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...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-01-01
|
Series: | Computer Methods and Programs in Biomedicine Update |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S266699002300006X |
_version_ | 1797802728325382144 |
---|---|
author | Chen Chen Hai Yan Zhao Shou Huan Zheng Reshma A Ramachandra Xiaonan He Yin Hua Zhang Vidya K Sudarshan |
author_facet | Chen Chen Hai Yan Zhao Shou Huan Zheng Reshma A Ramachandra Xiaonan He Yin Hua Zhang Vidya K Sudarshan |
author_sort | Chen Chen |
collection | DOAJ |
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 | 2024-03-13T05:10:05Z |
format | Article |
id | doaj.art-9204c09952954f208091e581f520ef21 |
institution | Directory Open Access Journal |
issn | 2666-9900 |
language | English |
last_indexed | 2024-03-13T05:10:05Z |
publishDate | 2023-01-01 |
publisher | Elsevier |
record_format | Article |
series | Computer Methods and Programs in Biomedicine Update |
spelling | doaj.art-9204c09952954f208091e581f520ef212023-06-16T05:12:12ZengElsevierComputer Methods and Programs in Biomedicine Update2666-99002023-01-013100097Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signalsChen Chen0Hai Yan Zhao1Shou Huan Zheng2Reshma A Ramachandra3Xiaonan He4Yin Hua Zhang5Vidya K Sudarshan6Yanbian University Hospital, Yanji 133000, Jilin Province, ChinaYanbian University Hospital, Yanji 133000, Jilin Province, ChinaYanbian University Hospital, Yanji 133000, Jilin Province, ChinaGenMed Systems, SingaporeEmergency Critical Care Center, Anzhen Hospital, Capital Medical University, Beijing, ChinaYanbian University Hospital, Yanji 133000, Jilin Province, China; Department of Physiology & Biomedical Sciences, Ischemic/Hypoxic Disease Institutes, Seoul National University, College of Medicine, Jongno-Gu, Seoul, Republic of Korea; Corresponding author at: Yanbian University Hospital, Yanji 133000, Jilin Province, China.GenMed Systems, Singapore; School of Computer Science and Engineering, Nanyang Technological University, NTU, Singapore; Corresponding author at: School of Computer Science and Engineering, Nanyang Technological University, NTU, Singapore.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.http://www.sciencedirect.com/science/article/pii/S266699002300006XHypertensionDeep neural networkConvolutional neural networkSupport vector machineLIMEInterpretable AI |
spellingShingle | Chen Chen Hai Yan Zhao Shou Huan Zheng Reshma A Ramachandra Xiaonan He Yin Hua Zhang Vidya K Sudarshan Interpretable hybrid model for an automated patient-wise categorization of hypertensive and normotensive electrocardiogram signals Computer Methods and Programs in Biomedicine Update Hypertension Deep neural network Convolutional neural network Support vector machine LIME Interpretable AI |
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 | Hypertension Deep neural network Convolutional neural network Support vector machine LIME Interpretable AI |
url | http://www.sciencedirect.com/science/article/pii/S266699002300006X |
work_keys_str_mv | AT chenchen interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT haiyanzhao interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT shouhuanzheng interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT reshmaaramachandra interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT xiaonanhe interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT yinhuazhang interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals AT vidyaksudarshan interpretablehybridmodelforanautomatedpatientwisecategorizationofhypertensiveandnormotensiveelectrocardiogramsignals |