Advancement Of Medical Instrumentation Standards Research Articles

Costs involved in compliance with new endoscope reprocessing guidelines.

In March 2022, the Association for the Advancement of Medical Instrumentation (AAMI) released the American National Standards Institute (ANSI)/AAMI ST91:2021, their latest update on comprehensive, flexible, and semirigid endoscope reprocessing. These updated standards recommend the sterilization of high-risk endoscopes when possible and provide new recommendations for the precleaning, leak testing, manual cleaning, visual inspection, automated reprocessing, drying, storage, and transport of endoscopes. ANSI/AAMI ST91:2021 was compared with ANSI/AAMI ST91:2015 for major reprocessing differences that result in either time and/or cost increases. Time estimates were captured by explicit recommendation inclusion or taken from the literature. All the costs were estimated using publicly available resources. The updated standards represent a potential 24.3-minute and 52.35 to 67.57 United States dollars increase per procedure in terms of reprocessing time and spending, respectively, not including capital investments. Capital costs per procedure were highly dependent on the procedure volume of the facility. The new AAMI standards recommend several major changes, such as sterilization, for facilities to reprocess and manage endoscopes between uses. As more facilities increase their reprocessing methods to reflect the updated standards, they do so at a cost and introduce several delays. As the reprocessing landscape evolves, facilities should consider their true costs and alternative solutions, such as single-use endoscopes.

Blood Pressure Estimation Based on PPG and ECG Signals Using Knowledge Distillation.

Easy access bio-signals are useful for alleviating the shortcomings and difficulties associated with cuff-based and invasive blood pressure (BP) measurement techniques. This study proposes a deep learning model, trained using knowledge distillation, based on photoplethysmographic (PPG) and electrocardiogram (ECG) signals to estimate systolic and diastolic blood pressures. The estimation model comprises convolutional layers followed by one bidirectional recurrent layer and attention layers. The training approach involves knowledge distillation, where a smaller model (student model) is trained by leveraging information from a larger model (teacher model). The proposed multistage model was evaluated on 1205 subjects from Medical Information Mart for Intensive Care (MIMIC) III database using the Association for the Advancement of Medical Instrumentation (AAMI) and the standards of the British Hypertension Society (BHS). The results revealed that our model performance achieved grade A in estimating both systolic blood pressure (SBP) and diastolic blood pressure (DBP) and met the requirements of the AAMI standard. After training with knowledge distillation (KD), the model achieved a mean absolute error and standard deviation of 2.94 ± 5.61mmHg for SBP and 2.02 ± 3.60mmHg for DBP. Our results demonstrate the benefits of the knowledge distillation training method in reducing the number of parameters and improving the predictive accuracy of the blood pressure regression model.

PPG-based Continuous BP Waveform Estimation Using Polarized Attention-guided Conditional Adversarial Learning Model.

The blood pressure (BP) waveform is a vital source of physiological and pathological information concerning the cardiovascular system. This study proposes a novel attention-guided conditional generative adversarial network (cGAN), named PPG2BP-cGAN, to estimate BP waveforms based on photoplethysmography (PPG) signals. The proposed model comprises a generator and a discriminator. Specifically, the UNet3+-based generator integrates a full-scale skip connection structure with a modified polarized self-attention module based on a spatial-temporal attention mechanism. Additionally, its discriminator comprises PatchGAN, which augments the discriminative power of the generated BP waveform by increasing the perceptual field through fully convolutional layers. We demonstrate the superior BP waveform prediction performance of our proposed method compared to state-of-the-art (SOTA) techniques on two independent datasets. Our approach first pre-trained on a dataset containing 683 subjects and then tested on a public dataset. Experimental results from the Multi-parameter Intelligent Monitoring in Intensive Care dataset show that the proposed method achieves a root mean square error of 3.54, mean absolute error of 2.86, and Pearson coefficient of 0.99 for BP waveform estimation. Furthermore, the estimation errors (mean error ± standard deviation error) for systolic BP and diastolic BP are 0.72 ± 4.34 mmHg and 0.41 ± 2.48 mmHg, respectively, meeting the American Association for the Advancement of Medical Instrumentation standard. Our approach exhibits significant superiority over SOTA techniques on independent datasets, thus highlighting its potential for future applications in continuous cuffless BP waveform measurement.

Abstract 17573: Reliability of Non-Invasive Arterial Pressure Monitoring via ClearSight System™ During Cardiac Ablation and Transvenous Pacemaker Lead Removal

Background: Invasive arterial catheter (IAC) placement can lead to hematoma, vessel occlusion, pain and & procedure delay. The ClearSight System™ (CSS) is a non-invasive blood pressure (NIBP) device that measures beat-to-beat arterial pressures (AP) via a finger cuff. The validity of CSS during cardiac ablation & transvenous pacemaker lead removal has not been described. Therefore, we performed a single center observational study to validate AP monitoring by CSS compared to IAC in such patients (pts). Methods: Pts undergoing cardiac ablation or lead removal from June-November 2022 were included. AP was simultaneously measured via CSS & IAC. Measurements were compared using Bland-Altman analysis. Acceptable bias & precision (standard deviation) were defined as <5 mm Hg & <8 mm Hg respectively based on Association for the Advancement of Medical Instrumentation standards. An exploratory analysis on impacts of BMI, sex, & type of procedure on validity of CSS was also assessed. Results: Paired AP measurements were available for 61 pts (6967 paired measurements). Median age was 67 (IQR 60.5-73.5), BMI 29.2 (IQR 26.1-37.1) & 31% of pts were female. Procedures included atrial fibrillation ablation (n=32), SVT ablation (n=13), lead extraction (n=9), & VT ablation (n=7). Bland-Altman analysis comparing AP via CSS vs IAC showed that the CSS overestimated systolic arterial pressure (SAP) & underestimated both diastolic arterial pressure (DAP) & mean arterial pressure (MAP). Mean bias was 4.2 ± 12.9 (SAP), -4.99 ± 9.2 (DAP) & -2.4 ± 11.78 (MAP) (Figure 1). Exploratory analysis showed that CSS was not interchangeable with IAC monitoring regardless of subgroup (MAP male sex -1.9 ± 11.1; BMI ≥30 -2.7 ± 9.7; ablation -1.8 ± 12.2). Conclusion: Continuous NIBP monitoring via CSS was not interchangeable with IAC monitoring in pts undergoing cardiac ablation & lead extraction.

Cascade forest regression algorithm for non-invasive blood pressure estimation using PPG signals

The regression and classification performances of deep-learning algorithms depend on the tuning of the model and require significant intervention to train the model. A blood pressure prediction (BP) method – which is an improved cascade forest regression method based on a deep forest framework – is proposed in this study to mitigate the adverse effects of hyperparameters on deep learning algorithms and human errors. The impact of hyperparameters on the model can be reduced using random forest regression and extra tree regression as base estimators and by applying them to bootstrap aggregation strategies for learning data. The photoplethysmography (PPG) data and ambulatory blood pressure obtained from the MIMIC II database were evenly divided into 5 s segments to accurately estimate blood pressure. Nonlinear indices of the time domain, frequency domain, and heart rate variability were obtained from the PPG signal as training characteristic values. This process is similar to collecting data directly from a wearable device for rapid blood pressure prediction. This improves the predictive performance of the model and reduces additional memory consumption. Our proposed algorithm achieved mean absolute errors of 1.760 and 2.896 mmHg for systolic blood pressure (SBP) and diastolic blood pressure (DBP), respectively. Additionally, our best model achieved R2 scores of 0.948 and 0.926 for SBP and DBP, respectively. According to the Association for the Advancement of Medical Instrumentation standards, the standard deviation and mean error of the predicted results for systolic and diastolic BPs were within the standard range. According to the British Hypertension Society standard, the results of the proposed algorithm reached grade A. This study confirmed the possibility of developing an algorithm that can accurately estimate blood pressure.

Multifunctional waterproof breathable coating on polyester-based woven protective clothing for healthcare application

The development of multifunctional waterproof breathable coated textiles (WBCTs) with a long-lasting ultraviolet resistant, antibacterial properties is created by integrating weaving and surface coating technology. Using oxford weave, four different polyester-based jammed woven textiles structures are created from 100 % polyester, 100 % texturized polyester, polyester/viscose and polyester/cotton, and then treated with four different biopolymeric finishes viz. Neem, Tulsi, Aloe Vera and Grapeseed oil. The finished samples are then coated with two different concentration of breathable polyurethane (PU) coating. As a result, the PU coating significantly reduces the overall pore size, resulting in highest level of liquid barrier protection of Level 4 according to Association for the Advancement of Medical Instrumentation (AAMI) requirements. The proposed material complies with AAMI standards and can be used in protective apparel along with healthcare applications.

PPG-based blood pressure estimation can benefit from scalable multi-scale fusion neural networks and multi-task learning

The continuous measurement of blood pressure (BP) plays an important role in preventing cardiovascular diseases. However, common cuff-based devices with cumbersome operations are difficult to realize continuous BP monitoring. We propose a continuous BP estimation method based on the end-to-end multi-scale fusion and multi-task learning neural network (MSF-MTLNet). It can use the 8-second PPG segment and its derivatives as input and automatically learn their multi-scale features to improve BP accuracy. The proposed method implements feature extraction by adaptively fusing multiple convolution kernels with different sizes through the attention mechanism. Simultaneously, multi-task learning was introduced to discover task-relevant features. A total of 277,600 segments from 1825 patients in the University of California, Irvine database are used for experiments. They are divided into the independent training set, validation set, and test set according to the ratio of 8:1:1 in an inter-subject manner. The mean and standard deviation of estimation error for systolic blood pressure and diastolic blood pressure are 0.97 ± 8.87 mmHg and 0.55 ± 4.23 mmHg, respectively, which outperforms the current cutting-edge method. Our approach almost meets the Association for the Advancement of Medical Instrumentation standard. Considering the British Hypertension Society standards, it achieves an 'A' grade for DBP estimation and a 'B' grade for SBP estimation. Experimental results show that MSF-MTLNet can obtain promising precision in cuffless and continuous BP estimation.

Noninvasive Blood Pressure Measurement Using the NICCI Monitor in Adolescents During Intraoperative Anesthetic Care.

BackgroundThe intermittent measurement of blood pressure (BP) remains the standard of care during anesthesia or procedural sedation. To improve the early identification of hemodynamic compromise, various noninvasive BP devices have been developed which provide a continuous BP reading. The current study evaluates the accuracy of a novel continuous BP device, the NICCI system, in adolescents weighing 40 - 80 kg.MethodsDuring intraoperative anesthetic care, BP readings (systolic, diastolic, and mean) were captured from the arterial cannula and the NICCI device every second.ResultsThe study cohort included 44 pediatric patients undergoing major orthopedic, cardiac, and neurosurgical procedures. A total of 383,126 pairs of systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP) values from the arterial cannula and the NICCI device were analyzed. The absolute difference for SBP, DBP, and MAP values from the NICCI monitor and the arterial cannula were 10 ± 8, 9 ± 7, and 9 ± 7 mm Hg, respectively. The difference between the BP values from the NICCI and the arterial cannula was ≤ 10 mm Hg for 60% of the SBP readings, 67% of the DBP readings, and 56% of the MAP readings. Using Bland-Altman analysis, the bias was 2, 3, and 4 mm Hg for the SBP, DBP, and MAP.ConclusionsAlthough there were technical limitations related to patient size that affected its ability to meet the strict accuracy criteria set by the American National Standards Institute/Association for the Advancement of Medical Instrumentation standards for noninvasive BP measurement (ANSI/AAMI SP10), the NICCI system provided a continuous noninvasive beat-to-beat BP measurement which was clinically relevant during a significant portion of intraoperative care.

A new approach for daily life Blood-Pressure estimation using smart watch

Hypertension has become a major factor affecting people’s health. Timely monitoring and prevention of hypertension are of great significance. Most blood-pressure monitoring devices have redundant accessories and complex operations, which are not suitable for daily life applications. To solve these problems, we designed an application-level smart watch that can calculate the PAT feature using simultaneously collected ECG and PPG signals. By fusing the time–frequency-domain features of PPG and the correlation matrix between pulses, the information related to blood pressure in physiological signals was comprehensively extracted. Most of unstable signal segments can be eliminated and the impact of signal disturbances on overall accuracy will be reduced. This paper proposed two blood-pressure estimation modes: a two-step calib-free mode and a personal calibration mode based on transfer learning. The results on our self-established dataset (36 normotensive subjects and 40 hypertensive subjects) indicated that the two-step calib-free mode could estimate blood pressure with accuracy of 0.23 ± 6.1 mmHg and 0.63 ± 9.35 mmHg for DBP and SBP respectively, which was better than previous calib-free methods. Through the personal calibration mode, the estimation accuracy reached 0.02 ± 5.94 mmHg for DBP and 0.3 ± 7.69 mmHg for SBP, which complied with the Association for the Advancement of Medical Instrumentation standard.

Evaluation of Some Chemical Parameters of Hemodialysis Water: A Case Study in Iran.

One of the most common diseases in the world is kidney failure, which can lead to the death of patients. Hemodialysis is a treatment for patients whose kidneys are failing. The water used to perform dialysis must be healthy, safe, and clean. This study aimed to investigate the concentration of heavy metals in hemodialysis water in one of the Hospitals in Iran and compare it with European Pharmacopeia (EPH) and Association for the Advancement of Medical Instrumentation (AAMI) standards. The present study is a descriptive-analytical study conducted on the inlet water of hemodialysis machines in hospital. The samples were collected for 3 months from June to September 2021, Which was examined in terms of free residual chlorine, electrical conductivity, pH, and calcium, magnesium, sodium, aluminum, zinc, copper, and lead concentration. Metals concentration in hemodialysis water was measured by Inductively Coupled Plasma Mass Spectrometry (ICP-MS) technique. The average value of parameters such as electrical conductivity, pH, residual free chlorine, sodium, calcium, magnesium, zinc, copper and lead in the hemodialysis water was less than the AAMI and EPH standards limits. There was a significant difference at the 95% confidence level with the standard limits, but the aluminum concentration was higher than the standard limits. Also, by examining the medical files of dialysis patients, the most observed problems were anemia and bone diseases, which are probably caused by exposure to high concentrations of aluminum in hemodialysis water. In present study the aluminum concentration is higher than the standard limits. Considering that the higher aluminum concentration can cause diseases such as anemia, bone diseases, nervous deterioration, and death in hemodialysis patients, therefore, it is recommended to continuously evaluate and monitor the quality of hemodialysis water and the performance of its treatment system.

Attention Mechanism-Based Convolutional Long Short-Term Memory Neural Networks to Electrocardiogram-Based Blood Pressure Estimation

Monitoring people’s blood pressure can effectively prevent blood pressure-related diseases. Therefore, providing a convenient and comfortable approach can effectively help patients in monitoring blood pressure. In this study, an attention mechanism-based convolutional long short-term memory (LSTM) neural network is proposed to easily estimate blood pressure. To easily and comfortably estimate blood pressure, electrocardiogram (ECG) and photoplethysmography (PPG) signals are acquired. To precisely represent the characteristics of ECG and PPG signals, the signals in the time and frequency domain are selected as the inputs of the proposed NN structure. To automatically extract the features, the convolutional neural networks (CNNs) are adopted as the first part of neural networks. To identify the meaningful features, the attention mechanism is used in the second part of neural networks. To model the characteristic of time series, the long short-term memory (LSTM) is adopted in the third part of neural networks. To integrate the information of previous neural networks, the fully connected networks are used to estimate blood pressure. The experimental results show that the proposed approach outperforms CNN and CNN-LSTM and complies with the Association for the Advancement of Medical Instrumentation standard.

Validation of oscillometric blood pressure measurement using a Datex S/5 Compact multiparameter monitor in anaesthetized adult dogs

ObjectiveTo compare noninvasive (NIBP) with invasive blood pressure (IBP) measurements from a Datex S/5 Compact monitor in anaesthetized adult dogs, and to evaluate it according to the American College of Veterinary Internal Medicine (ACVIM) and the Association for the Advancement of Medical Instrumentation (AAMI) criteria. Study designProspective clinical study. AnimalsA group of 34 client-owned adult dogs. MethodsDogs were anaesthetized for different surgical procedures using different anaesthetic protocols. IBP was measured using a catheter placed in a dorsal pedal artery. A blood pressure cuff was placed over the contralateral dorsal pedal artery for NIBP measurement. Data were recorded using the Datex iCollect program, and paired readings were matched every 3 minutes for 60 minutes. Bland-Altman and error grid analyses were used to estimate the agreement between IBP and NIBP measurements, and its clinical significance, respectively. Data were reported as mean bias [lower, upper limits of agreement (LoA)]. ResultsThe Datex S/5 monitor conformed to most ACVIM criteria. The correlation coefficient was less than 0.9 for systolic, diastolic, and mean arterial pressures (MAP). The best agreement between the noninvasive and invasive methods was observed for MAP, with LoA (–17 to 13 mmHg) and higher percentage of NIBP readings within 5 (55.6%), 10 (81.7%) and 20 (98.6%) mmHg of the IBP values. The Datex S/5 NIBP technology did not meet the AAMI validation criteria and less than 95% of the paired measurements were found within the green zone of the error grid analysis. Conclusions and clinical relevanceThe Datex S/5 monitor conformed to most ACVIM criteria but not with the more rigorous AAMI standards. Despite good agreement between IBP and NIBP for MAP measurements, care must be taken when using this device to guide therapeutic interventions of blood pressure in anaesthetized healthy adult dogs.

Robust Heartbeat Classification for Wearable Single-Lead ECG via Extreme Gradient Boosting.

Wearable electrocardiogram (ECG) monitoring devices have enabled everyday ECG collection in our daily lives. However, the condition of ECG signal acquisition using wearable devices varies and wearable ECG signals could be interfered with by severe noises, resulting in great challenges of computer-aided automated ECG analysis, especially for single-lead ECG signals without spare channels as references. There remains room for improvement of the beat-level single-lead ECG diagnosis regarding accuracy and efficiency. In this paper, we propose new morphological features of heartbeats for an extreme gradient boosting-based beat-level ECG analysis method to carry out the five-class heartbeat classification according to the Association for the Advancement of Medical Instrumentation standard. The MIT-BIH Arrhythmia Database (MITDB) and a self-collected wearable single-lead ECG dataset are used for performance evaluation in the static and wearable ECG monitoring conditions, respectively. The results show that our method outperforms other state-of-the-art models with an accuracy of 99.14% on the MITDB and maintains robustness with an accuracy of 98.68% in the wearable single-lead ECG analysis.

Cuffless blood pressure estimation based on composite neural network and graphics information

Blood pressure (BP) assessment and dynamic detection are of great significance for timely detection of the morbidity of hypertension, which is a major risk factor for most cardiovascular diseases (CVDs). It has been proved that the dynamic BP can be effectively predicted by using the combined input of photoplethysmogram (PPG) and electrocardiographic (ECG) signals. In this paper, we proposed a hybrid neural network architecture, which contains CNN-Sequential-Adapt layer, ResNet25_BP layer with squeeze and excitation (SE) block and fully connected layers, for BP estimation. The structure based on the convolutional network aims at the current inputs, which can effectively absorb the graph information of the inputted biological signals and make the model more stable and reliable. We evaluated the performance of two datasets including 1216 and 40 subjects, based on the criterions of British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). According to the BHS and AAMI standards, the outputs of the model achieved grade A on BHS and met the AAMI criteria. The mean absolute errors (MAE) of systolic BP and diastolic BP are 3.70 and 2.81 mmHg in the large dataset, and 1.37 and 0.93 mmHg in the small dataset, respectively.

A novel feature representation approach for single-lead heartbeat classification based on adaptive Fourier decomposition

This paper proposes a novel feature representation approach for heartbeat classification using single-lead electrocardiogram (ECG) signals based on adaptive Fourier decomposition (AFD). AFD is a recently developed signal processing tool that provides useful morphological features, which are referred as AFD-derived instantaneous frequency (IF) features and differ from those provided by traditional tools. The AFD-derived IF features, together with ECG landmark features and RR interval features, are trained by a support vector machine to perform the classification. The proposed method improves the average accuracy of the feature extraction-based methods, reaching a level comparable to deep learning but with less training data, and at the same time being interpretable for the learned features. It also greatly reduces the dimension of the feature set, which is a disadvantage of the feature extraction-based methods, especially for ECG signals. To evaluate the performance, the Association for the Advancement of Medical Instrumentation standard is applied to publicly available benchmark databases, including the MIT-BIH arrhythmia and MIT-BIH supraventricular arrhythmia databases, to classify heartbeats from the single-lead ECG. The overall performance is compared to selected state-of-the-art automatic heartbeat classification algorithms, including one-lead and even several two-lead-based methods. The proposed approach achieves superior balanced performance and real-time implementation.

Using a Targeted Process to Reduce Subsequent Bloodstream Infections Related to Environmental Sources in Dialysis

Background Focus on pathogens in water reservoirs in the hemodialysis setting has largely concentrated on the internal/closed system as indicated by the Association for the Advancement of Medical Instrumentation standards (AAMI), with environmental sources generally unnoticed as potential issues. In 2016, an outbreak of gram-negative bloodstream infections (BSIs) occurred in three clinics. The cause was determined to be the dialysis station wall box and inadequate infection control practices. This study examines if a targeted Infection Preventionist (IP) driven process is effective in reducing subsequent unusual pathogen BSIs within a clinic. Methods A retrospective comparison of the frequency of unusual pathogen BSIs within dialysis clinics was performed. National Healthcare Safety Network (NHSN) Dialysis Event data was utilized to track cases of unusual pathogen BSIs; cases where attribution was identified as “other” were excluded. Cases were defined as BSIs with any mycobacterium, fungus and/or gram-negative pathogen, with the exception of Proteus. A decrease was defined as a reduction in the number of subsequent cases following an initial case. The frequency of subsequent cases was compared from 2016-2017 before the implementation of the targeted process to 2018-2019 after the implementation. Results Data from approximately 700 dialysis clinics were assessed. A baseline review revealed 990 cases in 401 clinics with an average of 2.47 cases per clinic with a range of subsequent cases of 1 to 30. A post-process implementation review revealed 657 cases in 368 clinics with an average of 1.74 cases per clinic with a range of 1 to 6. The median decreased from 2 cases to 1. Conclusions This study found that targeted interventions and education with individual dialysis clinics resulted in improved infection control practices and a decrease in subsequent bloodstream infections with unusual pathogens. Focus on pathogens in water reservoirs in the hemodialysis setting has largely concentrated on the internal/closed system as indicated by the Association for the Advancement of Medical Instrumentation standards (AAMI), with environmental sources generally unnoticed as potential issues. In 2016, an outbreak of gram-negative bloodstream infections (BSIs) occurred in three clinics. The cause was determined to be the dialysis station wall box and inadequate infection control practices. This study examines if a targeted Infection Preventionist (IP) driven process is effective in reducing subsequent unusual pathogen BSIs within a clinic. A retrospective comparison of the frequency of unusual pathogen BSIs within dialysis clinics was performed. National Healthcare Safety Network (NHSN) Dialysis Event data was utilized to track cases of unusual pathogen BSIs; cases where attribution was identified as “other” were excluded. Cases were defined as BSIs with any mycobacterium, fungus and/or gram-negative pathogen, with the exception of Proteus. A decrease was defined as a reduction in the number of subsequent cases following an initial case. The frequency of subsequent cases was compared from 2016-2017 before the implementation of the targeted process to 2018-2019 after the implementation. Data from approximately 700 dialysis clinics were assessed. A baseline review revealed 990 cases in 401 clinics with an average of 2.47 cases per clinic with a range of subsequent cases of 1 to 30. A post-process implementation review revealed 657 cases in 368 clinics with an average of 1.74 cases per clinic with a range of 1 to 6. The median decreased from 2 cases to 1. This study found that targeted interventions and education with individual dialysis clinics resulted in improved infection control practices and a decrease in subsequent bloodstream infections with unusual pathogens.

Continuous blood pressure measurement from one-channel electrocardiogram signal using deep-learning techniques.

Continuous blood pressure (BP) measurement is crucial for reliable and timely hypertension detection. State-of-the-art continuous BP measurement methods based on pulse transit time or multiple parameters require simultaneous electrocardiogram (ECG) and photoplethysmogram (PPG) signals. Compared with PPG signals, ECG signals are easy to collect using wearable devices. This study examined a novel continuous BP estimation approach using one-channel ECG signals for unobtrusive BP monitoring. A BP model is developed based on the fusion of a residual network and long short-term memory to obtain the spatial-temporal information of ECG signals. The public multiparameter intelligent monitoring waveform database, which contains ECG, PPG, and invasive BP data of patients in intensive care units, is used to develop and verify the model. Experimental results demonstrated that the proposed approach exhibited an estimation error of 0.07 ± 7.77 mmHg for mean arterial pressure (MAP) and 0.01 ± 6.29 for diastolic BP (DBP), which comply with the Association for the Advancement of Medical Instrumentation standard. According to the British Hypertension Society standards, the results achieved grade A for MAP and DBP estimation and grade B for systolic BP (SBP) estimation. Furthermore, we verified the model with an independent dataset for arrhythmia patients. The experimental results exhibited an estimation error of -0.22 ± 5.82 mmHg, -0.57 ± 4.39 mmHg, and -0.75 ± 5.62 mmHg for SBP, MAP, and DBP measurements, respectively. These results indicate the feasibility of estimating BP by using a one-channel ECG signal, thus enabling continuous BP measurement for ubiquitous health care applications.

A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals

ObjectiveEasy access bio-signals are useful to alleviate the shortcomings and difficulties of cuff-based and invasive blood pressure (BP) measuring techniques. This study proposes a multistage model based on deep neural networks to estimate systolic and diastolic blood pressures using the photoplethysmogram (PPG) signal. MethodsThe proposed model consists of two key ingredients, using two successive stages. The first stage includes two convolutional neural networks (CNN) to extract morphological features from each PPG segment and then to estimate systolic and diastolic BPs separately. The second stage relies on long short-term memory (LSTM) to capture temporal dependencies. Further, the method incorporates the dynamic relationship between systolic and diastolic BPs to improve accuracy. ResultsThe proposed multistage model was evaluated on 200 subjects using the standards of the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). The results revealed that our model performance met the requirements of the AAMI standard. Also, according to the BHS standard, it achieved grade A in estimating both systolic and diastolic BPs. The mean and standard deviation of error for systolic and diastolic blood pressure estimations were +1.91±5.55mmHg and +0.67±2.84mmHg, respectively. ConclusionOur results highlight the benefits of the proposed model in terms of appropriate feature extraction as well as estimation consistency.

Accurate Fiducial Point Detection Using Haar Wavelet for Beat-by-Beat Blood Pressure Estimation.

Pulse Arrival Time (PAT) derived from Electrocardiogram (ECG) and Photoplethysmogram (PPG) for cuff-less Blood Pressure (BP) measurement has been a contemporary and widely accepted technique. However, the features extracted for it are conventionally from an isolated pulse of ECG and PPG signals. As a result, the estimated BP is intermittent. Objective: This paper presents feature extraction from each beat of ECG and PPG signals to make BP measurements uninterrupted. These features are extracted by employing Haar transformation to adaptively attenuate measurement noise and improve the fiducial point detection precision. Method: the use of only PAT feature as an independent variable leads to an inaccurate estimation of either Systolic Blood Pressure (SBP) or Diastolic Blood Pressure (DBP) or both. We propose the extraction of supplementary features that are highly correlated to physiological parameters. Concurrent data was collected as per the Association for the Advancement of Medical Instrumentation (AAMI) guidelines from 171 human subjects belonging to diverse age groups. An Adaptive Window Wavelet Transformation (AWWT) technique based on Haar wavelet transformation has been introduced to segregate pulses. Further, an algorithm based on log-linear regression analysis is developed to process extracted features from each beat to calculate BP. Results: The mean error of 0.43 and 0.20 mmHg, mean absolute error of 4.6 and 2.3 mmHg, and Standard deviation of 6.13 and 3.06 mmHg is achieved for SBP and DBP respectively. Conclusions: The features extracted are highly precise and evaluated BP values are as per the AAMI standards. Clinical Impact: This continuous real-time BP monitoring technique can be useful in the treatment of hypertensive and potential-hypertensive subjects.

A Generic and Robust System for Automated Detection of Different Classes of Arrhythmia

Cardiovascular Arrhythmias (irregular beat) are related to the sudden death, can be characterized into two kinds, life-threatening (dangerous) and non-life-threatening. In clinical research and diagnosis analysis electrocardiography (ECG) plays an important role. The Advancement of Medical Instrumentation (AAMI) suggests, all the heartbeat of MIT-BIH dataset into four classes, namely, normal or bundle branch block (N), supraventricular ectopic (S), ventricular ectopic (V) and fusion of ventricular and normal (F). The objective of this paper is the classification of arrhythmias on the ECG as per AAMI standards. First beat detection and then on a given window size beat segmentation is performed. Then, features computed from ECG signals are RR (separation between two successive heartbeat pulses), local binary pattern(LBP), morphological changes, wavelet, high order statistics, and several amplitude values; Pre-RR, Post-RR, Local RR and Global RR. The main reason is to computing many morphological features to comparison analysis with the model when trained and tested on single features vs combining all features together. Model gives highest performance which is 90.8% accuracy using LBP as single feature compared with other features. Combined all important features together and optimal features (total 104) are given as an input to Single SVM classifier as well as ensembles of SVM which maps the component feature vectors to the particular class name. Principal Component Analysis (PCA) technique is also applied to the model which reduces the total number of features from 104 to 30 features. The Single SVM system can accurately classify four beat types and has an overall classification rate of 94.05% without PCA and using PCA 92.84% while the Ensemble SVM classifies and with an accuracy of 92.96%