Subject-Independent per Beat PPG to Single-Lead ECG Mapping
In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a single-lead electrocardiogram (single-lead ECG) signal. The main limiting factors represented in uncleaned data, subject dependency, and erroneous beat segmentation are regarded. The dataset is cleaned by...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/7/377 |
| _version_ | 1797588902643499008 |
|---|---|
| author | Khaled M. Abdelgaber Mostafa Salah Osama A. Omer Ahmed E. A. Farghal Ahmed S. Mubarak |
| author_facet | Khaled M. Abdelgaber Mostafa Salah Osama A. Omer Ahmed E. A. Farghal Ahmed S. Mubarak |
| author_sort | Khaled M. Abdelgaber |
| collection | DOAJ |
| description | In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a single-lead electrocardiogram (single-lead ECG) signal. The main limiting factors represented in uncleaned data, subject dependency, and erroneous beat segmentation are regarded. The dataset is cleaned by a two-stage clustering approach. Rather than complete single–lead ECG signal reconstruction, a beat-based PPG-to-single-lead-ECG (PPG2ECG) conversion is introduced for providing a simple lightweight model that meets the computational capabilities of wearable devices. In addition, peak-to-peak segmentation is employed for alleviating errors in PPG onset detection. Furthermore, subject-dependent training is highlighted as a critical factor in training procedures because most existing work includes different beats/signals from the same subject’s record in both training and testing sets. So, we provide a completely subject-independent model where the testing subjects’ records are hidden in the training stage entirely, i.e., a subject record appears once either in the training or testing set, but testing beats/signals belong to records that never appear in the training set. The proposed deep learning model is designed for providing efficient feature extraction that attains high reconstruction quality over subject-independent scenarios. The achieved performance is about 0.92 for the correlation coefficient and 0.0086 for the mean square error for the dataset extracted/cleaned from the MIMIC II dataset. |
| first_indexed | 2024-03-11T00:58:38Z |
| format | Article |
| id | doaj.art-56553ef8254947c7ac79a6c7e472fcf4 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T00:58:38Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-56553ef8254947c7ac79a6c7e472fcf42023-11-18T19:46:46ZengMDPI AGInformation2078-24892023-07-0114737710.3390/info14070377Subject-Independent per Beat PPG to Single-Lead ECG MappingKhaled M. Abdelgaber0Mostafa Salah1Osama A. Omer2Ahmed E. A. Farghal3Ahmed S. Mubarak4Department of Electrical Engineering, Faculty of Engineering, Sohag University, Sohag 82524, EgyptDepartment of Electrical Engineering, Faculty of Engineering, Sohag University, Sohag 82524, EgyptDepartment of Electrical Engineering, Faculty of Engineering, Aswan University, Aswan 81542, EgyptDepartment of Electrical Engineering, Faculty of Engineering, Sohag University, Sohag 82524, EgyptDepartment of Electrical Engineering, Faculty of Engineering, Aswan University, Aswan 81542, EgyptIn this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a single-lead electrocardiogram (single-lead ECG) signal. The main limiting factors represented in uncleaned data, subject dependency, and erroneous beat segmentation are regarded. The dataset is cleaned by a two-stage clustering approach. Rather than complete single–lead ECG signal reconstruction, a beat-based PPG-to-single-lead-ECG (PPG2ECG) conversion is introduced for providing a simple lightweight model that meets the computational capabilities of wearable devices. In addition, peak-to-peak segmentation is employed for alleviating errors in PPG onset detection. Furthermore, subject-dependent training is highlighted as a critical factor in training procedures because most existing work includes different beats/signals from the same subject’s record in both training and testing sets. So, we provide a completely subject-independent model where the testing subjects’ records are hidden in the training stage entirely, i.e., a subject record appears once either in the training or testing set, but testing beats/signals belong to records that never appear in the training set. The proposed deep learning model is designed for providing efficient feature extraction that attains high reconstruction quality over subject-independent scenarios. The achieved performance is about 0.92 for the correlation coefficient and 0.0086 for the mean square error for the dataset extracted/cleaned from the MIMIC II dataset.https://www.mdpi.com/2078-2489/14/7/377photoplethysmographyelectrocardiogramECG reconstructionbiomedical wearable devices |
| spellingShingle | Khaled M. Abdelgaber Mostafa Salah Osama A. Omer Ahmed E. A. Farghal Ahmed S. Mubarak Subject-Independent per Beat PPG to Single-Lead ECG Mapping Information photoplethysmography electrocardiogram ECG reconstruction biomedical wearable devices |
| title | Subject-Independent per Beat PPG to Single-Lead ECG Mapping |
| title_full | Subject-Independent per Beat PPG to Single-Lead ECG Mapping |
| title_fullStr | Subject-Independent per Beat PPG to Single-Lead ECG Mapping |
| title_full_unstemmed | Subject-Independent per Beat PPG to Single-Lead ECG Mapping |
| title_short | Subject-Independent per Beat PPG to Single-Lead ECG Mapping |
| title_sort | subject independent per beat ppg to single lead ecg mapping |
| topic | photoplethysmography electrocardiogram ECG reconstruction biomedical wearable devices |
| url | https://www.mdpi.com/2078-2489/14/7/377 |
| work_keys_str_mv | AT khaledmabdelgaber subjectindependentperbeatppgtosingleleadecgmapping AT mostafasalah subjectindependentperbeatppgtosingleleadecgmapping AT osamaaomer subjectindependentperbeatppgtosingleleadecgmapping AT ahmedeafarghal subjectindependentperbeatppgtosingleleadecgmapping AT ahmedsmubarak subjectindependentperbeatppgtosingleleadecgmapping |