingrestseismocardiographyandgyrocardiography AT andrewpblaber detectingcoronaryarterydiseaseusingrestseismocardiographyandgyrocardiography AT farzadkhosrowkhavar detectingcoronaryarterydiseaseusingrestseismocardiographyandgyrocardiography |