Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG Waveforms
Objective: The early detection of cardiac disease is important because the disease can lead to sudden death and poor prognosis. Electrocardiograms (ECG) are used to screen for cardiac diseases and are useful for the early detection and determination of treatment strategies. However, the ECG waveform...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10056148/ |
| _version_ | 1827997858020720640 |
|---|---|
| author | Terumasa Kondo Atsushi Teramoto Eiichi Watanabe Yoshihiro Sobue Hideo Izawa Kuniaki Saito Hiroshi Fujita |
| author_facet | Terumasa Kondo Atsushi Teramoto Eiichi Watanabe Yoshihiro Sobue Hideo Izawa Kuniaki Saito Hiroshi Fujita |
| author_sort | Terumasa Kondo |
| collection | DOAJ |
| description | Objective: The early detection of cardiac disease is important because the disease can lead to sudden death and poor prognosis. Electrocardiograms (ECG) are used to screen for cardiac diseases and are useful for the early detection and determination of treatment strategies. However, the ECG waveforms of cardiac care unit (CCU) patients with severe cardiac disease are often complicated by comorbidities and patient conditions, making it difficult to predict the severity of further cardiac disease. Therefore, this study predicts the short-term prognosis of CCU patients to detect further deterioration in CCU patients at an early stage. Methods: The ECG data (II, V3, V5, aVR induction) of CCU patients were converted to image data. The transformed ECG images were used to predict short-term prognosis with a two-dimensional convolutional neural network (CNN). Results: The prediction accuracy was 77.3%. Visualization by GradCAM showed that the CNN tended to focus on the shape and regularity of waveforms, such as heart failure and myocardial infarction. Conclusion: These results suggest that the proposed method may be useful for short-term prognosis prediction using the ECG waveforms of CCU patients. Clinical impact: The proposed method could be used to determine the treatment strategy and choose the intensity of treatment after admission to the CCU. |
| first_indexed | 2024-04-10T05:35:28Z |
| format | Article |
| id | doaj.art-4aef041e4e19491aa499fc7aec2d970f |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-04-10T05:35:28Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-4aef041e4e19491aa499fc7aec2d970f2023-03-07T00:00:14ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722023-01-011119119810.1109/JTEHM.2023.325035210056148Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG WaveformsTerumasa Kondo0https://orcid.org/0009-0004-6697-055XAtsushi Teramoto1https://orcid.org/0000-0001-7613-5348Eiichi Watanabe2https://orcid.org/0000-0002-2375-2323Yoshihiro Sobue3Hideo Izawa4Kuniaki Saito5Hiroshi Fujita6https://orcid.org/0000-0002-2936-9296Graduate School of Health Sciences, Fujita Health University, Aichi, JapanGraduate School of Health Sciences, Fujita Health University, Aichi, JapanDepartment of Internal Medicine, Division of Cardiology, Fujita Health University Bantane Hospital, Aichi, JapanDepartment of Internal Medicine, Division of Cardiology, Fujita Health University Bantane Hospital, Aichi, JapanDepartment of Cardiology, School of Medicine, Fujita Health University, Aichi, JapanGraduate School of Health Sciences, Fujita Health University, Aichi, JapanFaculty of Engineering, Gifu University, Gifu, JapanObjective: The early detection of cardiac disease is important because the disease can lead to sudden death and poor prognosis. Electrocardiograms (ECG) are used to screen for cardiac diseases and are useful for the early detection and determination of treatment strategies. However, the ECG waveforms of cardiac care unit (CCU) patients with severe cardiac disease are often complicated by comorbidities and patient conditions, making it difficult to predict the severity of further cardiac disease. Therefore, this study predicts the short-term prognosis of CCU patients to detect further deterioration in CCU patients at an early stage. Methods: The ECG data (II, V3, V5, aVR induction) of CCU patients were converted to image data. The transformed ECG images were used to predict short-term prognosis with a two-dimensional convolutional neural network (CNN). Results: The prediction accuracy was 77.3%. Visualization by GradCAM showed that the CNN tended to focus on the shape and regularity of waveforms, such as heart failure and myocardial infarction. Conclusion: These results suggest that the proposed method may be useful for short-term prognosis prediction using the ECG waveforms of CCU patients. Clinical impact: The proposed method could be used to determine the treatment strategy and choose the intensity of treatment after admission to the CCU.https://ieeexplore.ieee.org/document/10056148/Deep learningelectrocardiogramGradCAMmortality prediction |
| spellingShingle | Terumasa Kondo Atsushi Teramoto Eiichi Watanabe Yoshihiro Sobue Hideo Izawa Kuniaki Saito Hiroshi Fujita Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG Waveforms IEEE Journal of Translational Engineering in Health and Medicine Deep learning electrocardiogram GradCAM mortality prediction |
| title | Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG Waveforms |
| title_full | Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG Waveforms |
| title_fullStr | Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG Waveforms |
| title_full_unstemmed | Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG Waveforms |
| title_short | Prediction of Short-Term Mortality of Cardiac Care Unit Patients Using Image-Transformed ECG Waveforms |
| title_sort | prediction of short term mortality of cardiac care unit patients using image transformed ecg waveforms |
| topic | Deep learning electrocardiogram GradCAM mortality prediction |
| url | https://ieeexplore.ieee.org/document/10056148/ |
| work_keys_str_mv | AT terumasakondo predictionofshorttermmortalityofcardiaccareunitpatientsusingimagetransformedecgwaveforms AT atsushiteramoto predictionofshorttermmortalityofcardiaccareunitpatientsusingimagetransformedecgwaveforms AT eiichiwatanabe predictionofshorttermmortalityofcardiaccareunitpatientsusingimagetransformedecgwaveforms AT yoshihirosobue predictionofshorttermmortalityofcardiaccareunitpatientsusingimagetransformedecgwaveforms AT hideoizawa predictionofshorttermmortalityofcardiaccareunitpatientsusingimagetransformedecgwaveforms AT kuniakisaito predictionofshorttermmortalityofcardiaccareunitpatientsusingimagetransformedecgwaveforms AT hiroshifujita predictionofshorttermmortalityofcardiaccareunitpatientsusingimagetransformedecgwaveforms |