Congestive heart failure waveform classification based on short time-step analysis with recurrent network
Congestive heart failure (CHF) is characterized by the heart's inability to pump blood adequately throughout the body without increased intracardiac pressure. Diverse approaches are used to treat CHF. These approaches, which include physical examination, echocardiography, and laboratory testing...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914820305918 |
| _version_ | 1818844747412799488 |
|---|---|
| author | Annisa Darmawahyuni Siti Nurmaini Meiryka Yuwandini Muhammad Naufal Rachmatullah Firdaus Firdaus Bambang Tutuko |
| author_facet | Annisa Darmawahyuni Siti Nurmaini Meiryka Yuwandini Muhammad Naufal Rachmatullah Firdaus Firdaus Bambang Tutuko |
| author_sort | Annisa Darmawahyuni |
| collection | DOAJ |
| description | Congestive heart failure (CHF) is characterized by the heart's inability to pump blood adequately throughout the body without increased intracardiac pressure. Diverse approaches are used to treat CHF. These approaches, which include physical examination, echocardiography, and laboratory testing, require a high degree of competence to interpret findings and make diagnoses. Moreover, existing methods do not account for the relationships between variables and thus provide limited performance. Electrocardiogram (ECG), as a non-invasive test, may be used for CHF early diagnosis, which would require further examination to be referred. A previous study revealed a significant correlation between heart failure (HF) and ECG features. However, the method was only performed on small, balanced data; then, the features must be derived from trial and error. The current paper proposes deep-learning techniques—recurrent neural networks (RNNs) with long short-term memory (LSTM) architectures—to create a diagnostic algorithm that achieves high accuracy with limited information and automated feature extraction. The ECG signals used in this study were obtained from the public PhysioNet databases. We fine-tuned the hyperparameters of 24 LSTM models to obtain the best model. Moreover, ECG signal segmentation was compared among the first five and fifteen minutes as features. Out of the 24 LSTM models, the model with the first fifteen minutes of ECG signals (model 1) obtained the highest accuracy, sensitivity, specificity, precision, and F1-score (99.86%, 99.85%, 99.85%, 99.87%, and 99.86%, respectively). The first fifteen minutes of ECG signals performed well because the LSTM model learned an increasing number of features. In conclusion, the proposed LSTM model could give a clinician a preliminary CHF diagnosis for further medical attention. Deep learning can be a useful predictive method for increasing the number of identified CHF patients. |
| first_indexed | 2024-12-19T05:18:41Z |
| format | Article |
| id | doaj.art-688cbf5035cb4855811d318601f3e5bd |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-12-19T05:18:41Z |
| publishDate | 2020-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-688cbf5035cb4855811d318601f3e5bd2022-12-21T20:34:34ZengElsevierInformatics in Medicine Unlocked2352-91482020-01-0121100441Congestive heart failure waveform classification based on short time-step analysis with recurrent networkAnnisa Darmawahyuni0Siti Nurmaini1Meiryka Yuwandini2 Muhammad Naufal Rachmatullah3Firdaus Firdaus4Bambang Tutuko5Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, IndonesiaCorresponding author. Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, Indonesia.; Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, IndonesiaCongestive heart failure (CHF) is characterized by the heart's inability to pump blood adequately throughout the body without increased intracardiac pressure. Diverse approaches are used to treat CHF. These approaches, which include physical examination, echocardiography, and laboratory testing, require a high degree of competence to interpret findings and make diagnoses. Moreover, existing methods do not account for the relationships between variables and thus provide limited performance. Electrocardiogram (ECG), as a non-invasive test, may be used for CHF early diagnosis, which would require further examination to be referred. A previous study revealed a significant correlation between heart failure (HF) and ECG features. However, the method was only performed on small, balanced data; then, the features must be derived from trial and error. The current paper proposes deep-learning techniques—recurrent neural networks (RNNs) with long short-term memory (LSTM) architectures—to create a diagnostic algorithm that achieves high accuracy with limited information and automated feature extraction. The ECG signals used in this study were obtained from the public PhysioNet databases. We fine-tuned the hyperparameters of 24 LSTM models to obtain the best model. Moreover, ECG signal segmentation was compared among the first five and fifteen minutes as features. Out of the 24 LSTM models, the model with the first fifteen minutes of ECG signals (model 1) obtained the highest accuracy, sensitivity, specificity, precision, and F1-score (99.86%, 99.85%, 99.85%, 99.87%, and 99.86%, respectively). The first fifteen minutes of ECG signals performed well because the LSTM model learned an increasing number of features. In conclusion, the proposed LSTM model could give a clinician a preliminary CHF diagnosis for further medical attention. Deep learning can be a useful predictive method for increasing the number of identified CHF patients.http://www.sciencedirect.com/science/article/pii/S2352914820305918Congestive heart failureNormal sinus rhythmRecurrent neural networksLong short-term memory |
| spellingShingle | Annisa Darmawahyuni Siti Nurmaini Meiryka Yuwandini Muhammad Naufal Rachmatullah Firdaus Firdaus Bambang Tutuko Congestive heart failure waveform classification based on short time-step analysis with recurrent network Informatics in Medicine Unlocked Congestive heart failure Normal sinus rhythm Recurrent neural networks Long short-term memory |
| title | Congestive heart failure waveform classification based on short time-step analysis with recurrent network |
| title_full | Congestive heart failure waveform classification based on short time-step analysis with recurrent network |
| title_fullStr | Congestive heart failure waveform classification based on short time-step analysis with recurrent network |
| title_full_unstemmed | Congestive heart failure waveform classification based on short time-step analysis with recurrent network |
| title_short | Congestive heart failure waveform classification based on short time-step analysis with recurrent network |
| title_sort | congestive heart failure waveform classification based on short time step analysis with recurrent network |
| topic | Congestive heart failure Normal sinus rhythm Recurrent neural networks Long short-term memory |
| url | http://www.sciencedirect.com/science/article/pii/S2352914820305918 |
| work_keys_str_mv | AT annisadarmawahyuni congestiveheartfailurewaveformclassificationbasedonshorttimestepanalysiswithrecurrentnetwork AT sitinurmaini congestiveheartfailurewaveformclassificationbasedonshorttimestepanalysiswithrecurrentnetwork AT meirykayuwandini congestiveheartfailurewaveformclassificationbasedonshorttimestepanalysiswithrecurrentnetwork AT muhammadnaufalrachmatullah congestiveheartfailurewaveformclassificationbasedonshorttimestepanalysiswithrecurrentnetwork AT firdausfirdaus congestiveheartfailurewaveformclassificationbasedonshorttimestepanalysiswithrecurrentnetwork AT bambangtutuko congestiveheartfailurewaveformclassificationbasedonshorttimestepanalysiswithrecurrentnetwork |