A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring
Health-tracking from photoplethysmography (PPG) signals is significantly hindered by motion artifacts (MAs). Although many algorithms exist to detect MAs, the corrupted signal often remains unexploited. This work introduces a novel method able to reconstruct noisy PPGs and facilitate uninterrupted h...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/1/141 |
| _version_ | 1827384399512993792 |
|---|---|
| author | Aikaterini Vraka Roberto Zangróniz Aurelio Quesada Fernando Hornero Raúl Alcaraz José J. Rieta |
| author_facet | Aikaterini Vraka Roberto Zangróniz Aurelio Quesada Fernando Hornero Raúl Alcaraz José J. Rieta |
| author_sort | Aikaterini Vraka |
| collection | DOAJ |
| description | Health-tracking from photoplethysmography (PPG) signals is significantly hindered by motion artifacts (MAs). Although many algorithms exist to detect MAs, the corrupted signal often remains unexploited. This work introduces a novel method able to reconstruct noisy PPGs and facilitate uninterrupted health monitoring. The algorithm starts with spectral-based MA detection, followed by signal reconstruction by using the morphological and heart-rate variability information from the clean segments adjacent to noise. The algorithm was tested on (a) 30 noisy PPGs of a maximum 20 s noise duration and (b) 28 originally clean PPGs, after noise addition (2–120 s) (1) with and (2) without cancellation of the corresponding clean segment. Sampling frequency was 250 Hz after resampling. Noise detection was evaluated by means of accuracy, sensitivity, and specificity. For the evaluation of signal reconstruction, the heart-rate (HR) was compared via Pearson correlation (PC) and absolute error (a) between ECGs and reconstructed PPGs and (b) between original and reconstructed PPGs. Bland-Altman (BA) analysis for the differences in HR estimation on original and reconstructed segments of (b) was also performed. Noise detection accuracy was <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.91</mn><mo>%</mo></mrow></semantics></math></inline-formula> for (a) and 99.38–100% for (b). For the PPG reconstruction, HR showed <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.31</mn><mo>%</mo></mrow></semantics></math></inline-formula> correlation in (a) and >90% for all noise lengths in (b). Mean absolute error was <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.59</mn></mrow></semantics></math></inline-formula> bpm for (a) and 1.26–1.82 bpm for (b). BA analysis indicated that, in most cases, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90</mn><mo>%</mo></mrow></semantics></math></inline-formula> or more of the recordings fall within the confidence interval, regardless of the noise length. Optimal performance is achieved even for signals of noise up to 2 min, allowing for the utilization and further analysis of recordings that would otherwise be discarded. Thereby, the algorithm can be implemented in monitoring devices, assisting in uninterrupted health-tracking. |
| first_indexed | 2024-03-08T14:57:05Z |
| format | Article |
| id | doaj.art-2c8ee6ec529c4d2e8ea8f749ef5a217c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T14:57:05Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2c8ee6ec529c4d2e8ea8f749ef5a217c2024-01-10T15:08:44ZengMDPI AGSensors1424-82202023-12-0124114110.3390/s24010141A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health MonitoringAikaterini Vraka0Roberto Zangróniz1Aurelio Quesada2Fernando Hornero3Raúl Alcaraz4José J. Rieta5Biosignals and Minimally Invasive Technologies (BioMIT.org), Electronic Engineering Department, Universitat Politecnica de Valencia, 46022 Valencia, SpainResearch Group in Electronic, Biomedical and Telecommunication Engineering, University of Castilla-La Mancha, 16071 Cuenca, SpainArrhythmia Unit, Cardiology Department, General University Hospital Consortium of Valencia, 46014 Valencia, SpainCardiovascular Surgery Department, Hospital Clínico Universitario de Valencia, 46010 Valencia, SpainResearch Group in Electronic, Biomedical and Telecommunication Engineering, University of Castilla-La Mancha, 16071 Cuenca, SpainBiosignals and Minimally Invasive Technologies (BioMIT.org), Electronic Engineering Department, Universitat Politecnica de Valencia, 46022 Valencia, SpainHealth-tracking from photoplethysmography (PPG) signals is significantly hindered by motion artifacts (MAs). Although many algorithms exist to detect MAs, the corrupted signal often remains unexploited. This work introduces a novel method able to reconstruct noisy PPGs and facilitate uninterrupted health monitoring. The algorithm starts with spectral-based MA detection, followed by signal reconstruction by using the morphological and heart-rate variability information from the clean segments adjacent to noise. The algorithm was tested on (a) 30 noisy PPGs of a maximum 20 s noise duration and (b) 28 originally clean PPGs, after noise addition (2–120 s) (1) with and (2) without cancellation of the corresponding clean segment. Sampling frequency was 250 Hz after resampling. Noise detection was evaluated by means of accuracy, sensitivity, and specificity. For the evaluation of signal reconstruction, the heart-rate (HR) was compared via Pearson correlation (PC) and absolute error (a) between ECGs and reconstructed PPGs and (b) between original and reconstructed PPGs. Bland-Altman (BA) analysis for the differences in HR estimation on original and reconstructed segments of (b) was also performed. Noise detection accuracy was <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.91</mn><mo>%</mo></mrow></semantics></math></inline-formula> for (a) and 99.38–100% for (b). For the PPG reconstruction, HR showed <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.31</mn><mo>%</mo></mrow></semantics></math></inline-formula> correlation in (a) and >90% for all noise lengths in (b). Mean absolute error was <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.59</mn></mrow></semantics></math></inline-formula> bpm for (a) and 1.26–1.82 bpm for (b). BA analysis indicated that, in most cases, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90</mn><mo>%</mo></mrow></semantics></math></inline-formula> or more of the recordings fall within the confidence interval, regardless of the noise length. Optimal performance is achieved even for signals of noise up to 2 min, allowing for the utilization and further analysis of recordings that would otherwise be discarded. Thereby, the algorithm can be implemented in monitoring devices, assisting in uninterrupted health-tracking.https://www.mdpi.com/1424-8220/24/1/141photoplethysmographymotion artifactsnoise detectionsignal reconstructionhealth-trackinguninterrupted monitoring |
| spellingShingle | Aikaterini Vraka Roberto Zangróniz Aurelio Quesada Fernando Hornero Raúl Alcaraz José J. Rieta A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring Sensors photoplethysmography motion artifacts noise detection signal reconstruction health-tracking uninterrupted monitoring |
| title | A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring |
| title_full | A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring |
| title_fullStr | A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring |
| title_full_unstemmed | A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring |
| title_short | A Novel Signal Restoration Method of Noisy Photoplethysmograms for Uninterrupted Health Monitoring |
| title_sort | novel signal restoration method of noisy photoplethysmograms for uninterrupted health monitoring |
| topic | photoplethysmography motion artifacts noise detection signal reconstruction health-tracking uninterrupted monitoring |
| url | https://www.mdpi.com/1424-8220/24/1/141 |
| work_keys_str_mv | AT aikaterinivraka anovelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT robertozangroniz anovelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT aurelioquesada anovelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT fernandohornero anovelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT raulalcaraz anovelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT josejrieta anovelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT aikaterinivraka novelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT robertozangroniz novelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT aurelioquesada novelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT fernandohornero novelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT raulalcaraz novelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring AT josejrieta novelsignalrestorationmethodofnoisyphotoplethysmogramsforuninterruptedhealthmonitoring |