Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning
Cardiovascular diseases are the leading cause of death globally, highlighting the need for accurate diagnostic tools. To address this issue, we introduce a novel approach for arrhythmia detection based on electrocardiogram (ECG) that incorporates explainable artificial intelligence through three key...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7080/13/1/34 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587423649890304 |
|---|---|
| author | Oleksii Kovalchuk Oleksandr Barmak Pavlo Radiuk Liliana Klymenko Iurii Krak |
| author_facet | Oleksii Kovalchuk Oleksandr Barmak Pavlo Radiuk Liliana Klymenko Iurii Krak |
| author_sort | Oleksii Kovalchuk |
| collection | DOAJ |
| description | Cardiovascular diseases are the leading cause of death globally, highlighting the need for accurate diagnostic tools. To address this issue, we introduce a novel approach for arrhythmia detection based on electrocardiogram (ECG) that incorporates explainable artificial intelligence through three key methods. First, we developed an enhanced R peak detection method that integrates domain-specific knowledge into the ECG, improving peak identification accuracy by accounting for the characteristic features of R peaks. Second, we proposed an arrhythmia classification method utilizing a modified convolutional neural network (CNN) architecture with additional convolutional and batch normalization layers. This model processes a triad of cardio cycles—the preceding, current, and following cycles—to capture temporal dependencies and hidden features related to arrhythmias. Third, we implemented an interpretation method that explains CNN’s decisions using clinically relevant features, making the results understandable to clinicians. Using the MIT-BIH database, our approach achieved an accuracy of 99.43%, with F1-scores approaching 100% for major arrhythmia classes. The integration of these methods enhances both the performance and transparency of arrhythmia detection systems. |
| format | Article |
| id | doaj-art-5469f990b9924df4a7120411fb3fe66b |
| institution | Kabale University |
| issn | 2227-7080 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Technologies |
| spelling | doaj-art-5469f990b9924df4a7120411fb3fe66b2025-01-24T13:50:48ZengMDPI AGTechnologies2227-70802025-01-011313410.3390/technologies13010034Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep LearningOleksii Kovalchuk0Oleksandr Barmak1Pavlo Radiuk2Liliana Klymenko3Iurii Krak4Department of Computer Science, Khmelnytskyi National University, 11 Instytuts’ka Str., 29016 Khmelnytskyi, UkraineDepartment of Computer Science, Khmelnytskyi National University, 11 Instytuts’ka Str., 29016 Khmelnytskyi, UkraineDepartment of Computer Science, Khmelnytskyi National University, 11 Instytuts’ka Str., 29016 Khmelnytskyi, UkraineDepartment of Family Medicine and Outpatient Care, Shupyk National Healthcare University of Ukraine, 9 Dorohozhytska Str., 04112 Kyiv, UkraineDepartment of Theoretical Cybernetics, Taras Shevchenko National University of Kyiv, 4d Akademika Glushkova Ave, 03680 Kyiv, UkraineCardiovascular diseases are the leading cause of death globally, highlighting the need for accurate diagnostic tools. To address this issue, we introduce a novel approach for arrhythmia detection based on electrocardiogram (ECG) that incorporates explainable artificial intelligence through three key methods. First, we developed an enhanced R peak detection method that integrates domain-specific knowledge into the ECG, improving peak identification accuracy by accounting for the characteristic features of R peaks. Second, we proposed an arrhythmia classification method utilizing a modified convolutional neural network (CNN) architecture with additional convolutional and batch normalization layers. This model processes a triad of cardio cycles—the preceding, current, and following cycles—to capture temporal dependencies and hidden features related to arrhythmias. Third, we implemented an interpretation method that explains CNN’s decisions using clinically relevant features, making the results understandable to clinicians. Using the MIT-BIH database, our approach achieved an accuracy of 99.43%, with F1-scores approaching 100% for major arrhythmia classes. The integration of these methods enhances both the performance and transparency of arrhythmia detection systems.https://www.mdpi.com/2227-7080/13/1/34electrocardiography (ECG)arrhythmia detectionECG classificationECG interpretationexplainable artificial intelligence (XAI)transparent artificial intelligence |
| spellingShingle | Oleksii Kovalchuk Oleksandr Barmak Pavlo Radiuk Liliana Klymenko Iurii Krak Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning Technologies electrocardiography (ECG) arrhythmia detection ECG classification ECG interpretation explainable artificial intelligence (XAI) transparent artificial intelligence |
| title | Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning |
| title_full | Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning |
| title_fullStr | Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning |
| title_full_unstemmed | Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning |
| title_short | Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning |
| title_sort | towards transparent ai in medicine ecg based arrhythmia detection with explainable deep learning |
| topic | electrocardiography (ECG) arrhythmia detection ECG classification ECG interpretation explainable artificial intelligence (XAI) transparent artificial intelligence |
| url | https://www.mdpi.com/2227-7080/13/1/34 |
| work_keys_str_mv | AT oleksiikovalchuk towardstransparentaiinmedicineecgbasedarrhythmiadetectionwithexplainabledeeplearning AT oleksandrbarmak towardstransparentaiinmedicineecgbasedarrhythmiadetectionwithexplainabledeeplearning AT pavloradiuk towardstransparentaiinmedicineecgbasedarrhythmiadetectionwithexplainabledeeplearning AT lilianaklymenko towardstransparentaiinmedicineecgbasedarrhythmiadetectionwithexplainabledeeplearning AT iuriikrak towardstransparentaiinmedicineecgbasedarrhythmiadetectionwithexplainabledeeplearning |