scholarly journals A Comparison of Deep Learning Techniques for Arterial Blood Pressure Prediction

2021 ◽  
Author(s):  
Annunziata Paviglianiti ◽  
Vincenzo Randazzo ◽  
Stefano Villata ◽  
Giansalvo Cirrincione ◽  
Eros Pasero
Keyword(s):  
Blood Pressure ◽  
Neural Networks ◽  
Deep Learning ◽  
Arterial Blood Pressure ◽  
Blood Pressure Measurement ◽  
National Standards ◽  
Detection Methods ◽  
Physiological Parameter ◽  
Arterial Blood ◽  
Learning Techniques

AbstractContinuous vital signal monitoring is becoming more relevant in preventing diseases that afflict a large part of the world’s population; for this reason, healthcare equipment should be easy to wear and simple to use. Non-intrusive and non-invasive detection methods are a basic requirement for wearable medical devices, especially when these are used in sports applications or by the elderly for self-monitoring. Arterial blood pressure (ABP) is an essential physiological parameter for health monitoring. Most blood pressure measurement devices determine the systolic and diastolic arterial blood pressure through the inflation and the deflation of a cuff. This technique is uncomfortable for the user and may result in anxiety, and consequently affect the blood pressure and its measurement. The purpose of this paper is the continuous measurement of the ABP through a cuffless, non-intrusive approach. The approach of this paper is based on deep learning techniques where several neural networks are used to infer ABP, starting from photoplethysmogram (PPG) and electrocardiogram (ECG) signals. The ABP was predicted first by utilizing only PPG and then by using both PPG and ECG. Convolutional neural networks (ResNet and WaveNet) and recurrent neural networks (LSTM) were compared and analyzed for the regression task. Results show that the use of the ECG has resulted in improved performance for every proposed configuration. The best performing configuration was obtained with a ResNet followed by three LSTM layers: this led to a mean absolute error (MAE) of 4.118 mmHg on and 2.228 mmHg on systolic and diastolic blood pressures, respectively. The results comply with the American National Standards of the Association for the Advancement of Medical Instrumentation. ECG, PPG, and ABP measurements were extracted from the MIMIC database, which contains clinical signal data reflecting real measurements. The results were validated on a custom dataset created at Neuronica Lab, Politecnico di Torino.

GRANGER CAUSALITY ANALYSIS BETWEEN INTRA-OSSEOUS PRESSURE AND ARTERIAL BLOOD PRESSURE IN AFRICAN GREY PARROTS (PSITTACUS ERITHACUS)

2021 ◽  
pp. 1-8
Author(s):  
Yi-Tse Hsiao ◽  
Yun-Wen Peng ◽  
Pin Huan Yu
Keyword(s):  
Blood Pressure ◽  
Arterial Pressure ◽  
Granger Causality ◽  
Arterial Blood Pressure ◽  
Pressure Measurement ◽  
Direct Method ◽  
Blood Pressure Measurement ◽  
Rational Approach ◽  
Arterial Blood ◽  
The Relationship

Monitoring blood pressure helps a clinical veterinarian assess various conditions in birds. Blood pressure is not only a bio-indicator of renal or cardiovascular disease but is also a vital indicator for anesthesia. Anesthetic- and sedation-related mortality is higher in birds than dogs or cats. The traditional method of blood pressure measurement in mammals mainly relies on indirect methods. However, indirect blood pressure measurement is not reliable in birds, making the direct method the only gold standard. Although an arterial catheter can provide continuous real-time arterial pressure in birds, the method requires technical skill and is limited by bird size, and is thus not practical in birds with circulatory collapse. Intra-osseous (IO) blood pressure is potentially related to arterial pressure and may be a much easier and safer technique that is less limited by animal size. However, the relationship between IO pressure and arterial blood pressure has not been established. This study used mathematical methods to determine the relationship between IO pressure and arterial blood pressure. The Granger causality (G.C.) theory was applied in the study and used to analyze which pressure signal was leading the other. Our findings suggest that IO pressure is G.C. by arterial blood pressure; thus, the use of IO pressure measurements as an alternative to arterial blood pressure measurement is a rational approach.

Arterial Blood Pressure Measurement Technique

1993 ◽  
Vol 4 (1) ◽  
pp. 66-80 ◽  
Author(s):  
Deborah A. Gorny
Keyword(s):  
Blood Pressure ◽  
Arterial Blood Pressure ◽  
Measurement Technique ◽  
Blood Pressure Measurement ◽  
Direct Methods ◽  
Clinical Situation ◽  
Noninvasive Methods ◽  
Pulse Wave Amplitude ◽  
Arterial Blood ◽  
Arterial Blood Pressure Measurement

Arterial blood pressure (BP) measurements, which include invasive direct methods and noninvasive indirect methods, provide a picture of the hemodynamic status of the patient. Invasive BP methods measure pressure pulse wave amplitude; noninvasive methods rely on blood flow or arterial wall motion as a basis for the determination of BP values. To obtain the most accurate BP value, the clinician must identify which measurement variables in a specific clinical situation are most contributory to error and, if possible, use a method of measurement for which the sources of error are not parallel. Blood pressure values obtained by different methods cannot be compared without a thorough understanding of the user-related and instrumentation-related limitations associated with each BP measurement technique

scholarly journals Evaluation of the Accuracy of the Delta Life DL 1000 Oscillometric Monitor for Blood Pressure Measurement in Anesthetized Dogs of Different Weight Ranges

2020 ◽  
Vol 48 ◽  
Author(s):  
Bárbara Silva Correia ◽  
Eduardo Raposo Monteiro ◽  
João Victor Barbieri Ferronatto ◽  
Luciana Branquinho Queiroga ◽  
José Ricardo Herrera Becerra
Keyword(s):  
Blood Pressure ◽  
Arterial Blood Pressure ◽  
Pressure Measurement ◽  
Elective Surgery ◽  
Blood Pressure Measurement ◽  
Measurement Data ◽  
Arterial Blood ◽  
Anesthetized Dogs ◽  
Group 2 ◽  
Group 1

Background: Arterial blood pressure is one of the most commonly variables monitored during anesthetic procedures in veterinary patients. The most reliable method for measuring arterial blood pressure in dogs and cats is the direct (invasive) method. However, the oscillometric method is less complex and more practical for clinical routine in small animals. Nevertheless, oscillometric monitors present great variability in accuracy. The present study aimed to determine the accuracy of the Delta Life DL 1000 oscillometric monitor for measurement of systolic, mean and diastolic blood pressures (SAP, MAP and DAP, respectively) in anesthetized dogs of different weight ranges.Materials, Methods & Results: This study was approved by the Institutional Ethics Committee of Animal Use. Fifteen female dogs of different breeds, weighing 11.6 ± 10.0 kg and with a mean age of 48 ± 51 months were used. All animals were scheduled for elective surgery under general anesthesia in the Institution Veterinary Hospital. Dogs were anesthetized with morphine, propofol and isoflurane and had one 20 or 22 gauge catheter introduced into the dorsal pedal artery for continuous, invasive monitoring of SAP, MAP and DAP. A blood pressure cuff was positioned over the middle third of the radius and connected to Delta Life DL 1000 monitor. Oscillometric readings of SAP, MAP and DAP were registered every 5 minutes, and invasive values were simultaneously recorded. Values obtained with both methods were compared (invasive versus oscillometric) by use of the Bland Altman method to determine the bias, standard deviation of bias and 95% limits of agreement. The percentages of errors between the methods within 10 mmHg and within 20 mmHg were calculated. The results obtained were compared with the criteria from the American College of Veterinary Internal Medicine (ACVIM) for validation of indirect methods of arterial blood pressure measurement. Data were stratified into two groups according to the weight: < 10 kg (Group 1; n = 9); and ≥ 10 kg (Group 2; n = 6). In Group 1, 119 paired measurements were obtained, four of which classified as hypotension (SAP < 90 mmHg), 98 as normotension (SAP from 90 to 140mmHg) and 17 as hypertension (SAP > 140 mmHg). Bias (± SD) values in Group 1 were as follows: SAP, 5.2 ± 18.1 mmHg; MAP, -3.4 ± 17.2 mmHg; and DAP, 12.0 ± 17.5 mmHg. The percentages of errors within 10 mmHg were 40.3% for SAP; 45.4% for MAP and 28.6% for DAP. The percentages of errors within 20 mmHg were 72.3% for SAP, 84.0% for MAP and 68.1% for DAP. In Group 2, 66 paired measurements were obtained, nine of which classified as hypotension, 56 as normotension and one as hypertension. Bias (± SD) in Group 2 were as follows: SAP, 13.6 ± 14.3 mmHg; MAP, -1.1 ± 13.5 mmHg; and DAP, 8.2 ± 16.0 mmHg. The percentages of errors within 10 mmHg were 33.3% for SAP, 77.3% for MAP and 33.3% for DAP. The percentages of errors within 20 mmHg were 65.1% for SAP, 92.4% for MAP and 83.4% for DAP.Discussion: Based on the results of this study and reference criteria from the ACVIM, the Delta Life DL 1000 monitor had a poor accuracy for SAP, MAP and DAP and did not meet the criteria from the ACVIM in anesthetized dogs under 10 kg. Measurements of MAP in dogs ≥ 10 kg met the ACVIM criteria, but measurements of SAP and DAP did not. Based on the findings in this study, the DL 1000 oscillometric monitor is not recommended for blood pressure measurement in anesthetized dogs < 10 kg. In dogs ≥ 10 kg, measurements of MAP yielded acceptable values, but SAP and DAP measurements did not.

Sign in / Sign up

Export Citation Format

Share Document