1
|
Mieke S, Murray A. Technical evaluation of a simulator for accurate reproduction of oscillometric blood pressure pulses, providing traceability for automated oscillometric sphygmomanometers. Biomed Phys Eng Express 2023; 9:065003. [PMID: 37657422 DOI: 10.1088/2057-1976/acf5f4] [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: 05/28/2023] [Accepted: 09/01/2023] [Indexed: 09/03/2023]
Abstract
Oscillometric blood pressure measurement devices are not directly traceable to primary standards. Currently, device accuracy is measured by comparison between a sample device and reference measurements in a clinical trial. We researched in this study the potential for an alternative evaluation with a simulator. Our research simulator was studied for repeatability and accuracy in delivering simulated blood pressure pulses. Clinical cuff pressure measurements were obtained, along with simultaneous recordings of oscillometric pulse waveforms, spanning the clinical range of cuff pressures, pulse intervals and pulse shapes. Oscillometric pulse peak amplitudes ranged from 1.1 to 3.6 mmHg. Simulated repeatability results showed an average Standard Deviation (SD) for pulse peaks of 0.018 mmHg; 1.0% of peak amplitudes. Comparing simulated pulse shapes, the average repeat SD was 0.015 mmHg; 0.8% of the normalised pulse shapes. The simulated accuracy results had a mean error of - 0.014 ± 0.042 mmHg with a mean accuracy of 97.8%. For pulse shape the corresponding values were - 0.104 ± 0.071 mmHg with a mean accuracy of 95.4%. The correlation between the reference and simulated pulse shapes ranged from 0.991 to 0.996 (all p < 0.00003), with a mean 0.994. We conclude that oscillometric pulses can be reproduced with high repeatability and high accuracy with our research simulator. The extended uncertaintyU(psim) = 0.3 mmHg for the simulated pulses is dominated by the uncertainty (64%) of the clinical reference data. These results underpin the potential of the simulator to become a secondary standard for millions of oscillometric sphygmomanometers.
Collapse
Affiliation(s)
- Stephan Mieke
- Retired from the Physikalisch-Technische Bundesanstalt, Abbestrasse 2-12, 10587 Berlin, Germany
| | - Alan Murray
- Engineering School and Medical Faculty, Newcastle University, Newcastle upon Tyne, United Kingdom
| |
Collapse
|
2
|
Manga S, Muthavarapu N, Redij R, Baraskar B, Kaur A, Gaddam S, Gopalakrishnan K, Shinde R, Rajagopal A, Samaddar P, Damani DN, Shivaram S, Dey S, Mitra D, Roy S, Kulkarni K, Arunachalam SP. Estimation of Physiologic Pressures: Invasive and Non-Invasive Techniques, AI Models, and Future Perspectives. SENSORS (BASEL, SWITZERLAND) 2023; 23:5744. [PMID: 37420919 DOI: 10.3390/s23125744] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/01/2023] [Revised: 05/25/2023] [Accepted: 06/12/2023] [Indexed: 07/09/2023]
Abstract
The measurement of physiologic pressure helps diagnose and prevent associated health complications. From typical conventional methods to more complicated modalities, such as the estimation of intracranial pressures, numerous invasive and noninvasive tools that provide us with insight into daily physiology and aid in understanding pathology are within our grasp. Currently, our standards for estimating vital pressures, including continuous BP measurements, pulmonary capillary wedge pressures, and hepatic portal gradients, involve the use of invasive modalities. As an emerging field in medical technology, artificial intelligence (AI) has been incorporated into analyzing and predicting patterns of physiologic pressures. AI has been used to construct models that have clinical applicability both in hospital settings and at-home settings for ease of use for patients. Studies applying AI to each of these compartmental pressures were searched and shortlisted for thorough assessment and review. There are several AI-based innovations in noninvasive blood pressure estimation based on imaging, auscultation, oscillometry and wearable technology employing biosignals. The purpose of this review is to provide an in-depth assessment of the involved physiologies, prevailing methodologies and emerging technologies incorporating AI in clinical practice for each type of compartmental pressure measurement. We also bring to the forefront AI-based noninvasive estimation techniques for physiologic pressure based on microwave systems that have promising potential for clinical practice.
Collapse
Affiliation(s)
- Sharanya Manga
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | - Neha Muthavarapu
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | - Renisha Redij
- GIH Artificial Intelligence Laboratory (GAIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | | | - Avneet Kaur
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | - Sunil Gaddam
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | - Keerthy Gopalakrishnan
- GIH Artificial Intelligence Laboratory (GAIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | - Rutuja Shinde
- Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | | | - Poulami Samaddar
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
| | - Devanshi N Damani
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55905, USA
- Department of Internal Medicine, Texas Tech University Health Science Center, El Paso, TX 79995, USA
| | - Suganti Shivaram
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN 55905, USA
| | - Shuvashis Dey
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
- Department of Electrical and Computer Engineering, North Dakota State University, Fargo, ND 58105, USA
| | - Dipankar Mitra
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
- Department of Computer Science, University of Wisconsin-La Crosse, La Crosse, WI 54601, USA
| | - Sayan Roy
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
- Department of Electrical Engineering and Computer Science, South Dakota Mines, Rapid City, SD 57701, USA
| | - Kanchan Kulkarni
- Centre de Recherche Cardio-Thoracique de Bordeaux, University of Bordeaux, INSERM, U1045, 33000 Bordeaux, France
- IHU Liryc, Heart Rhythm Disease Institute, Fondation Bordeaux Université, Bordeaux, 33600 Pessac, France
| | - Shivaram P Arunachalam
- GIH Artificial Intelligence Laboratory (GAIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
- Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
- Microwave Engineering and Imaging Laboratory (MEIL), Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
- Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
| |
Collapse
|
4
|
Argha A, Celler BG, Lovell NH. A Novel Automated Blood Pressure Estimation Algorithm Using Sequences of Korotkoff Sounds. IEEE J Biomed Health Inform 2021; 25:1257-1264. [PMID: 32750976 DOI: 10.1109/jbhi.2020.3012567] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
The use of automated non-invasive blood pressure (NIBP) measurement devices is growing, as they can be used without expertise, and BP measurement can be performed by patients at home. Non-invasive cuff-based monitoring is the dominant method for BP measurement. While the oscillometric technique is most common, a few automated NIBP measurement methods have been developed based on the auscultatory technique. Amongst artificial intelligence (AI) techniques, deep learning has received increasing attention in different fields due to its strength in data classification, and feature extraction problems. This paper proposes a novel automated AI-based technique for NIBP estimation from auscultatory waveforms (AWs) based on converting the NIBP estimation problem to a sequence-to-sequence classification problem. To do this, a sequence of segments was first formed by segmenting the AWs, and their corresponding decomposed detail, and approximation parts obtained by wavelet packet decomposition method, and extracting features from each segment. Then, a label was assigned to each segment, i.e. (i) between systolic, and diastolic segments, and (ii) otherwise, and a bidirectional long short term memory recurrent neural network (BiLSTM-RNN) was devised to solve the resulting sequence-to-sequence classification problem. Adopting a 5-fold cross-validation scheme, and using a data base of 350 NIBP recordings gave an average mean absolute error of 1.7±3.7 mmHg for systolic BP (SBP), and 3.4 ±5.0 mmHg for diastolic BP (DBP) relative to reference values. Based on the results achieved, and comparisons made with the existing literature, it is concluded that the proposed automated BP estimation algorithm based on deep learning methods, and auscultatory waveform brings plausible benefits to the field of BP estimation.
Collapse
|
9
|
Development of a Blood Pressure Measurement Instrument with Active Cuff Pressure Control Schemes. JOURNAL OF HEALTHCARE ENGINEERING 2017; 2017:9128745. [PMID: 29118964 PMCID: PMC5651164 DOI: 10.1155/2017/9128745] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/29/2017] [Revised: 07/31/2017] [Accepted: 08/29/2017] [Indexed: 11/21/2022]
Abstract
This paper presents an oscillometric blood pressure (BP) measurement approach based on the active control schemes of cuff pressure. Compared with conventional electronic BP instruments, the novelty of the proposed BP measurement approach is to utilize a variable volume chamber which actively and stably alters the cuff pressure during inflating or deflating cycles. The variable volume chamber is operated with a closed-loop pressure control scheme, and it is activated by controlling the piston position of a single-acting cylinder driven by a screw motor. Therefore, the variable volume chamber could significantly eliminate the air turbulence disturbance during the air injection stage when compared to an air pump mechanism. Furthermore, the proposed active BP measurement approach is capable of measuring BP characteristics, including systolic blood pressure (SBP) and diastolic blood pressure (DBP), during the inflating cycle. Two modes of air injection measurement (AIM) and accurate dual-way measurement (ADM) were proposed. According to the healthy subject experiment results, AIM reduced 34.21% and ADM reduced 15.78% of the measurement time when compared to a commercial BP monitor. Furthermore, the ADM performed much consistently (i.e., less standard deviation) in the measurements when compared to a commercial BP monitor.
Collapse
|
10
|
Abderahman HN, Dajani HR, Bolic M, Groza VZ. An integrated blood pressure measurement system for suppression of motion artifacts. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2017; 145:1-10. [PMID: 28552114 DOI: 10.1016/j.cmpb.2017.03.007] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/10/2016] [Revised: 02/20/2017] [Accepted: 03/01/2017] [Indexed: 06/07/2023]
Abstract
Accuracy in blood pressure (BP) estimation is essential for proper diagnosis and management of hypertension. Motion artifacts are considered external sources of inaccuracy and can be due to sudden arm motion, muscle tremor, shivering, and transport vehicle vibrations. In the proposed work, a new algorithmic stage is integrated in a non-invasive BP monitor. This stage suppresses the effect of the motion artifact and adjusts the pressure estimation before displaying it to users. The proposed stage is based on a 3-axis accelerometer signal, which helps in the accurate detection of the motion artifact. Both transient motion artifacts and artifact due to vibrations are suppressed using algorithms based on Empirical Mode Decomposition (EMD). Measurements with human subjects show that the proposed algorithms considerably improved the accuracy of the blood pressure estimates in comparison with the commonly-used conventional oscillometric algorithm that does not include an EMD-based stage for artifact suppression, and allowed the estimates to meet the requirements of the international ANSI/AAMI/ISO standard.
Collapse
Affiliation(s)
- Huthaifa N Abderahman
- School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada.
| | - Hilmi R Dajani
- School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada
| | - Miodrag Bolic
- School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada
| | - Voicu Z Groza
- School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada
| |
Collapse
|
11
|
Lee J, Ghasemi Z, Kim CS, Cheng HM, Chen CH, Sung SH, Mukkamala R, Hahn JO. Investigation of Viscoelasticity in the Relationship Between Carotid Artery Blood Pressure and Distal Pulse Volume Waveforms. IEEE J Biomed Health Inform 2017; 22:460-470. [PMID: 28237937 DOI: 10.1109/jbhi.2017.2672899] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
We investigated the relationship between carotid artery blood pressure (BP) and distal pulse volume waveforms (PVRs) via subject-specific mathematical modeling. We conceived three physical models to define the relationship: a tube-load model augmented with a gain (TLG), Voigt (TLV), and standard linear solid (TLS) models. We compared these models using PVRs measured via BP cuffs at an upper arm and an ankle as well as carotid artery tonometry waveform collected from 133 subjects. At both upper arm and ankle, PVR was related to carotid artery tonometry by TLV and TLS models better than by TLG model; when root-mean-squared over all the subjects, the systolic and diastolic BP errors between measured carotid artery tonometry waveform and the one estimated from distal PVR reduced from 4.3 mmHg and 4.6 mmHg (TLG) to 1.1 mmHg and 1.0 mmHg (TLS) for the upper arm (p < 0.0167), and from 2.1 mmHg and 1.7 mmHg (TLG) to 2.1 mmHg and 1.5 mmHg (TLV) for the ankle. Further, TLV and TLS models exhibited superior Akaike's Information Criterion (AIC) in both locations than TLG model. However, the difference between TLG versus TLV and TLS models associated with the ankle was not large. Therefore, the relationship of central arterial BP to arm PVR arises from both wave reflection and viscoelasticity while the relationship to ankle PVR mainly arises from wave reflection. These findings may imply that an effective subject-specific transfer function for estimating accurate central arterial BP from an arm PVR should account for the impact of viscoelasticity.
Collapse
|