1
|
Argüello-Prada EJ, Marcillo Ibarra KD, Díaz Jiménez KL. The use of successive systolic differences in photoplethysmographic (PPG) signals for respiratory rate estimation. Heliyon 2024; 10:e26036. [PMID: 38370197 PMCID: PMC10869914 DOI: 10.1016/j.heliyon.2024.e26036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2023] [Revised: 02/06/2024] [Accepted: 02/07/2024] [Indexed: 02/20/2024] Open
Abstract
Most PPG-based methods for extracting the respiratory rate (RR) rely on changes in the PPG signal's amplitude, baseline, or frequency. However, several other parameters may provide more valuable information for accurate RR computation. In this study, we explored the capabilities of the respiratory-induced variations in successive systolic differences (RISSDV) of PPG signals to estimate RR. We partitioned fifty-three publicly available recordings into eight 1-min segments and identified peaks and troughs of the PPG signals to quantify respiratory-induced variations in amplitude (RIAV), baseline (RIIV), frequency (RIFV), and peak-to-peak amplitude differences (RISSDV). RR values were extracted by determining the peak frequency of the power spectral density of the four variations and the reference respiratory signal. We assessed each feature's performance by computing the root-mean-squared (RMSE) and mean absolute errors (MAE). RISSDV errors were significantly lower than those of RIAV (RMSE and MAE: p < 0.001), RIIV (RMSE: p < 0.01; MAE p < 0.05), and RIFV (RMSE and MAE: p < 0.001), and it appeared less sensitive to absent or missed PPG pulses than respiratory-induced frequency variations. Further research is necessary to extrapolate these findings to subjects under ambulatory rather than stationary conditions, including pediatric and neonatal populations.
Collapse
Affiliation(s)
- Erick Javier Argüello-Prada
- Programa de Bioingeniería, Facultad de Ingeniería, Universidad Santiago de Cali, Cali-Colombia, Calle 5 # 62-00 Barrio Pampalinda, Santiago de Cali, Valle del Cauca, Colombia
| | - Katherin Daniela Marcillo Ibarra
- Programa de Bioingeniería, Facultad de Ingeniería, Universidad Santiago de Cali, Cali-Colombia, Calle 5 # 62-00 Barrio Pampalinda, Santiago de Cali, Valle del Cauca, Colombia
| | - Kevin Leonardo Díaz Jiménez
- Programa de Bioingeniería, Facultad de Ingeniería, Universidad Santiago de Cali, Cali-Colombia, Calle 5 # 62-00 Barrio Pampalinda, Santiago de Cali, Valle del Cauca, Colombia
| |
Collapse
|
2
|
Shuzan MNI, Chowdhury MH, Chowdhury MEH, Murugappan M, Hoque Bhuiyan E, Arslane Ayari M, Khandakar A. Machine Learning-Based Respiration Rate and Blood Oxygen Saturation Estimation Using Photoplethysmogram Signals. Bioengineering (Basel) 2023; 10:bioengineering10020167. [PMID: 36829661 PMCID: PMC9952751 DOI: 10.3390/bioengineering10020167] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Revised: 01/22/2023] [Accepted: 01/23/2023] [Indexed: 02/03/2023] Open
Abstract
The continuous monitoring of respiratory rate (RR) and oxygen saturation (SpO2) is crucial for patients with cardiac, pulmonary, and surgical conditions. RR and SpO2 are used to assess the effectiveness of lung medications and ventilator support. In recent studies, the use of a photoplethysmogram (PPG) has been recommended for evaluating RR and SpO2. This research presents a novel method of estimating RR and SpO2 using machine learning models that incorporate PPG signal features. A number of established methods are used to extract meaningful features from PPG. A feature selection approach was used to reduce the computational complexity and the possibility of overfitting. There were 19 models trained for both RR and SpO2 separately, from which the most appropriate regression model was selected. The Gaussian process regression model outperformed all the other models for both RR and SpO2 estimation. The mean absolute error (MAE) for RR was 0.89, while the root-mean-squared error (RMSE) was 1.41. For SpO2, the model had an RMSE of 0.98 and an MAE of 0.57. The proposed system is a state-of-the-art approach for estimating RR and SpO2 reliably from PPG. If RR and SpO2 can be consistently and effectively derived from the PPG signal, patients can monitor their RR and SpO2 at a cheaper cost and with less hassle.
Collapse
Affiliation(s)
- Md Nazmul Islam Shuzan
- Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Moajjem Hossain Chowdhury
- Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Muhammad E. H. Chowdhury
- Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
- Correspondence: (M.E.H.C.); or (M.M.)
| | - Murugappan Murugappan
- Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, Doha 13133, Kuwait
- Department of Electronics and Communication Engineering, School of Engineering, Vels Institute of Sciences, Technology and Advanced Studies, Chennai 600117, Tamil Nadu, India
- Center for Excellence for Unmanned Aerial Systems, Universiti Malaysia Perlis, Perlis 02600, Malaysia
- Correspondence: (M.E.H.C.); or (M.M.)
| | - Enamul Hoque Bhuiyan
- BioMedical Engineering and Imaging Institute (BMEII), Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA
| | - Mohamed Arslane Ayari
- Department of Civil and Architectural Engineering, Qatar University, Doha 2713, Qatar
| | - Amith Khandakar
- Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
| |
Collapse
|
3
|
Chowdhury MH, Shuzan MNI, Chowdhury MEH, Reaz MBI, Mahmud S, Al Emadi N, Ayari MA, Ali SHM, Bakar AAA, Rahman SM, Khandakar A. Lightweight End-to-End Deep Learning Solution for Estimating the Respiration Rate from Photoplethysmogram Signal. BIOENGINEERING (BASEL, SWITZERLAND) 2022; 9:bioengineering9100558. [PMID: 36290527 PMCID: PMC9598342 DOI: 10.3390/bioengineering9100558] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/10/2022] [Revised: 09/28/2022] [Accepted: 09/29/2022] [Indexed: 11/05/2022]
Abstract
Respiratory ailments are a very serious health issue and can be life-threatening, especially for patients with COVID. Respiration rate (RR) is a very important vital health indicator for patients. Any abnormality in this metric indicates a deterioration in health. Hence, continuous monitoring of RR can act as an early indicator. Despite that, RR monitoring equipment is generally provided only to intensive care unit (ICU) patients. Recent studies have established the feasibility of using photoplethysmogram (PPG) signals to estimate RR. This paper proposes a deep-learning-based end-to-end solution for estimating RR directly from the PPG signal. The system was evaluated on two popular public datasets: VORTAL and BIDMC. A lightweight model, ConvMixer, outperformed all of the other deep neural networks. The model provided a root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R) of 1.75 breaths per minute (bpm), 1.27 bpm, and 0.92, respectively, for VORTAL, while these metrics were 1.20 bpm, 0.77 bpm, and 0.92, respectively, for BIDMC. The authors also showed how fine-tuning a small subset could increase the performance of the model in the case of an out-of-distribution dataset. In the fine-tuning experiments, the models produced an average R of 0.81. Hence, this lightweight model can be deployed to mobile devices for real-time monitoring of patients.
Collapse
Affiliation(s)
- Moajjem Hossain Chowdhury
- Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Md Nazmul Islam Shuzan
- Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Muhammad E. H. Chowdhury
- Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
- Correspondence: (M.E.H.C.); (M.B.I.R.); (M.A.A.)
| | - Mamun Bin Ibne Reaz
- Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
- Correspondence: (M.E.H.C.); (M.B.I.R.); (M.A.A.)
| | - Sakib Mahmud
- Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
| | - Nasser Al Emadi
- Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
| | - Mohamed Arselene Ayari
- Department of Civil and Architectural Engineering, Qatar University, Doha 2713, Qatar
- Technology Innovation and Engineering Education Unit (TIEE), Qatar University, Doha 2713, Qatar
- Correspondence: (M.E.H.C.); (M.B.I.R.); (M.A.A.)
| | - Sawal Hamid Md Ali
- Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Ahmad Ashrif A. Bakar
- Department of Electrical, Electronic and System Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Syed Mahfuzur Rahman
- Department of Biomedical Engineering, Military Institute of Science and Technology, Mirpur Cantonment, Dhaka 1216, Bangladesh
| | - Amith Khandakar
- Department of Electrical Engineering, Qatar University, Doha 2713, Qatar
| |
Collapse
|