Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics
The main objective of this study is to propose relatively simple techniques for the automatic diagnosis of electrocardiogram (ECG) signals based on a classical rule-based method and a convolutional deep learning architecture. The validation task was performed in the framework of the PhysioNet/Comput...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/9/1678 |
| _version_ | 1797519631892611072 |
|---|---|
| author | Giovanni Bortolan Ivaylo Christov Iana Simova |
| author_facet | Giovanni Bortolan Ivaylo Christov Iana Simova |
| author_sort | Giovanni Bortolan |
| collection | DOAJ |
| description | The main objective of this study is to propose relatively simple techniques for the automatic diagnosis of electrocardiogram (ECG) signals based on a classical rule-based method and a convolutional deep learning architecture. The validation task was performed in the framework of the PhysioNet/Computing in Cardiology Challenge 2020, where seven databases consisting of 66,361 recordings with 12-lead ECGs were considered for training, validation and test sets. A total of 24 different diagnostic classes are considered in the entire training set. The rule-based method uses morphological and time-frequency ECG descriptors that are defined for each diagnostic label. These rules are extracted from the knowledge base of a cardiologist or from a textbook, with no direct learning procedure in the first phase, whereas a refinement was tested in the second phase. The deep learning method considers both raw ECG and median beat signals. These data are processed via continuous wavelet transform analysis, obtaining a time-frequency domain representation, with the generation of specific images (ECG scalograms). These images are then used for the training of a convolutional neural network based on GoogLeNet topology for ECG diagnostic classification. Cross-validation evaluation was performed for testing purposes. A total of 217 teams submitted 1395 algorithms during the Challenge. The diagnostic accuracy of our algorithm produced a challenge validation score of 0.325 (CPU time = 35 min) for the rule-based method, and a 0.426 (CPU time = 1664 min) for the deep learning method, which resulted in our team attaining 12th place in the competition. |
| first_indexed | 2024-03-10T07:45:33Z |
| format | Article |
| id | doaj.art-7dfade246bb84feb8068f4124a54a652 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T07:45:33Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-7dfade246bb84feb8068f4124a54a6522023-11-22T12:40:44ZengMDPI AGDiagnostics2075-44182021-09-01119167810.3390/diagnostics11091678Potential of Rule-Based Methods and Deep Learning Architectures for ECG DiagnosticsGiovanni Bortolan0Ivaylo Christov1Iana Simova2Institute of Neuroscience IN-CNR, Corso Stati Uniti 4, 35127 Padova, ItalyInstitute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Acad. G. Bonchev Str. Bl 105, 1113 Sofia, BulgariaHeart and Brain Center of Excellence, University Hospital Pleven, Pierre Curie 2 Str, 5804 Pleven, BulgariaThe main objective of this study is to propose relatively simple techniques for the automatic diagnosis of electrocardiogram (ECG) signals based on a classical rule-based method and a convolutional deep learning architecture. The validation task was performed in the framework of the PhysioNet/Computing in Cardiology Challenge 2020, where seven databases consisting of 66,361 recordings with 12-lead ECGs were considered for training, validation and test sets. A total of 24 different diagnostic classes are considered in the entire training set. The rule-based method uses morphological and time-frequency ECG descriptors that are defined for each diagnostic label. These rules are extracted from the knowledge base of a cardiologist or from a textbook, with no direct learning procedure in the first phase, whereas a refinement was tested in the second phase. The deep learning method considers both raw ECG and median beat signals. These data are processed via continuous wavelet transform analysis, obtaining a time-frequency domain representation, with the generation of specific images (ECG scalograms). These images are then used for the training of a convolutional neural network based on GoogLeNet topology for ECG diagnostic classification. Cross-validation evaluation was performed for testing purposes. A total of 217 teams submitted 1395 algorithms during the Challenge. The diagnostic accuracy of our algorithm produced a challenge validation score of 0.325 (CPU time = 35 min) for the rule-based method, and a 0.426 (CPU time = 1664 min) for the deep learning method, which resulted in our team attaining 12th place in the competition.https://www.mdpi.com/2075-4418/11/9/1678ECGarrhythmiafeaturesrule-based methodconvolutional neural networkGoogLeNet network |
| spellingShingle | Giovanni Bortolan Ivaylo Christov Iana Simova Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics Diagnostics ECG arrhythmia features rule-based method convolutional neural network GoogLeNet network |
| title | Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics |
| title_full | Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics |
| title_fullStr | Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics |
| title_full_unstemmed | Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics |
| title_short | Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics |
| title_sort | potential of rule based methods and deep learning architectures for ecg diagnostics |
| topic | ECG arrhythmia features rule-based method convolutional neural network GoogLeNet network |
| url | https://www.mdpi.com/2075-4418/11/9/1678 |
| work_keys_str_mv | AT giovannibortolan potentialofrulebasedmethodsanddeeplearningarchitecturesforecgdiagnostics AT ivaylochristov potentialofrulebasedmethodsanddeeplearningarchitecturesforecgdiagnostics AT ianasimova potentialofrulebasedmethodsanddeeplearningarchitecturesforecgdiagnostics |