A robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography
CCBY Objective: Respiratory rate (RR) estimation algorithms based on the photoplethymogram (PPG) and electrocardiogram (ECG) lack clinical robustness. This is because the PPG and ECG respiratory modulations are highly dependent on patient physiology, regardless of general signal quality. The present...
| Main Authors: | , , , |
|---|---|
| Format: | Journal article |
| Published: |
Institute of Electrical and Electronics Engineers
2017
|
| _version_ | 1826264456820162560 |
|---|---|
| author | Birrenkott, D Pimentel, M Watkinson, P Clifton, D |
| author_facet | Birrenkott, D Pimentel, M Watkinson, P Clifton, D |
| author_sort | Birrenkott, D |
| collection | OXFORD |
| description | CCBY Objective: Respiratory rate (RR) estimation algorithms based on the photoplethymogram (PPG) and electrocardiogram (ECG) lack clinical robustness. This is because the PPG and ECG respiratory modulations are highly dependent on patient physiology, regardless of general signal quality. The present work describes an RR estimation algorithm using respiratory quality indices (RQIs) which assess the presence or absence of the PPG- and ECG-derived respiratory modulations. Methods: Six respiratory waveform are derived from the amplitude modulation, frequency modulation, and baseline wander of the PPG and ECG. The respiratory quality of each modulation is assessed using RQIs based on the FFT, autoregression, autocorrelation, and Hjorth complexity. The individual RQIs are fused to obtain a single RQI per modulation per time window. Based on a tunable threshold, the RQIs are used to discard poor modulations and weight the remaining modulations to provide a single RR estimation per time window. Results: The proposed method was tested on two independent data sets and found that using a conservative threshold, the mean absolute error (MAE) was 0.71 & #x00B1; 0.89 and 3.12 & #x00B1; 4.39 brpm while discarding only 1.3% and 23.2% of all time windows, for each data set, respectively. Conclusion: These errors are either better than or comparable to current methods, and the number of windows discarded is far lower demonstrating improved robustness. Significance: This work describes a novel pre-processing algorithm that can be implemented in conjunction with other RR estimation techniques to improve robustness by specifically considering the quality of the respiratory information. |
| first_indexed | 2024-03-06T20:08:06Z |
| format | Journal article |
| id | oxford-uuid:2996f015-df52-459a-b38d-6a1ebc98d529 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:08:06Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:2996f015-df52-459a-b38d-6a1ebc98d5292022-03-26T12:20:05ZA robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiographyJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:2996f015-df52-459a-b38d-6a1ebc98d529Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2017Birrenkott, DPimentel, MWatkinson, PClifton, DCCBY Objective: Respiratory rate (RR) estimation algorithms based on the photoplethymogram (PPG) and electrocardiogram (ECG) lack clinical robustness. This is because the PPG and ECG respiratory modulations are highly dependent on patient physiology, regardless of general signal quality. The present work describes an RR estimation algorithm using respiratory quality indices (RQIs) which assess the presence or absence of the PPG- and ECG-derived respiratory modulations. Methods: Six respiratory waveform are derived from the amplitude modulation, frequency modulation, and baseline wander of the PPG and ECG. The respiratory quality of each modulation is assessed using RQIs based on the FFT, autoregression, autocorrelation, and Hjorth complexity. The individual RQIs are fused to obtain a single RQI per modulation per time window. Based on a tunable threshold, the RQIs are used to discard poor modulations and weight the remaining modulations to provide a single RR estimation per time window. Results: The proposed method was tested on two independent data sets and found that using a conservative threshold, the mean absolute error (MAE) was 0.71 & #x00B1; 0.89 and 3.12 & #x00B1; 4.39 brpm while discarding only 1.3% and 23.2% of all time windows, for each data set, respectively. Conclusion: These errors are either better than or comparable to current methods, and the number of windows discarded is far lower demonstrating improved robustness. Significance: This work describes a novel pre-processing algorithm that can be implemented in conjunction with other RR estimation techniques to improve robustness by specifically considering the quality of the respiratory information. |
| spellingShingle | Birrenkott, D Pimentel, M Watkinson, P Clifton, D A robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography |
| title | A robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography |
| title_full | A robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography |
| title_fullStr | A robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography |
| title_full_unstemmed | A robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography |
| title_short | A robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography |
| title_sort | robust fusion model for estimating respiratory rate from photoplethysmography and electrocardiography |
| work_keys_str_mv | AT birrenkottd arobustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography AT pimentelm arobustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography AT watkinsonp arobustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography AT cliftond arobustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography AT birrenkottd robustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography AT pimentelm robustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography AT watkinsonp robustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography AT cliftond robustfusionmodelforestimatingrespiratoryratefromphotoplethysmographyandelectrocardiography |