1
|
Kolakowski M, Djaja-Josko V, Kolakowski J, Cichocki J. Wrist-to-Tibia/Shoe Inertial Measurement Results Translation Using Neural Networks. SENSORS (BASEL, SWITZERLAND) 2024; 24:293. [PMID: 38203155 PMCID: PMC10781324 DOI: 10.3390/s24010293] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 12/28/2023] [Accepted: 01/02/2024] [Indexed: 01/12/2024]
Abstract
Most of the established gait evaluation methods use inertial sensors mounted in the lower limb area (tibias, ankles, shoes). Such sensor placement gives good results in laboratory conditions but is hard to apply in everyday scenarios due to the sensors' fragility and the user's comfort. The paper presents an algorithm that enables translation of the inertial signal measurements (acceleration and angular velocity) registered with a wrist-worn sensor to signals, which would be obtained if the sensor was worn on a tibia or a shoe. Four different neural network architectures are considered for that purpose: Dense and CNN autoencoders, a CNN-LSTM hybrid, and a U-Net-based model. The performed experiments have shown that the CNN autoencoder and U-Net can be successfully applied for inertial signal translation purposes. Estimating gait parameters based on the translated signals yielded similar results to those obtained based on shoe-sensor signals.
Collapse
Affiliation(s)
- Marcin Kolakowski
- Institute of Radioelectronics and Multimedia Technology, Warsaw University of Technology, 00-661 Warsaw, Poland
| | | | | | | |
Collapse
|
2
|
Pankaj, Kumar A, Kumar M, Komaragiri R. Optimized deep neural network models for blood pressure classification using Fourier analysis-based time-frequency spectrogram of photoplethysmography signal. Biomed Eng Lett 2023; 13:739-750. [PMID: 37872982 PMCID: PMC10590347 DOI: 10.1007/s13534-023-00296-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Revised: 05/28/2023] [Accepted: 06/09/2023] [Indexed: 10/25/2023] Open
Abstract
Appropriate blood pressure (BP) management through continuous monitoring and rapid diagnosis helps to take preventive care against cardiovascular diseases (CVD). As hypertension is one of the leading causes of CVDs, keeping hypertension under control by a timely screening of subjects becomes lifesaving. This work proposes estimating BP from motion artifact-affected photoplethysmography signals (PPG) by applying signal processing techniques in realtime. This paper proposes a deep neural network-based methodology to accurately classify PPG signals using a Fourier theory-based time-frequency (TF) spectrogram. This work uses the Fourier decomposition method (FDM) to transform a PPG signal into a TF spectrogram. In the proposed work, the last three layers of the pre-trained deep neural network, namely, GoogleNet, DenseNet, and AlexNet, are modified and then used to classify the PPG signal into normotension, pre-hypertension, and hypertension. The proposed framework is trained and tested using the MIMIC-III and PPG-BP databases using five-fold training and testing. Out of the three deep neural networks, the proposed framework with the DenseNet-201 network performs best, with a test accuracy of 96.5%. The proposed work uses FDM to compute the TF spectrogram to accurately separate the motion artifacts and noise components from a noise-corrupted PPG signal. Capturing more frequency components that contain more information from PPG signals makes the deep neural networks extract better and more meaningful features. Thus, training a deep neural network model with clean PPG signal features improves the generalized capability of a BP classification model when tested in realtime.
Collapse
Affiliation(s)
- Pankaj
- Department of Electronics and Communication Engineering, Bennett University, Greater Noida, India
| | - Ashish Kumar
- School of Electronics Engineering, Vellore Institute of Technology, Chennai, Tamil Nadu India
| | - Manjeet Kumar
- Department of Electronics and Communication Engineering, Delhi Technological University, Delhi, India
| | - Rama Komaragiri
- Department of Electronics and Communication Engineering, Bennett University, Greater Noida, India
| |
Collapse
|
3
|
Attivissimo F, D’Alessandro VI, De Palma L, Lanzolla AML, Di Nisio A. Non-Invasive Blood Pressure Sensing via Machine Learning. SENSORS (BASEL, SWITZERLAND) 2023; 23:8342. [PMID: 37837172 PMCID: PMC10574845 DOI: 10.3390/s23198342] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/28/2023] [Revised: 09/21/2023] [Accepted: 10/07/2023] [Indexed: 10/15/2023]
Abstract
In this paper, a machine learning (ML) approach to estimate blood pressure (BP) using photoplethysmography (PPG) is presented. The final aim of this paper was to develop ML methods for estimating blood pressure (BP) in a non-invasive way that is suitable in a telemedicine health-care monitoring context. The training of regression models useful for estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP) was conducted using new extracted features from PPG signals processed using the Maximal Overlap Discrete Wavelet Transform (MODWT). As a matter of fact, the interest was on the use of the most significant features obtained by the Minimum Redundancy Maximum Relevance (MRMR) selection algorithm to train eXtreme Gradient Boost (XGBoost) and Neural Network (NN) models. This aim was satisfactorily achieved by also comparing it with works in the literature; in fact, it was found that XGBoost models are more accurate than NN models in both systolic and diastolic blood pressure measurements, obtaining a Root Mean Square Error (RMSE) for SBP and DBP, respectively, of 5.67 mmHg and 3.95 mmHg. For SBP measurement, this result is an improvement compared to that reported in the literature. Furthermore, the trained XGBoost regression model fulfills the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) as well as grade A of the British Hypertension Society (BHS) standard.
Collapse
Affiliation(s)
| | | | | | - Anna Maria Lucia Lanzolla
- Department of Electrical and Information Engineering, Polytechnic University of Bari, 70125 Bari, Italy; (F.A.); (V.I.D.); (L.D.P.); (A.D.N.)
| | | |
Collapse
|
4
|
Wang H, Han M, Zhong C, Wang C, Chen R, Zhang G, Wang J, Wei R. Non-invasive continuous blood pressure prediction based on ECG and PPG fusion map. Med Eng Phys 2023; 119:104037. [PMID: 37634908 DOI: 10.1016/j.medengphy.2023.104037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Revised: 07/12/2023] [Accepted: 08/06/2023] [Indexed: 08/29/2023]
Abstract
To achieve real-time blood pressure monitoring, a novel non-invasive method is proposed in this article. Electrocardiographic (ECG) and pulse wave signals (PPG) are fused from a multi-omics signal-level perspective. A physiological signal fusion matrix and fusion map, which can estimate the blood pressure of blood loss(BPBL), are constructed. The results demonstrate the efficacy of the fusion map model, with correlation values of 0.988 and 0.991 between the estimated BPBL and the true systolic blood pressure (SBP) and diastolic blood pressure (DBP), respectively. The root mean square errors for SBP and DBP were 3.21 mmHg and 3.00 mmHg, respectively. The model validation showed that the fusion map method is capable of simultaneous highlighting of the respective characteristics of ECG and PPG and their correlation, improving the utilization of the information and the accuracy of BPBL. This article validates that physiological signal fusion map can effectively improve the accuracy of BPBL estimation and provides a new perspective for the field of physiological information fusion.
Collapse
Affiliation(s)
- Huiquan Wang
- School of Life Sciences, TianGong University, Tianjin 300387, China; Tianjin Key Laboratory of Quality Control and Evaluation Technology for Medical Devices, Tianjin 300384, China
| | - Mengting Han
- School of Life Sciences, TianGong University, Tianjin 300387, China
| | - Chuwei Zhong
- School of Life Sciences, TianGong University, Tianjin 300387, China
| | - Cong Wang
- School of Life Sciences, TianGong University, Tianjin 300387, China
| | - Ruijuan Chen
- School of Life Sciences, TianGong University, Tianjin 300387, China; Tianjin Key Laboratory of Quality Control and Evaluation Technology for Medical Devices, Tianjin 300384, China
| | - Guang Zhang
- Institute of Medical Support, Academy of Military Sciences, Tianjin 300361, China
| | - Jinhai Wang
- School of Life Sciences, TianGong University, Tianjin 300387, China; Tianjin Key Laboratory of Quality Control and Evaluation Technology for Medical Devices, Tianjin 300384, China
| | - Ran Wei
- Beijing College of Social Administration (Training Center of the Ministry of Civil Affairs), Beijing 101601, China.
| |
Collapse
|
5
|
Toda S, Matsumura K. Investigation of Optimal Light Source Wavelength for Cuffless Blood Pressure Estimation Using a Single Photoplethysmography Sensor. SENSORS (BASEL, SWITZERLAND) 2023; 23:3689. [PMID: 37050747 PMCID: PMC10098792 DOI: 10.3390/s23073689] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/24/2023] [Revised: 03/30/2023] [Accepted: 03/30/2023] [Indexed: 06/19/2023]
Abstract
Routine blood pressure measurement is important for the early detection of various diseases. Recently, cuffless blood pressure estimation methods that do not require cuff pressurization have attracted attention. In this study, we investigated the effect of the light source wavelength on the accuracy of blood pressure estimation using only two physiological indices that can be calculated with photoplethysmography alone, namely, heart rate and modified normalized pulse volume. Using a newly developed photoplethysmography sensor that can simultaneously measure photoplethysmograms at four wavelengths, we evaluated its estimation accuracy for systolic blood pressure, diastolic blood pressure, and mean arterial pressure against a standard cuff sphygmomanometer. Mental stress tasks were used to alter the blood pressure of 14 participants, and multiple linear regression analysis showed the best light sources to be near-infrared for systolic blood pressure and blue for both diastolic blood pressure and mean arterial pressure. The importance of the light source wavelength for the photoplethysmogram in cuffless blood pressure estimation was clarified.
Collapse
Affiliation(s)
- Sogo Toda
- Ishikawa College, National Institute of Technology, Tsubata 929-0392, Japan
| | - Kenta Matsumura
- Faculty of Medicine, University of Toyama, Toyama 930-0194, Japan
| |
Collapse
|
6
|
Qin C, Li Y, Liu C, Ma X. Cuff-Less Blood Pressure Prediction Based on Photoplethysmography and Modified ResNet. Bioengineering (Basel) 2023; 10:bioengineering10040400. [PMID: 37106587 PMCID: PMC10135940 DOI: 10.3390/bioengineering10040400] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2023] [Revised: 03/20/2023] [Accepted: 03/20/2023] [Indexed: 04/29/2023] Open
Abstract
Cardiovascular disease (CVD) has become a common health problem of mankind, and the prevalence and mortality of CVD are rising on a year-to-year basis. Blood pressure (BP) is an important physiological parameter of the human body and also an important physiological indicator for the prevention and treatment of CVD. Existing intermittent measurement methods do not fully indicate the real BP status of the human body and cannot get rid of the restraining feeling of a cuff. Accordingly, this study proposed a deep learning network based on the ResNet34 framework for continuous prediction of BP using only the promising PPG signal. The high-quality PPG signals were first passed through a multi-scale feature extraction module after a series of pre-processing to expand the perceptive field and enhance the perception ability on features. Subsequently, useful feature information was then extracted by stacking multiple residual modules with channel attention to increase the accuracy of the model. Lastly, in the training stage, the Huber loss function was adopted to stabilize the iterative process and obtain the optimal solution of the model. On a subset of the MIMIC dataset, the errors of both SBP and DBP predicted by the model met the AAMI standards, while the accuracy of DBP reached Grade A of the BHS standard, and the accuracy of SBP almost reached Grade A of the BHS standard. The proposed method verifies the potential and feasibility of PPG signals combined with deep neural networks in the field of continuous BP monitoring. Furthermore, the method is easy to deploy in portable devices, and it is more consistent with the future trend of wearable blood-pressure-monitoring devices (e.g., smartphones and smartwatches).
Collapse
Affiliation(s)
- Caijie Qin
- Institute of Information Engineering, Sanming University, Sanming 365004, China
- CBSR&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing 100049, China
| | - Yong Li
- Institute of Information Engineering, Sanming University, Sanming 365004, China
| | - Chibiao Liu
- Institute of Information Engineering, Sanming University, Sanming 365004, China
| | - Xibo Ma
- CBSR&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing 100049, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
| |
Collapse
|
7
|
Qin K, Huang W, Zhang T, Tang S. Machine learning and deep learning for blood pressure prediction: a methodological review from multiple perspectives. Artif Intell Rev 2022. [DOI: 10.1007/s10462-022-10353-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
|
8
|
Advances in Cuffless Continuous Blood Pressure Monitoring Technology Based on PPG Signals. BIOMED RESEARCH INTERNATIONAL 2022; 2022:8094351. [PMID: 36217389 PMCID: PMC9547685 DOI: 10.1155/2022/8094351] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/29/2022] [Accepted: 07/30/2022] [Indexed: 11/17/2022]
Abstract
Objective. To review the progress of research on photoplethysmography- (PPG-) based cuffless continuous blood pressure monitoring technologies and prospect the challenges that need to be addressed in the future. Methods. Using Web of Science and PubMed as search engines, the literature on cuffless continuous blood pressure studies using PPG signals in the recent five years were searched. Results. Based on the retrieved literature, this paper describes the available open datasets, commonly used signal preprocessing methods, and model evaluation criteria. Early researches employed multisite PPG signals to calculate pulse wave velocity or time and predicted blood pressure by a simple linear equation. Later, extensive researches were dedicated to mine the features of PPG signals related to blood pressure and regressed blood pressure by machine learning models. Most recently, many researches have emerged to experiment with complex deep learning models for blood pressure prediction with the raw PPG signal as input. Conclusion. This paper summarized the methods in the retrieved literature, provided insight into the artificial intelligence algorithms employed in the literature, and concluded with a discussion of the challenges and opportunities for the development of cuffless continuous blood pressure monitoring technologies.
Collapse
|
9
|
Advancing Digital Medicine with Wearables in the Wild. SENSORS 2022; 22:s22124576. [PMID: 35746358 PMCID: PMC9227612 DOI: 10.3390/s22124576] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 06/09/2022] [Accepted: 06/15/2022] [Indexed: 02/04/2023]
|