Predicting blood pressure from physiological index data using the SVR algorithm

Study on the relationship between body mass index and blood pressure indices in children aged 7-17 during COVID-19

Background

To explore the relationship between body mass index (BMI), age, sex, and blood pressure (systolic blood pressure, SBP; diastolic blood pressure, DBP) in children during COVID-19, providing reference for the prevention and screening of hypertension in children.

Methods

This study adopted a large-scale cross-sectional design to investigate the association between BMI and blood pressure in 7-17-year-old students in City N, China, during COVID-19. Thirty-six primary and secondary schools in City N were sampled using a stratified cluster sampling method. A total of 11,433 students aged 7-17 years in City N, China, were selected for blood pressure (Diastolic blood pressure, DBP, Systolic blood pressure, SBP), height, and weight, Resting heart rate (RHR), chest circumference, measurements, and the study was written using the STROBE checklist. Data analysis was conducted using SPSS 26.0, calculating the mean and standard deviation of BMI and blood pressure for male and female students in different age groups. Regression analysis was employed to explore the impact of BMI, age, and sex on SBP and DBP, and predictive models were established. The model fit was evaluated using the model R2.

Results

The study included 11,287 primary and secondary school students, comprising 5,649 boys and 5,638 girls. It was found that with increasing age, BMI and blood pressure of boys and girls generally increased. There were significant differences in blood pressure levels between boys and girls in different age groups. In regression models, LC, Age, BMI, and chest circumference show significant positive linear relationships with SBP and DBP in adolescents, while RHR exhibits a negative linear relationship with SBP. These factors were individually incorporated into a stratified regression model, significantly enhancing the model's explanatory power. After including factors such as Age, Gender, and BMI, the adjusted R2 value showed a significant improvement, with Age and BMI identified as key predictive factors for SBP and DBP. The robustness and predictive accuracy of the model were further examined through K-fold cross-validation and independent sample validation methods. The validation results indicate that the model has a high accuracy and explanatory power in predicting blood pressure in children of different weight levels, especially among obese children, where the prediction accuracy is highest.

Conclusion

During COVID-19, age, sex, and BMI significantly influence blood pressure in children aged 7-17 years, and predictive models for SBP and DBP were established. This model helps predict blood pressure in children and reduce the risk of cardiovascular diseases. Confirmation of factors such as sex, age, and BMI provide a basis for personalized health plans for children, especially during large-scale infectious diseases, providing guidance for addressing health challenges and promoting the health and well-being of children.

DMF-Net: a deep multi-level semantic fusion network for high-resolution chest CT and X-ray image de-noising

Medical images such as CT and X-ray have been widely used for the detection of several chest infections and lung diseases. However, these images are susceptible to different types of noise, and it is hard to remove these noises due to their complex distribution. The presence of such noise significantly deteriorates the quality of the images and significantly affects the diagnosis performance. Hence, the design of an effective de-noising technique is highly essential to remove the noise from chest CT and X-ray images prior to further processing. Deep learning methods, mainly, CNN have shown tremendous progress on de-noising tasks. However, existing CNN based models estimate the noise from the final layers, which may not carry adequate details of the image. To tackle this issue, in this paper a deep multi-level semantic fusion network is proposed, called DMF-Net for the removal of noise from chest CT and X-ray images. The DMF-Net mainly comprises of a dilated convolutional feature extraction block, a cascaded feature learning block (CFLB) and a noise fusion block (NFB) followed by a prominent feature extraction block. The CFLB cascades the features from different levels (convolutional layers) which are later fed to NFB to attain correct noise prediction. Finally, the Prominent Feature Extraction Block(PFEB) produces the clean image. To validate the proposed de-noising technique, a separate and a mixed dataset containing high-resolution CT and X-ray images with specific and blind noise are used. Experimental results indicate the effectiveness of the DMF-Net compared to other state-of-the-art methods in the context of peak signal-to-noise ratio (PSNR) and structural similarity measurement (SSIM) while drastically cutting down on the processing power needed.

Hypothesis Scoring for Confidence-Aware Blood Pressure Estimation With Particle Filters

We propose our Confidence-Aware Particle Filter (CAPF) framework that analyzes a series of estimated changes in blood pressure (BP) to provide several true state hypotheses for a given instance. Particularly, our novel confidence-awareness mechanism assigns likelihood scores to each hypothesis in an effort to discard potentially erroneous measurements - based on the agreement amongst a series of estimated changes and the physiological plausibility when considering DBP/SBP pairs. The particle filter formulation (or sequential Monte Carlo method) can jointly consider the hypotheses and their probabilities over time to provide a stable trend of estimated BP measurements. In this study, we evaluate BP trend estimation from an emerging bio-impedance (Bio-Z) prototype wearable modality although it is applicable to all types of physiological modalities. Each subject in the evaluation cohort underwent a hand-gripper exercise, a cold pressor test, and a recovery state to increase the variation to the captured BP ranges. Experiments show that CAPF yields superior continuous pulse pressure (PP), diastolic blood pressure (DBP), and systolic blood pressure (SBP) estimation performance compared to ten baseline approaches. Furthermore, CAPF performs on track to comply with AAMI and BHS standards for achieving a performance classification of Grade A, with mean error accuracies of -0.16 ± 3.75 mmHg for PP (r = 0.81), 0.42 ± 4.39 mmHg for DBP (r = 0.92), and -0.09 ± 6.51 mmHg for SBP (r = 0.92) from more than test 3500 data points.

Survey and Evaluation of Hypertension Machine Learning Research

Background Machine learning (ML) is pervasive in all fields of research, from automating tasks to complex decision-making. However, applications in different specialities are variable and generally limited. Like other conditions, the number of studies employing ML in hypertension research is growing rapidly. In this study, we aimed to survey hypertension research using ML, evaluate the reporting quality, and identify barriers to ML's potential to transform hypertension care. Methods and Results The Harmonious Understanding of Machine Learning Analytics Network survey questionnaire was applied to 63 hypertension-related ML research articles published between January 2019 and September 2021. The most common research topics were blood pressure prediction (38%), hypertension (22%), cardiovascular outcomes (6%), blood pressure variability (5%), treatment response (5%), and real-time blood pressure estimation (5%). The reporting quality of the articles was variable. Only 46% of articles described the study population or derivation cohort. Most articles (81%) reported at least 1 performance measure, but only 40% presented any measures of calibration. Compliance with ethics, patient privacy, and data security regulations were mentioned in 30 (48%) of the articles. Only 14% used geographically or temporally distinct validation data sets. Algorithmic bias was not addressed in any of the articles, with only 6 of them acknowledging risk of bias. Conclusions Recent ML research on hypertension is limited to exploratory research and has significant shortcomings in reporting quality, model validation, and algorithmic bias. Our analysis identifies areas for improvement that will help pave the way for the realization of the potential of ML in hypertension and facilitate its adoption.

Hybrid CNN-SVR Blood Pressure Estimation Model Using ECG and PPG Signals

Continuous blood pressure (BP) measurement is vital in monitoring patients' health with a high risk of cardiovascular disease. The complex and dynamic nature of the cardiovascular system can influence BP through many factors, such as cardiac output, blood vessel wall elasticity, circulated blood volume, peripheral resistance, respiration, and emotional behavior. Yet, traditional BP measurement methods in continuously estimating the BP are cumbersome and inefficient. This paper presents a novel hybrid model by integrating a convolutional neural network (CNN) as a trainable feature extractor and support vector regression (SVR) as a regression model. This model can automatically extract features from the electrocardiogram (ECG) and photoplethysmography (PPG) signals and continuously estimates the systolic blood pressure (SBP) and diastolic blood pressure (DBP). The CNN takes the correct topology of input data and establishes the relationship between ECG and PPG features and BP. A total of 120 patients with available ECG, PPG, SBP, and DBP data are selected from the MIMIC III database to evaluate the performance of the proposed model. This novel model achieves an overall Mean Absolute Error (MAE) of 1.23 ± 2.45 mmHg (MAE ± STD) for SBP and 3.08 ± 5.67 for DBP, all of which comply with the accuracy requirements of the AAMI SP10 standard.

Empirical analyses and simulations showed that different machine and statistical learning methods had differing performance for predicting blood pressure

Machine learning is increasingly being used to predict clinical outcomes. Most comparisons of different methods have been based on empirical analyses in specific datasets. We used Monte Carlo simulations to determine when machine learning methods perform better than statistical learning methods in a specific setting. We evaluated six learning methods: stochastic gradient boosting machines using trees as the base learners, random forests, artificial neural networks, the lasso, ridge regression, and linear regression estimated using ordinary least squares (OLS). Our simulations were informed by empirical analyses in patients with acute myocardial infarction (AMI) and congestive heart failure (CHF) and used six data-generating processes, each based on one of the six learning methods, to simulate continuous outcomes in the derivation and validation samples. The outcome was systolic blood pressure at hospital discharge, a continuous outcome. We applied the six learning methods in each of the simulated derivation samples and evaluated performance in the simulated validation samples. The primary observation was that neural networks tended to result in estimates with worse predictive accuracy than the other five methods in both disease samples and across all six data-generating processes. Boosted trees and OLS regression tended to perform well across a range of scenarios.

Soft Transducer for Patient's Vitals Telemonitoring with Deep Learning-Based Personalized Anomaly Detection

This work addresses the design, development and implementation of a 4.0-based wearable soft transducer for patient-centered vitals telemonitoring. In particular, first, the soft transducer measures hypertension-related vitals (heart rate, oxygen saturation and systolic/diastolic pressure) and sends the data to a remote database (which can be easily consulted both by the patient and the physician). In addition to this, a dedicated deep learning algorithm, based on a Long-Short-Term-Memory Autoencoder, was designed, implemented and tested for providing an alert when the patient’s vitals exceed certain thresholds, which are automatically personalized for the specific patient. Furthermore, a mobile application (EcO2u) was developed to manage the entire data flow and facilitate the data fruition; this application also implements an innovative face-detection algorithm that ensures the identity of the patient. The robustness of the proposed soft transducer was validated experimentally on five individuals, who used the system for 30 days. The experimental results demonstrated an accuracy in anomaly detection greater than 93%, with a true positive rate of more than 94%.

Continuous Blood Pressure Estimation From Non-Invasive Measurements Using Support Vector Regression

Blood pressure (BP) is one of the most crucial vital signs of the human body that can be assessed as a critical risk factor for severe health conditions such as cardiovascular diseases (CVD) and hypertension. An accurate, continuous, and cuff-less BP monitoring technique could help clinicians improve the prevention, detection, and diagnosis of hypertension and manage related treatment plans. Notably, the complex and dynamic nature of the cardiovascular system necessitates that any BP monitoring system could benefit from an intelligent technology that can extract and analyze compelling BP features. In this study, a support vector regression (SVR) model was developed to estimate systolic blood pressure (SBP) and diastolic blood pressure (DBP) continuously. We selected a set of features commonly used in previous studies to train the proposed SVR model. A total of 120 patients with available ECG, PPG, DBP and SBP data were chosen from the Medical Information Mart for Intensive Care (MIMIC III) dataset to validate the proposed model. The results showed that the average root mean square error (RMSE) of 2.37 mmHg and 4.18 mmHg were achieved for SBP and DBP, respectively.

Imputation of the continuous arterial line blood pressure waveform from non-invasive measurements using deep learning

In two-thirds of intensive care unit (ICU) patients and 90% of surgical patients, arterial blood pressure (ABP) is monitored non-invasively but intermittently using a blood pressure cuff. Since even a few minutes of hypotension increases the risk of mortality and morbidity, for the remaining (high-risk) patients ABP is measured continuously using invasive devices, and derived values are extracted from the recorded waveforms. However, since invasive monitoring is associated with major complications (infection, bleeding, thrombosis), the ideal ABP monitor should be both non-invasive and continuous. With large volumes of high-fidelity physiological waveforms, it may be possible today to impute a physiological waveform from other available signals. Currently, the state-of-the-art approaches for ABP imputation only aim at intermittent systolic and diastolic blood pressure imputation, and there is no method that imputes the continuous ABP waveform. Here, we developed a novel approach to impute the continuous ABP waveform non-invasively using two continuously-monitored waveforms that are currently part of the standard-of-care, the electrocardiogram (ECG) and photo-plethysmogram (PPG), by adapting a deep learning architecture designed for image segmentation. Using over 150,000 min of data collected at two separate health systems from 463 patients, we demonstrate that our model provides a highly accurate prediction of the continuous ABP waveform (root mean square error 5.823 (95% CI 5.806–5.840) mmHg), as well as the derived systolic (mean difference 2.398 ± 5.623 mmHg) and diastolic blood pressure (mean difference − 2.497 ± 3.785 mmHg) compared to arterial line measurements. Our approach can potentially be used to measure blood pressure continuously and non-invasively for all patients in the acute care setting, without the need for any additional instrumentation beyond the current standard-of-care.

Non-invasive cuff-less blood pressure machine learning algorithm using photoplethysmography and prior physiological data

Conventional blood pressure (BP) measurement methods have a number of drawbacks such as being invasive, cuff-based or requiring manual operation. Many studies are focussed on emerging methods of noninvasive, cuff-less and continuous BP measurement, and using only photoplethysmography to estimate BP has become popular. Although it is well known that physiological characteristics of the subject are important in BP estimation, this has not been widely explored. This article presents a novel method which adopts photoplethysmography and prior knowledge of a subject's physiological features to estimate DBP and SBP. Features extracted from a fingertip photoplethysmography signal and prior knowledge of a subject's physiological characteristics, such as gender, age, height, weight and BMI is used to estimate BP using three different machine learning models: artificial neural networks, support vector machine and least absolute shrinkage and selection operator regression. The accuracy of BP estimation obtained when prior knowledge of the physiological characteristics are incorporated into the model is superior to those which do not take the physiological characteristics into consideration. In this study, the best performing algorithm is an artificial neural network which obtains a mean absolute error and SD of 4.74 ± 5.55 mm Hg for DBP and 9.18 ± 12.57 mm Hg for SBP compared to 6.61 ± 8.04 mm Hg for DBP and 11.12 ± 14.20 mm Hg for SBP without prior knowledge. The inclusion of prior knowledge of the physiological characteristics can improve the accuracy of BP estimation using machine learning methods, and the incorporation of more physiological characteristics enhances the accuracy of the BP estimation.

Learning and non-learning algorithms for cuffless blood pressure measurement: a review

The machine learning approach has gained a significant attention in the healthcare sector because of the prospect of developing new techniques for medical devices and handling the critical database of chronic diseases. The learning approach has potential to analyze complex medical data, disease diagnosis, and patient monitoring system, and to monitor e-health record. Non-invasive cuffless blood pressure (CLBP) measurement secured a significant position in the patient monitoring system. From a few recent decades, the importance of cuffless technology has been perceived towards continuous monitoring of blood pressure (BP) and supplementary efforts have been made towards its continuous monitoring. However, the optimal method that measures BP unambiguously and continuously has not yet emerged along with issues like calibration time, accuracy and long-term estimation of BP with miniaturizing hardware. The present study provides an insight into several learning algorithms along with their feature selection models. Various challenges and future improvements towards the current state of machine learning in healthcare industries are discussed in the present review. The bottom line of this study is to provide a comprehensive perspective of the machine learning approach of CLBP for the generation of highly precise predictive models for continuous BP measurement.

A novel method of trans-esophageal Doppler cardiac output monitoring utilizing peripheral arterial pulse contour with/without machine learning approach

Transesophageal Doppler (TED) velocity in the descending thoracic aorta (DA) is used to track changes in cardiac output (CO). However, CO tracking by this method is hampered by substantial change in aortic cross-sectional area (CSA) or proportionality between blood flow to the upper and lower body. To overcome this, we have developed a new method of TED CO monitoring. In this method, TED signal is obtained primarily from the aortic arch (AA). Using AA velocity signal, CO (CO_AA-CSA) is estimated by compensating changes in the aortic CSA with peripheral arterial pulse contour. When AA cannot be displayed properly or when the quality of AA velocity signal is unacceptable, our method estimates CO (CO_DA-ML) from DA velocity signal first by compensating changes in the aortic CSA, and by compensating changes in the blood flow proportionality through a machine learning of the relation between the CSA-adjusted CO and a reference CO (CO_ref). In 12 anesthetized dogs, we compared CO_AA-CSA and CO_DA-ML with CO_ref measured by an ascending aortic flow probe under diverse hemodynamic conditions (CO_ref changed from 723 to 7316 ml·min^-1). Between CO_AA-CSA and CO_ref, concordance rate in the four-quadrant plot analysis was 96%, while angular concordance rate in the polar plot analysis was 91%. Between CO_DA-ML and CO_ref, concordance rate was 93% and angular concordance rate was 94%. Both CO_AA-CSA and CO_DA-ML demonstrated "good to marginal" tracking ability of CO_ref. In conclusion, our method may allow a robust and reliable tracking of CO during perioperative hemodynamic management.

Cuffless Blood Pressure Monitoring: Promises and Challenges

Current BP measurements are on the basis of traditional BP cuff approaches. Ambulatory BP monitoring, at 15- to 30-minute intervals usually over 24 hours, provides sufficiently continuous readings that are superior to the office-based snapshot, but this system is not suitable for frequent repeated use. A true continuous BP measurement that could collect BP passively and frequently would require a cuffless method that could be worn by the patient, with the data stored electronically much the same way that heart rate and heart rhythm are already done routinely. Ideally, BP should be measured continuously and frequently during diverse activities during both daytime and nighttime in the same subject by means of novel devices. There is increasing excitement for newer methods to measure BP on the basis of sensors and algorithm development. As new devices are refined and their accuracy is improved, it will be possible to better assess masked hypertension, nocturnal hypertension, and the severity and variability of BP. In this review, we discuss the progression in the field, particularly in the last 5 years, ending with sensor-based approaches that incorporate machine learning algorithms to personalized medicine.

Deep learning for prediction of cardiac indices from photoplethysmographic waveform: A virtual database approach

Deep learning methods combined with large datasets have recently shown significant progress in solving several medical tasks. However, collecting and annotating large datasets can be a very cumbersome and expensive task. We tackle these problems with a virtual database approach where training data is generated using computer simulations of related phenomena. Specifically, we concentrate on the following problem: can cardiovascular indices such as aortic elasticity, diastolic and systolic blood pressures, and blood flow from heart be predicted continuously using wearable photoplethysmographic sensors? We simulate the blood flow using a haemodynamic model consisting of the entire human circulation. Repeated evaluation of the simulator allows us to create a database of "virtual subjects" with size that is only limited by available computational resources. Using this database, we train neural networks to predict the cardiac indices from photoplethysmographic signal waveform. We consider two approaches: neural networks based on predefined input features and deep convolutional neural networks taking waveform directly as the input. The performance of the methods is demonstrated using numerical examples, thus carrying out a preliminary assessment of the approaches. The results show improvements in accuracy compared with the previous methods. The improvements are especially significant with indices related to aortic elasticity and maximum blood flow. The proposed approach would provide new means to measure cardiovascular health continuously, for example, with a simple wrist device.