Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals
Background and Objective: Hypertension is critical risk factor of fatal cardiovascular diseases and multiple organ damage. Early detection of hypertension even at pre-hypertension stage is helpful in preventing the forthcoming complications. Electrocardiogram (ECG) has been attempted to observe the...
| Hauptverfasser: | , , , , , , |
|---|---|
| Weitere Verfasser: | |
| Format: | Journal Article |
| Sprache: | English |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online Zugang: | https://hdl.handle.net/10356/170019 |
| _version_ | 1826123534763556864 |
|---|---|
| author | Chen, Chen Zhao, Hai Yan Zheng, Shou Huan Ramachandra, Reshma A. He, Xiaonan Zhang, Yin Hua Sudarshan, Vidya K. |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Chen, Chen Zhao, Hai Yan Zheng, Shou Huan Ramachandra, Reshma A. He, Xiaonan Zhang, Yin Hua Sudarshan, Vidya K. |
| author_sort | Chen, Chen |
| collection | NTU |
| description | Background and Objective: Hypertension is critical risk factor of fatal cardiovascular diseases and multiple organ damage. Early detection of hypertension even at pre-hypertension stage is helpful in preventing the forthcoming complications. Electrocardiogram (ECG) has been attempted to observe the changes in electrical activities of the hearts of hypertensive patients. To automate the ECG assessment in the detection of hypertension, an interpretable hybrid model is proposed in this paper. Methods: The proposed hybrid framework consists of one dimensional - Convolutional Neural Network architecture with four blocks of convolutional layers, maxpooling followed by dropout layers fused with Support Vector Machine classifier in the final layer. The implemented hybrid model is made explainable and interpretable using Local Interpretable Model-agnostic Explanations (LIME) method. The developed hybrid model is trained and tested for patient-wise classification of ECGs using online Physionet datasets and hospital data. Results: The proposed method achieved highest accuracy of 81.81% in patient-wise ECG classification of online datasets, and highest accuracy of 93.33% in patient-wise ECG classification of hospital datasets as normotensive and hypertensive. The visualization of results showed only one normotensive patient's ECG is misclassified (predicted) as hypertensive, with identification of patient number, among the 15 patients (8 normotensive and 7 hypertensive) ECGs tested. In addition, the LIME results demonstrated an explanation to the predictions of hybrid model by highlighting the features and location of ECG waveform responsible for it, thus making the decision of hybrid model more interpretable. Conclusion: Furthermore, our developed system is implemented as an assisting automated software tool called, HANDI (Hypertensive And Normotensive patient Detection with Interpretability) for real-time validation in clinics for early capture of hypertensive and proper monitoring of the patients. |
| first_indexed | 2024-10-01T06:06:14Z |
| format | Journal Article |
| id | ntu-10356/170019 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:06:14Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1700192023-08-25T15:35:48Z Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals Chen, Chen Zhao, Hai Yan Zheng, Shou Huan Ramachandra, Reshma A. He, Xiaonan Zhang, Yin Hua Sudarshan, Vidya K. School of Computer Science and Engineering Engineering::Computer science and engineering Hypertension Deep Neural Network Background and Objective: Hypertension is critical risk factor of fatal cardiovascular diseases and multiple organ damage. Early detection of hypertension even at pre-hypertension stage is helpful in preventing the forthcoming complications. Electrocardiogram (ECG) has been attempted to observe the changes in electrical activities of the hearts of hypertensive patients. To automate the ECG assessment in the detection of hypertension, an interpretable hybrid model is proposed in this paper. Methods: The proposed hybrid framework consists of one dimensional - Convolutional Neural Network architecture with four blocks of convolutional layers, maxpooling followed by dropout layers fused with Support Vector Machine classifier in the final layer. The implemented hybrid model is made explainable and interpretable using Local Interpretable Model-agnostic Explanations (LIME) method. The developed hybrid model is trained and tested for patient-wise classification of ECGs using online Physionet datasets and hospital data. Results: The proposed method achieved highest accuracy of 81.81% in patient-wise ECG classification of online datasets, and highest accuracy of 93.33% in patient-wise ECG classification of hospital datasets as normotensive and hypertensive. The visualization of results showed only one normotensive patient's ECG is misclassified (predicted) as hypertensive, with identification of patient number, among the 15 patients (8 normotensive and 7 hypertensive) ECGs tested. In addition, the LIME results demonstrated an explanation to the predictions of hybrid model by highlighting the features and location of ECG waveform responsible for it, thus making the decision of hybrid model more interpretable. Conclusion: Furthermore, our developed system is implemented as an assisting automated software tool called, HANDI (Hypertensive And Normotensive patient Detection with Interpretability) for real-time validation in clinics for early capture of hypertensive and proper monitoring of the patients. Published version This work is supported by National Natural Science Foundation of China (NSFC 31660284, NSFC31860288), Korean National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2019R1A2C1005720), Korean Hypertension Society (2021). 2023-08-22T01:15:35Z 2023-08-22T01:15:35Z 2023 Journal Article Chen, C., Zhao, H. Y., Zheng, S. H., Ramachandra, R. A., He, X., Zhang, Y. H. & Sudarshan, V. K. (2023). Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals. Computer Methods and Programs in Biomedicine Update, 3, 100097-. https://dx.doi.org/10.1016/j.cmpbup.2023.100097 2666-9900 https://hdl.handle.net/10356/170019 10.1016/j.cmpbup.2023.100097 2-s2.0-85161595567 3 100097 en Computer Methods and Programs in Biomedicine Update © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/bync-nd/4.0/). application/pdf |
| spellingShingle | Engineering::Computer science and engineering Hypertension Deep Neural Network Chen, Chen Zhao, Hai Yan Zheng, Shou Huan Ramachandra, Reshma A. He, Xiaonan Zhang, Yin Hua Sudarshan, Vidya K. Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals |
| title | Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals |
| title_full | Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals |
| title_fullStr | Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals |
| title_full_unstemmed | Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals |
| title_short | Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals |
| title_sort | interpretable hybrid model for an automated patient wise categorization of hypertensive and normotensive electrocardiogram signals |
| topic | Engineering::Computer science and engineering Hypertension Deep Neural Network |
| url | https://hdl.handle.net/10356/170019 |
| work_keys_str_mv | AT chenchen interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT zhaohaiyan interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT zhengshouhuan interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT ramachandrareshmaa interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT hexiaonan interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT zhangyinhua interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT sudarshanvidyak interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals |