Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks
Electrocardiographic imaging (ECGi) reconstructs electrograms at the heart’s surface using the potentials recorded at the body’s surface. This is called the inverse problem of electrocardiography. This study aimed to improve on the current solution methods using machine learning and deep learning fr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/6/2331 |
| _version_ | 1797442296547901440 |
|---|---|
| author | Ke-Wei Chen Laura Bear Che-Wei Lin |
| author_facet | Ke-Wei Chen Laura Bear Che-Wei Lin |
| author_sort | Ke-Wei Chen |
| collection | DOAJ |
| description | Electrocardiographic imaging (ECGi) reconstructs electrograms at the heart’s surface using the potentials recorded at the body’s surface. This is called the inverse problem of electrocardiography. This study aimed to improve on the current solution methods using machine learning and deep learning frameworks. Electrocardiograms were simultaneously recorded from pigs’ ventricles and their body surfaces. The Fully Connected Neural network (FCN), Long Short-term Memory (LSTM), Convolutional Neural Network (CNN) methods were used for constructing the model. A method is developed to align the data across different pigs. We evaluated the method using leave-one-out cross-validation. For the best result, the overall median of the correlation coefficient of the predicted ECG wave was 0.74. This study demonstrated that a neural network can be used to solve the inverse problem of ECGi with relatively small datasets, with an accuracy compatible with current standard methods. |
| first_indexed | 2024-03-09T12:39:47Z |
| format | Article |
| id | doaj.art-552af64be1784dfdb8b679518d15e1ef |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:39:47Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-552af64be1784dfdb8b679518d15e1ef2023-11-30T22:19:31ZengMDPI AGSensors1424-82202022-03-01226233110.3390/s22062331Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning FrameworksKe-Wei Chen0Laura Bear1Che-Wei Lin2Department of BioMedical Engineering, National Cheng Kung University, Tainan City 70101, TaiwanElectrophysiology and Heart Modelling Institute (IHU-LIRYC), Fondation Bordeaux Université, 33000 Bordeaux, FranceDepartment of BioMedical Engineering, National Cheng Kung University, Tainan City 70101, TaiwanElectrocardiographic imaging (ECGi) reconstructs electrograms at the heart’s surface using the potentials recorded at the body’s surface. This is called the inverse problem of electrocardiography. This study aimed to improve on the current solution methods using machine learning and deep learning frameworks. Electrocardiograms were simultaneously recorded from pigs’ ventricles and their body surfaces. The Fully Connected Neural network (FCN), Long Short-term Memory (LSTM), Convolutional Neural Network (CNN) methods were used for constructing the model. A method is developed to align the data across different pigs. We evaluated the method using leave-one-out cross-validation. For the best result, the overall median of the correlation coefficient of the predicted ECG wave was 0.74. This study demonstrated that a neural network can be used to solve the inverse problem of ECGi with relatively small datasets, with an accuracy compatible with current standard methods.https://www.mdpi.com/1424-8220/22/6/2331electrocardiographic imaging (ECGi)deep learningmachine learninginverse problemFully Connected Neural network (FCN)Long Short-term Memory (LSTM) |
| spellingShingle | Ke-Wei Chen Laura Bear Che-Wei Lin Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks Sensors electrocardiographic imaging (ECGi) deep learning machine learning inverse problem Fully Connected Neural network (FCN) Long Short-term Memory (LSTM) |
| title | Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks |
| title_full | Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks |
| title_fullStr | Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks |
| title_full_unstemmed | Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks |
| title_short | Solving Inverse Electrocardiographic Mapping Using Machine Learning and Deep Learning Frameworks |
| title_sort | solving inverse electrocardiographic mapping using machine learning and deep learning frameworks |
| topic | electrocardiographic imaging (ECGi) deep learning machine learning inverse problem Fully Connected Neural network (FCN) Long Short-term Memory (LSTM) |
| url | https://www.mdpi.com/1424-8220/22/6/2331 |
| work_keys_str_mv | AT keweichen solvinginverseelectrocardiographicmappingusingmachinelearninganddeeplearningframeworks AT laurabear solvinginverseelectrocardiographicmappingusingmachinelearninganddeeplearningframeworks AT cheweilin solvinginverseelectrocardiographicmappingusingmachinelearninganddeeplearningframeworks |