Real‐time photoplethysmographic heart rate measurement using deep neural network filters
AbstractPhotoplethysmography (PPG) is a noninvasive technique that can be used to conveniently measure heart rate (HR) and thus obtain relevant health‐related information. However, developing an automated PPG system is difficult, because its waveforms are susceptible to motion artifacts and between‐...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronics and Telecommunications Research Institute (ETRI)
2021-10-01
|
| Series: | ETRI Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.4218/etrij.2020-0394 |
| _version_ | 1831811422630182912 |
|---|---|
| author | Ji Woon Kim Sung Min Park Seong Wook Choi |
| author_facet | Ji Woon Kim Sung Min Park Seong Wook Choi |
| author_sort | Ji Woon Kim |
| collection | DOAJ |
| description | AbstractPhotoplethysmography (PPG) is a noninvasive technique that can be used to conveniently measure heart rate (HR) and thus obtain relevant health‐related information. However, developing an automated PPG system is difficult, because its waveforms are susceptible to motion artifacts and between‐patient variation, making its interpretation difficult. We use deep neural network (DNN) filters to mimic the cognitive ability of a human expert who can distinguish the features of PPG altered by noise from various sources. Systolic (S), onset (O), and first derivative peaks (W) are recognized by three different DNN filters. In addition, the boundaries of uninformative regions caused by artifacts are identified by two different filters. The algorithm reliably derives the HR and presents recognition scores for the S, O, and W peaks and artifacts with only a 0.7‐s delay. In the evaluation using data from 11 patients obtained from PhysioNet, the algorithm yields 8643 (86.12%) reliable HR measurements from a total of 10 036 heartbeats, including some with uninformative data resulting from arrhythmias and artifacts. |
| first_indexed | 2024-12-22T21:17:49Z |
| format | Article |
| id | doaj.art-bf9d7ff161334534903d6a78adc52319 |
| institution | Directory Open Access Journal |
| issn | 1225-6463 |
| language | English |
| last_indexed | 2024-12-22T21:17:49Z |
| publishDate | 2021-10-01 |
| publisher | Electronics and Telecommunications Research Institute (ETRI) |
| record_format | Article |
| series | ETRI Journal |
| spelling | doaj.art-bf9d7ff161334534903d6a78adc523192022-12-21T18:12:19ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632021-10-0143588189010.4218/etrij.2020-039410.4218/etrij.2020-0394Real‐time photoplethysmographic heart rate measurement using deep neural network filtersJi Woon KimSung Min ParkSeong Wook ChoiAbstractPhotoplethysmography (PPG) is a noninvasive technique that can be used to conveniently measure heart rate (HR) and thus obtain relevant health‐related information. However, developing an automated PPG system is difficult, because its waveforms are susceptible to motion artifacts and between‐patient variation, making its interpretation difficult. We use deep neural network (DNN) filters to mimic the cognitive ability of a human expert who can distinguish the features of PPG altered by noise from various sources. Systolic (S), onset (O), and first derivative peaks (W) are recognized by three different DNN filters. In addition, the boundaries of uninformative regions caused by artifacts are identified by two different filters. The algorithm reliably derives the HR and presents recognition scores for the S, O, and W peaks and artifacts with only a 0.7‐s delay. In the evaluation using data from 11 patients obtained from PhysioNet, the algorithm yields 8643 (86.12%) reliable HR measurements from a total of 10 036 heartbeats, including some with uninformative data resulting from arrhythmias and artifacts.https://doi.org/10.4218/etrij.2020-0394deep learningdeep neural network filterheart ratephotoplethysmographyrecognition score |
| spellingShingle | Ji Woon Kim Sung Min Park Seong Wook Choi Real‐time photoplethysmographic heart rate measurement using deep neural network filters ETRI Journal deep learning deep neural network filter heart rate photoplethysmography recognition score |
| title | Real‐time photoplethysmographic heart rate measurement using deep neural network filters |
| title_full | Real‐time photoplethysmographic heart rate measurement using deep neural network filters |
| title_fullStr | Real‐time photoplethysmographic heart rate measurement using deep neural network filters |
| title_full_unstemmed | Real‐time photoplethysmographic heart rate measurement using deep neural network filters |
| title_short | Real‐time photoplethysmographic heart rate measurement using deep neural network filters |
| title_sort | real time photoplethysmographic heart rate measurement using deep neural network filters |
| topic | deep learning deep neural network filter heart rate photoplethysmography recognition score |
| url | https://doi.org/10.4218/etrij.2020-0394 |
| work_keys_str_mv | AT jiwoonkim realtimephotoplethysmographicheartratemeasurementusingdeepneuralnetworkfilters AT sungminpark realtimephotoplethysmographicheartratemeasurementusingdeepneuralnetworkfilters AT seongwookchoi realtimephotoplethysmographicheartratemeasurementusingdeepneuralnetworkfilters |