scholarly journals Blood Pressure Continuous Measurement through a Wearable Device: Development and Validation of a Cuffless Method

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7334
Author(s):  
Beatrice De Marchi ◽  
Mattia Frigerio ◽  
Silvia De Nadai ◽  
Gianluigi Longinotti-Buitoni ◽  
Andrea Aliverti
Keyword(s):  
Blood Pressure ◽  
Time Delay ◽  
Continuous Measurement ◽  
Model Performance ◽  
Absolute Error ◽  
International Standards ◽  
Wearable Device ◽  
Time Relation ◽  
Marker Point ◽  
Peripheral Site

The present study aims to develop and validate a cuffless method for blood pressure continuous measurement through a wearable device. The goal is achieved according to the time-delay method, with the guiding principle of the time relation it takes for a blood volume to travel from the heart to a peripheral site. Inversely proportional to the blood pressure, this time relation is obtained as the time occurring between the R peak of the electrocardiographic signal and a marker point on the photoplethysmographic wave. Such physiological signals are recorded by using L.I.F.E. Italia’s wearable device, made of a sensorized shirt and wristband. A linear regression model is implemented to estimate the corresponding blood pressure variations from the obtained time-delay and other features of the photoplethysmographic wave. Then, according to the international standards, the model performance is assessed, comparing the estimates with the measurements provided by a certified digital sphygmomanometer. According to the standards, the results obtained during this study are notable, with 85% of the errors lower than 10 mmHg and a mean absolute error lower than 7 mmHg. In conclusion, this study suggests a time-delay method for continuous blood pressure estimates with good performance, compared with a reference device based on the oscillometric technique.

scholarly journals Non-invasive cuff-less blood pressure estimation using a hybrid deep learning model

2021 ◽  
Vol 53 (2) ◽  
Author(s):  
Sen Yang ◽  
Yaping Zhang ◽  
Siu-Yeung Cho ◽  
Ricardo Correia ◽  
Stephen P. Morgan
Keyword(s):  
Machine Learning ◽  
Blood Pressure ◽  
Deep Learning ◽  
Absolute Error ◽  
Learning Model ◽  
Physiological Measurement ◽  
British Hypertension Society ◽  
Non Invasive ◽  
Blood Pressure Estimation ◽  
Deep Learning Model

AbstractConventional blood pressure (BP) measurement methods have different drawbacks such as being invasive, cuff-based or requiring manual operations. There is significant interest in the development of non-invasive, cuff-less and continual BP measurement based on physiological measurement. However, in these methods, extracting features from signals is challenging in the presence of noise or signal distortion. When using machine learning, errors in feature extraction result in errors in BP estimation, therefore, this study explores the use of raw signals as a direct input to a deep learning model. To enable comparison with the traditional machine learning models which use features from the photoplethysmogram and electrocardiogram, a hybrid deep learning model that utilises both raw signals and physical characteristics (age, height, weight and gender) is developed. This hybrid model performs best in terms of both diastolic BP (DBP) and systolic BP (SBP) with the mean absolute error being 3.23 ± 4.75 mmHg and 4.43 ± 6.09 mmHg respectively. DBP and SBP meet the Grade A and Grade B performance requirements of the British Hypertension Society respectively.

scholarly journals Continuous Blood Pressure Estimation Using Exclusively Photopletysmography by LSTM-Based Signal-to-Signal Translation

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2952
Author(s):  
Latifa Nabila Harfiya ◽  
Ching-Chun Chang ◽  
Yung-Hui Li
Keyword(s):  
Blood Pressure ◽  
Absolute Error ◽  
Estimation Methods ◽  
British Hypertension Society ◽  
Arterial Blood ◽  
Proposed Model ◽  
Pressure Estimation ◽  
Effective Signal ◽  
Blood Pressure Estimation ◽  
Continuous Blood Pressure

Monitoring continuous BP signal is an important issue, because blood pressure (BP) varies over days, minutes, or even seconds for short-term cases. Most of photoplethysmography (PPG)-based BP estimation methods are susceptible to noise and only provides systolic blood pressure (SBP) and diastolic blood pressure (DBP) prediction. Here, instead of estimating a discrete value, we focus on different perspectives to estimate the whole waveform of BP. We propose a novel deep learning model to learn how to perform signal-to-signal translation from PPG to arterial blood pressure (ABP). Furthermore, using a raw PPG signal only as the input, the output of the proposed model is a continuous ABP signal. Based on the translated ABP signal, we extract the SBP and DBP values accordingly to ease the comparative evaluation. Our prediction results achieve average absolute error under 5 mmHg, with 70% confidence for SBP and 95% confidence for DBP without complex feature engineering. These results fulfill the standard from Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS) with grade A. From the results, we believe that our model is applicable and potentially boosts the accuracy of an effective signal-to-signal continuous blood pressure estimation.

scholarly journals An Estimation Method of Continuous Non-Invasive Arterial Blood Pressure Waveform Using Photoplethysmography: A U-Net Architecture-Based Approach

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1867
Author(s):  
Tasbiraha Athaya ◽  
Sunwoong Choi
Keyword(s):  
Blood Pressure ◽  
Cardiovascular Health ◽  
Estimation Method ◽  
Absolute Error ◽  
British Hypertension Society ◽  
Non Invasive ◽  
Arterial Blood ◽  
Blood Pressure Waveform ◽  
The Mean ◽  
Mimic Iii

Blood pressure (BP) monitoring has significant importance in the treatment of hypertension and different cardiovascular health diseases. As photoplethysmogram (PPG) signals can be recorded non-invasively, research has been highly conducted to measure BP using PPG recently. In this paper, we propose a U-net deep learning architecture that uses fingertip PPG signal as input to estimate arterial BP (ABP) waveform non-invasively. From this waveform, we have also measured systolic BP (SBP), diastolic BP (DBP), and mean arterial pressure (MAP). The proposed method was evaluated on a subset of 100 subjects from two publicly available databases: MIMIC and MIMIC-III. The predicted ABP waveforms correlated highly with the reference waveforms and we have obtained an average Pearson’s correlation coefficient of 0.993. The mean absolute error is 3.68 ± 4.42 mmHg for SBP, 1.97 ± 2.92 mmHg for DBP, and 2.17 ± 3.06 mmHg for MAP which satisfy the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) standard and obtain grade A according to the British Hypertension Society (BHS) standard. The results show that the proposed method is an efficient process to estimate ABP waveform directly using fingertip PPG.

scholarly journals A Novel Neural Network Model for Blood Pressure Estimation Using Photoplethesmography without Electrocardiogram

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Ludi Wang ◽  
Wei Zhou ◽  
Ying Xing ◽  
Xiaoguang Zhou
Keyword(s):  
Neural Network ◽  
Blood Pressure ◽  
Mean Absolute Error ◽  
Wearable Sensors ◽  
Absolute Error ◽  
Noninvasive Estimation ◽  
Treatment Of Hypertension ◽  
The Mean ◽  
Artificial Neural Network Ann ◽  
Blood Pressure Estimation

The prevention, evaluation, and treatment of hypertension have attracted increasing attention in recent years. As photoplethysmography (PPG) technology has been widely applied to wearable sensors, the noninvasive estimation of blood pressure (BP) using the PPG method has received considerable interest. In this paper, a method for estimating systolic and diastolic BP based only on a PPG signal is developed. The multitaper method (MTM) is used for feature extraction, and an artificial neural network (ANN) is used for estimation. Compared with previous approaches, the proposed method obtains better accuracy; the mean absolute error is 4.02 ± 2.79 mmHg for systolic BP and 2.27 ± 1.82 mmHg for diastolic BP.

Is a Head-Worn Inertial Sensor a Valid Tool to Monitor Swimming?

2021 ◽  
pp. 1-4
Author(s):  
Stephanie J. Shell ◽  
Brad Clark ◽  
James R. Broatch ◽  
Katie Slattery ◽  
Shona L. Halson ◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Video Analysis ◽  
Inertial Sensor ◽  
Absolute Error ◽  
Wearable Device ◽  
Measurement Unit ◽  
Fisher Exact Test ◽  
Mean Velocity ◽  
Video Footage ◽  
Stroke Type

Purpose: This study aimed to independently validate a wearable inertial sensor designed to monitor training and performance metrics in swimmers. Methods: A total of 4 male (21 [4] y, 1 national and 3 international) and 6 female (22 [3] y, 1 national and 5 international) swimmers completed 15 training sessions in an outdoor 50-m pool. Swimmers were fitted with a wearable device (TritonWear, 9-axis inertial measurement unit with triaxial accelerometer, gyroscope, and magnetometer), placed under the swim cap on top of the occipital protuberance. Video footage was captured for each session to establish criterion values. Absolute error, standardized effect, and Pearson correlation coefficient were used to determine the validity of the wearable device against video footage for total swim distance, total stroke count, mean stroke count, and mean velocity. A Fisher exact test was used to analyze the accuracy of stroke-type identification. Results: Total swim distance was underestimated by the device relative to video analysis. Absolute error was consistently higher for total and mean stroke count, and mean velocity, relative to video analysis. Across all sessions, the device incorrectly detected total time spent in backstroke, breaststroke, butterfly, and freestyle by 51% (15%). The device did not detect time spent in drill. Intraclass correlation coefficient results demonstrated excellent intrarater reliability between repeated measures across all swimming metrics. Conclusions: The wearable device investigated in this study does not accurately measure distance, stroke count, and velocity swimming metrics or detect stroke type. Its use as a training monitoring tool in swimming is limited.

Abstract P211: Prediction of Stroke in a Population with High Prevalence of Diabetes: The Strong Heart Study

Circulation ◽  
2013 ◽  
Vol 127 (suppl_12) ◽  
Author(s):  
Ying Zhang ◽  
Wenyu Wang ◽  
Elisa T Lee ◽  
Thomas K Welty ◽  
Jorge R Kizer ◽  
...  
Keyword(s):  
Risk Factors ◽  
Blood Pressure ◽  
American Indians ◽  
Prediction Models ◽  
Model Performance ◽  
Prediction Equation ◽  
Prediction Equations ◽  
Strong Heart Study ◽  
Discrimination Ability ◽  
Heart Study

Background— Stroke prediction models are valuable to physicians in evaluating the risk of their patients so that preventive interventions can be promoted. The Framingham Risk Profile is a widely used stroke prediction equation. However, the contributions of some common risk factors for stroke vary across populations and some risk factors are specific to certain populations. For example, albuminuria is an important risk factor in American Indians (AIs), which is not included in the Framingham equation. The objective of the current study is to develop stroke prediction equations using routinely collected variables in AIs, a population with high rates of diabetes and stroke. Methods— The data used in the analysis are from 4507 stroke free participants at enrollment in the Strong Heart Study (SHS), the largest population-based longitudinal study of cardiovascular disease (CVD) and its risk factors in AIs in Arizona, Oklahoma, and South/North Dakota. As of December 2008, 379/4507 (8.4%) participants suffered a first stroke during an average follow-up of 17 years. Baseline potential risk factors were included in the Cox proportional-hazard models to develop gender-specific prediction equations. Backward selection was used to choose the predictors. Model performance was assessed using Harrell’s C statistics based on bootstrapping methods. Results— Baseline age, untreated systolic blood pressure, treated diastolic blood pressure, HDL-C, current smoking, diabetes, macro-albuminuria, and history of CVD are significant predictors for incident stroke among women. Most of these predictors except HDL-C were also in the prediction equation for men. The equations provided good discrimination ability, as indicated by a C statistic of 0.72 for men and 0.73 for women. Conclusions— Predicted risk of stroke in 10 years can be provided for physicians and their patients. Then appropriate intervention can be implemented. The stroke prediction equations from SHS can be applied to other AIs as well as other ethnic groups with high rates of diabetes and albuminuria.

Forecasting Of Covid-19 Cases Using Machine Learning Approach

2021 ◽  
Vol 17 ◽  
Author(s):  
Sachin Kumar ◽  
Karan Veer
Keyword(s):  
Machine Learning ◽  
Regression Model ◽  
Model Performance ◽  
Real Data ◽  
Absolute Error ◽  
Viral Disease ◽  
Support Vector ◽  
Family Welfare ◽  
Accuracy Score ◽  
Learning Approaches

Aims: The objective of this research is to predict the covid-19 cases in India based on the machine learning approaches. Background: Covid-19, a respiratory disease caused by one of the coronavirus family members, has led to a pandemic situation worldwide in 2020. This virus was detected firstly in Wuhan city of China in December 2019. This viral disease has taken less than three months to spread across the globe. Objective: In this paper, we proposed a regression model based on the Support vector machine (SVM) to forecast the number of deaths, the number of recovered cases, and total confirmed cases for the next 30 days. Method: For prediction, the data is collected from Github and the ministry of India's health and family welfare from March 14, 2020, to December 3, 2020. The model has been designed in Python 3.6 in Anaconda to forecast the forecasting value of corona trends until September 21, 2020. The proposed methodology is based on the prediction of values using SVM based regression model with polynomial, linear, rbf kernel. The dataset has been divided into train and test datasets with 40% and 60% test size and verified with real data. The model performance parameters are evaluated as a mean square error, mean absolute error, and percentage accuracy. Results and Conclusion: The results show that the polynomial model has obtained 95 % above accuracy score, linear scored above 90%, and rbf scored above 85% in predicting cumulative death, conformed cases, and recovered cases.

scholarly journals Reconstruction of Multidecadal Country-Aggregated Hydro Power Generation in Europe Based on a Random Forest Model

Energies ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 1786
Author(s):  
Linh T. T. Ho ◽  
Laurent Dubus ◽  
Matteo De Felice ◽  
Alberto Troccoli
Keyword(s):  
Power Generation ◽  
Random Forest ◽  
Model Performance ◽  
Absolute Error ◽  
Random Forest Model ◽  
Low Carbon ◽  
Climate Data ◽  
Hydro Power ◽  
Forest Model ◽  
Continental Scale

Hydro power can provide a source of dispatchable low-carbon electricity and a storage solution in a climate-dependent energy mix with high shares of wind and solar production. Therefore, understanding the effect climate has on hydro power generation is critical to ensure a stable energy supply, particularly at a continental scale. Here, we introduce a framework using climate data to model hydro power generation at the country level based on a machine learning method, the random forest model, to produce a publicly accessible hydro power dataset from 1979 to present for twelve European countries. In addition to producing a consistent European hydro power generation dataset covering the past 40 years, the specific novelty of this approach is to focus on the lagged effect of climate variability on hydro power. Specifically, multiple lagged values of temperature and precipitation are used. Overall, the model shows promising results, with the correlation values ranging between 0.85 and 0.98 for run-of-river and between 0.73 and 0.90 for reservoir-based generation. Compared to the more standard optimal lag approach the normalised mean absolute error reduces by an average of 10.23% and 5.99%, respectively. The model was also implemented over six Italian bidding zones to also test its skill at the sub-country scale. The model performance is only slightly degraded at the bidding zone level, but this also depends on the actual installed capacity, with higher capacities displaying higher performance. The framework and results presented could provide a useful reference for applications such as pan-European (continental) hydro power planning and for system adequacy and extreme events assessments.

scholarly journals A Comparison of Models for Estimating Solar Radiation from Sunshine Duration in Croatia

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Tihomir Betti ◽  
Ivana Zulim ◽  
Slavica Brkić ◽  
Blanka Tuka
Keyword(s):  
Mean Absolute Error ◽  
Sunshine Duration ◽  
Model Performance ◽  
Absolute Error ◽  
Mean Bias Error ◽  
Percentage Error ◽  
Bias Error ◽  
Mean Square ◽  
Using Data ◽  
Statistical Indicators

The performance of seventeen sunshine-duration-based models has been assessed using data from seven meteorological stations in Croatia. Conventional statistical indicators are used as numerical indicators of the model performance: mean absolute percentage error (MAPE), mean bias error (MBE), mean absolute error (MAE), and root-mean-square error (RMSE). The ranking of the models was done using the combination of all these parameters, all having equal weights. The Rietveld model was found to perform the best overall, followed by Soler and Dogniaux-Lemoine monthly dependent models. For three best-performing models, new adjusted coefficients are calculated, and they are validated using separate dataset. Only the Dogniaux-Lemoine model performed better with adjusted coefficients, but across all analysed locations, the adjusted models showed improvement in reduced maximum percentage error.

scholarly journals A New Wearable Device for Blood Pressure Estimation Using Photoplethysmogram

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2557 ◽  
Author(s):  
Remo Lazazzera ◽  
Yassir Belhaj ◽  
Guy Carrault
Keyword(s):  
Blood Pressure ◽  
Real Time ◽  
American Association ◽  
Index Finger ◽  
Pulse Transit Time ◽  
Estimation Algorithm ◽  
Wearable Device ◽  
Medical Instrumentation ◽  
Blood Pressure Estimation ◽  
Pulse Oximeters

We present a novel smartwatch, CareUp ® , for estimating the Blood Pressure (BP) in real time. It consists of two pulse oximeters: one placed on the back and one on the front of the device. Placing the index finger on the front oximeter starts the acquisition of two photoplethysmograms (PPG); the signals are then filtered and cross-correlated to obtain a Time Delay between them, called Pulse Transit Time (PTT). The Heart Rate (HR) (estimated from the finger PPG) and the PTT are then input in a linear model to give an estimation of the Systolic and Diastolic BP. The performance of the smartwatch in measuring BP have been validated in the Institut Coeur Paris Centre Turin (ICPC), using a sphygmomanometer, on 44 subjects. During the validation, the measures of the CareUp ® were compared to those of two oscillometry-based devices already available on the market: Thuasne ® and Magnien ® . The results showed an accuracy comparable to the oscillometry-based devices and they almost agreed with the American Association for the Advancement of Medical Instrumentation standard for non-automated sphygmomanometers. The integration of the BP estimation algorithm in the smartwatch makes the CareUp ® an easy-to-use, wearable device for monitoring the BP in real time.

Sign in / Sign up

Export Citation Format

Share Document