Learning about reflective PPG for SpO2 determination using Machine Learning
Reflective Photoplethysmography (PPG) sensors are less obtrusive than transmissive sensors, but they present patient-dependent variations in the so-called “Ratio of Modulation” (R). Thus, the conventionally employed calibration curves for determining peripheral oxygen saturation ( SpO2) may report i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2021-10-01
|
| Series: | Current Directions in Biomedical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cdbme-2021-2009 |
| _version_ | 1811246854871973888 |
|---|---|
| author | Badiola Aguirregomezcorta Idoia Blazek Vladimir Leonhardt Steffen Hoog Antink Christoph |
| author_facet | Badiola Aguirregomezcorta Idoia Blazek Vladimir Leonhardt Steffen Hoog Antink Christoph |
| author_sort | Badiola Aguirregomezcorta Idoia |
| collection | DOAJ |
| description | Reflective Photoplethysmography (PPG) sensors are less obtrusive than transmissive sensors, but they present patient-dependent variations in the so-called “Ratio of Modulation” (R). Thus, the conventionally employed calibration curves for determining peripheral oxygen saturation ( SpO2) may report inaccurate values. In this paper, we study the possibility of overcoming these limitations through Machine Learning (ML). For that, we show the results of applying several algorithms and feature combinations to PPG data from a human hypoxia study. The study was performed on ten healthy subjects. Their target oxygen saturation was reduced in five steps from 98- 100% to 70-77% through an oral mask. Blood Gas Analysis (BGA) was performed five times for each saturation level to measure the arterial oxygen saturation. PPG data were acquired from a reflective pulse oximeter placed in the subjects’ ear canals. PPG signals were pre-processed, and several features in the frequency and temporal domain were calculated. For the ML algorithms’ input, we explored different combinations of the features. We trained and validated the algorithms with the data from seven patients, and we tested them on three. Finally, we performed leaveone- out cross-validation to ensure the universality of the methods. The results show a good agreement of the predictions with the BGA values for Linear Regression, k- Nearest Neighbors, Stochastic Gradient Descent, and Neural Network for all input feature combinations with an average RMSE in the range of 3%. However, the performance of the Linear Regression was not beaten by the Neural Network, even for overfitting with 2000 hidden layers. The combination of R calculated with a Fast-Fourier Transform and ACRMS.red/ACRMS.irsignificantly improved the results, reducing the RMSE by 25%. This work demonstrates that a straight-forward Linear Regression is capable of determining SpO2with reflective PPG independently of the subject if the ratio ACRMS.red/ACRMS.ir is considered simultaneously with the Ratio of Modulation. |
| first_indexed | 2024-04-12T14:59:22Z |
| format | Article |
| id | doaj.art-dc151af4614d470dae8a50dc849802c0 |
| institution | Directory Open Access Journal |
| issn | 2364-5504 |
| language | English |
| last_indexed | 2024-04-12T14:59:22Z |
| publishDate | 2021-10-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Current Directions in Biomedical Engineering |
| spelling | doaj.art-dc151af4614d470dae8a50dc849802c02022-12-22T03:28:07ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042021-10-0172333610.1515/cdbme-2021-2009Learning about reflective PPG for SpO2 determination using Machine LearningBadiola Aguirregomezcorta Idoia0Blazek Vladimir1Leonhardt Steffen2Hoog Antink Christoph3Lehrstuhl für Medizinische Informationstechnik (MedIT), RWTH Aachen University, Pauwelsstraße 20,Aachen, GermanyLehrstuhl für Medizinische Informationstechnik (MedIT), RWTH Aachen University,Aachen, GermanyLehrstuhl für Medizinische Informationstechnik (MedIT), RWTH Aachen University,Aachen, GermanyLehrstuhl für Medizinische Informationstechnik (MedIT), RWTH Aachen University,Aachen, GermanyReflective Photoplethysmography (PPG) sensors are less obtrusive than transmissive sensors, but they present patient-dependent variations in the so-called “Ratio of Modulation” (R). Thus, the conventionally employed calibration curves for determining peripheral oxygen saturation ( SpO2) may report inaccurate values. In this paper, we study the possibility of overcoming these limitations through Machine Learning (ML). For that, we show the results of applying several algorithms and feature combinations to PPG data from a human hypoxia study. The study was performed on ten healthy subjects. Their target oxygen saturation was reduced in five steps from 98- 100% to 70-77% through an oral mask. Blood Gas Analysis (BGA) was performed five times for each saturation level to measure the arterial oxygen saturation. PPG data were acquired from a reflective pulse oximeter placed in the subjects’ ear canals. PPG signals were pre-processed, and several features in the frequency and temporal domain were calculated. For the ML algorithms’ input, we explored different combinations of the features. We trained and validated the algorithms with the data from seven patients, and we tested them on three. Finally, we performed leaveone- out cross-validation to ensure the universality of the methods. The results show a good agreement of the predictions with the BGA values for Linear Regression, k- Nearest Neighbors, Stochastic Gradient Descent, and Neural Network for all input feature combinations with an average RMSE in the range of 3%. However, the performance of the Linear Regression was not beaten by the Neural Network, even for overfitting with 2000 hidden layers. The combination of R calculated with a Fast-Fourier Transform and ACRMS.red/ACRMS.irsignificantly improved the results, reducing the RMSE by 25%. This work demonstrates that a straight-forward Linear Regression is capable of determining SpO2with reflective PPG independently of the subject if the ratio ACRMS.red/ACRMS.ir is considered simultaneously with the Ratio of Modulation.https://doi.org/10.1515/cdbme-2021-2009reflective ppgspo2arterial oxygen saturationmachine learninghypoxiaratio of modulation. |
| spellingShingle | Badiola Aguirregomezcorta Idoia Blazek Vladimir Leonhardt Steffen Hoog Antink Christoph Learning about reflective PPG for SpO2 determination using Machine Learning Current Directions in Biomedical Engineering reflective ppg spo2 arterial oxygen saturation machine learning hypoxia ratio of modulation. |
| title | Learning about reflective PPG for SpO2 determination using Machine Learning |
| title_full | Learning about reflective PPG for SpO2 determination using Machine Learning |
| title_fullStr | Learning about reflective PPG for SpO2 determination using Machine Learning |
| title_full_unstemmed | Learning about reflective PPG for SpO2 determination using Machine Learning |
| title_short | Learning about reflective PPG for SpO2 determination using Machine Learning |
| title_sort | learning about reflective ppg for spo2 determination using machine learning |
| topic | reflective ppg spo2 arterial oxygen saturation machine learning hypoxia ratio of modulation. |
| url | https://doi.org/10.1515/cdbme-2021-2009 |
| work_keys_str_mv | AT badiolaaguirregomezcortaidoia learningaboutreflectiveppgforspo2determinationusingmachinelearning AT blazekvladimir learningaboutreflectiveppgforspo2determinationusingmachinelearning AT leonhardtsteffen learningaboutreflectiveppgforspo2determinationusingmachinelearning AT hoogantinkchristoph learningaboutreflectiveppgforspo2determinationusingmachinelearning |