Advancement Of Medical Instrumentation Research Articles

A Continuous Non-Invasive Blood Pressure Prediction Method Based on Deep Sparse Residual U-Net Combined with Improved Squeeze and Excitation Skip Connections.

Arterial blood pressure (ABP) serves as a pivotal clinical metric in cardiovascular health assessments, with the precise forecasting of continuous blood pressure assuming a critical role in both preventing and treating cardiovascular diseases. This study proposes a novel continuous non-invasive blood pressure prediction model, DSRUnet, based on deep sparse residual U-net combined with improved SE skip connections, which aim to enhance the accuracy of using photoplethysmography (PPG) signals for continuous blood pressure prediction. The model first introduces a sparse residual connection approach for path contraction and expansion, facilitating richer information fusion and feature expansion to better capture subtle variations in the original PPG signals, thereby enhancing the network's representational capacity and predictive performance and mitigating potential degradation in the network performance. Furthermore, an enhanced SE-GRU module was embedded in the skip connections to model and weight global information using an attention mechanism, capturing the temporal features of the PPG pulse signals through GRU layers to improve the quality of the transferred feature information and reduce redundant feature learning. Finally, a deep supervision mechanism was incorporated into the decoder module to guide the lower-level network to learn effective feature representations, alleviating the problem of gradient vanishing and facilitating effective training of the network. The proposed DSRUnet model was trained and tested on the publicly available UCI-BP dataset, with the average absolute errors for predicting systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean blood pressure (MBP) being 3.36 ± 6.61 mmHg, 2.35 ± 4.54 mmHg, and 2.21 ± 4.36 mmHg, respectively, meeting the standards set by the Association for the Advancement of Medical Instrumentation (AAMI), and achieving Grade A according to the British Hypertension Society (BHS) Standard for SBP and DBP predictions. Through ablation experiments and comparisons with other state-of-the-art methods, the effectiveness of DSRUnet in blood pressure prediction tasks, particularly for SBP, which generally yields poor prediction results, was significantly higher. The experimental results demonstrate that the DSRUnet model can accurately utilize PPG signals for real-time continuous blood pressure prediction and obtain high-quality and high-precision blood pressure prediction waveforms. Due to its non-invasiveness, continuity, and clinical relevance, the model may have significant implications for clinical applications in hospitals and research on wearable devices in daily life.

The deep convolutional networks for the classification of multi-class arrhythmia

An arrhythmia is an irregular heartbeat. Many researchers in the AI field have carried out the automatic classification of arrhythmias, and the issue that has been widely discussed is imbalanced data. A popular technique for overcoming this problem is the synthetic minority oversampling technique (SMOTE) technique. In this paper, the author adds some sampling of data obtained from other datasets into the primary dataset. In this case, the main dataset is the Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) arrhythmia database and an additional dataset from the MIT-BIH supraventricular arrhythmia database. The classification process is carried out with one-dimensional convolutional neural network model (1D-CNN) to perform multiclass and subject-class advancement of medical instrumentation (AAMII) classifications. The results obtained from this study are an accuracy of 99.10% for multiclass and 99.25% for subject-class.

Классификация сигналов ЭКГ на основе цифровой обработки сигналов, технического выбора функций и радиочастотного классификатора

Determining the optimal integration between features and classifiers has a significant effect on the performance of automatic heartbeat diagnostic systems. This importance stands out when dealing with critical applications that contain limited resources devices and require accurate and fast heartbeat classifiers to help the doctor make an accurate and quick diagnosis of heart diseases. Aiming at this task, this paper introduces a novel approach for choosing the optimal features of the ECG signal to be used with the Random Forest (RF) classifier following the inter-patient method for ECG signals division and obeying the instructions of the "Association for the Advancement of Medical Instrumentation (AAMI)." The features were chosen based on the concept of "Mutual Information Ranking (MIR)." The presented framework is comprehensive in terms of performing all the necessary processes efficiently, starting from ECG digital signal processing, segmentation, feature extraction, feature selection, and ending with ECG classification. The results of the experiments demonstrate that features corresponding to the normalized QRS width and the normalized RR intervals are the most influential features in the heartbeat classification. All tests were conducted using real ECG signals taken from the "MIT-BIH" Arrhythmia Database (MIT-BIH-ARR-DB). The suggested scheme attained the following F1-scores: 91.02%, 73.17%, and 98.04% in the classification of the Ventricular Ectopic Beats (V or VEB), Supraventricular Ectopic Beats (S or SVEB), and Normal Beats (N or NB), respectively. The overall accuracy was 96.26%. Despite its relative simplicity and reliance on few features, the proposed approach outperforms most of the reported state-of-the-art.

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.

Continuous non-invasive arterial blood pressure monitoring with photoplethysmography via SE-MSResUNet network

ObjectiveArterial blood pressure (ABP) waveforms include physiological parameters closely related to BP values, while only a few studies predict BP values through the monitoring ABP waveforms. Current ABP waveforms monitoring methods are limited by its high computing cost and information redundancy of multi-channel input signals. The aim of our work is to propose a new end-to-end method for monitoring the ABP waveforms using single-channel photoplethysmography (PPG) signals by constructing a lightweight Multi-Scale Residual U-Net fused with Squeeze-and-Excitation module (SE-MSResUNet) model. MethodsFirstly, the PPG and ABP signals are preprocessed with denoising, segmentation, and eliminating phase difference. Subsequently, the SE-MSResUNet model is constructed and trained using training data to achieve the mapping relationship between PPG and ABP signals. Then, the BP values are extracted from the monitored ABP waveforms. Finally, the performance of the SE-MSResUNet in ABP waveform monitoring and BP estimation is investigated. ResultsThe ABP waveforms monitored by our proposed SE-MSResUNet network with PPG signals only are highly consistent with the reference ABP waveforms. The MAE ± SD of estimated diastolic blood pressure (DBP), mean arterial pressure (MAP) and systolic blood pressure (SBP) compared with reference values are 2.16 ± 3.75, 2.29 ± 3.72, and 3.88 ± 6.17 mmHg, respectively. The proposed method meets the Association for the Advancement of Medical Instrumentation (AAMI) standard and reach A level of the British Hypertension Society (BHS) standard. ConclusionsOur proposed method outperforms current state-of-the-art methods for non-invasive blood pressure monitoring from PPG signals. The algorithm provides a potential possibility for continuous non-invasive blood pressure monitoring through portable wearable devices.

Development of continuous cuffless blood pressure prediction platform using enhanced 1-D SENet–LSTM

In this study, we propose a blood pressure estimation that employs a combined 1-D squeeze and excitation network (SENet-LSTM) architecture. Combining photoplethysmography (PPG) and electrocardiogram (ECG) signals can provide more helpful feature information. The original signals were processed by removing the noise and artifacts. By introducing SE block, the ability to learn features is enhanced, and an end-to-end approach is used to realize the automatic learning process. Additionally, the algorithm has the ability to recover arterial blood pressure (ABP) waveforms from blood pressure readings. The results of this study met the Grade A standard for diastolic blood pressure (DBP), systolic blood pressure (SBP), and mean arterial pressure (MAP) set by the British Hypertension Society (BHS) and were also in accordance with the Association for the Advancement of Medical Instrumentation (AAMI) standard. According to the DBP and SBP ranges, blood pressure is divided into the following categories: normal blood pressure, prehypertension, and hypertension. For the classification of Hypertension, Normotension, and Prehypertension using SBP, we achieved accuracy of 94% and F1 scores of 0.92, 0.94, and 0.85. For the results obtained using DBP classification the overall accuracy was 91%, with F1 scores of 0.85, 0.98, and 0.78. When compared to other studies, the classifier results generated by SBP and DBP estimates based on the 1-D SENet-LSTM method improved accuracy by 2% and 11%, respectively.

RNN Based Deep Learning Approach for ECG Beat Classification

The electrical patterns of the heart, captured through an electrocardiogram (ECG/EKG), serve as a diagnostic tool to identify potential issues such as heart attacks, irregular heart rhythms, heart failure, and arrhythmia, which manifests as irregularities in the heartbeat's rhythm. Deep Learning (DL) architectures have been successfully employed for arrhythmia detection and classification and offered superior performance to traditional shallow Machine Learning (ML) approaches. This paper introduces a novel approach utilizing deep learning techniques, specifically a Bidirectional Gated Recurrent Unit (Bi-GRU) model a variant of RNN, to classify ECG arrhythmia beats into distinct categories. The Bi-GRU model is employed in this work due to its capability to capture temporal dependencies in ECG signals, enabling a nuanced understanding of beat sequences for precise classification. Leveraging the MIT-BIH arrhythmia database, a comprehensive dataset containing annotated ECG signals, this study explores the efficacy of deep learning in accurately categorizing beats in to five super classes as per the standard of Association for the Advancement of Medical Instrumentation (AAMI). Evaluation metrics encompassing accuracy (Acc), specificity (Spe), sensitivity (Sen), positive predictive value (Ppv), and F1-score are utilized to assess the model performance in distinguishing between diverse arrhythmia classes.

Single-point curved fiber optic pulse sensor for physiological signal prediction based on the genetic algorithm-support vector regression model

For hypertensive patients, a real-time human physiological signal monitoring system helps to track blood pressure status and provides valuable data to clinicians for early diagnosis and timely intervention. Optical fiber pulse sensing has superior conditions such as resistance to electromagnetic interference and richness of measured pulse characteristics. In this study, a monitoring system based on a single-point curved fiber pulse sensor (CFPS) was used to collect the pulse wave signal of a human radial artery. The features of the pulse wave signal were used to estimate the pulse wave transit time (PTT) and Blood Pressure—systolic blood pressure (SBP) and diastolic blood pressure (DBP)—based on support vector regression (SVR) optimized by a genetic algorithm (GA) (GA-SVR model). The results show that the root mean square error (RMSE) of SBP, DBP and PTT were 1.571 mmHg, 3.250 mmHg and 5.719 ms, respectively, and the results met the Advancement of Medical Instrumentation (AAMI) criteria. Therefore, a real-time pulse wave monitoring system based on a single-point CFPS can well predict human physiological signals such as PTT, SBP and DBP.

Non-Invasive Blood Pressure Sensing via Machine Learning.

In this paper, a machine learning (ML) approach to estimate blood pressure (BP) using photoplethysmography (PPG) is presented. The final aim of this paper was to develop ML methods for estimating blood pressure (BP) in a non-invasive way that is suitable in a telemedicine health-care monitoring context. The training of regression models useful for estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP) was conducted using new extracted features from PPG signals processed using the Maximal Overlap Discrete Wavelet Transform (MODWT). As a matter of fact, the interest was on the use of the most significant features obtained by the Minimum Redundancy Maximum Relevance (MRMR) selection algorithm to train eXtreme Gradient Boost (XGBoost) and Neural Network (NN) models. This aim was satisfactorily achieved by also comparing it with works in the literature; in fact, it was found that XGBoost models are more accurate than NN models in both systolic and diastolic blood pressure measurements, obtaining a Root Mean Square Error (RMSE) for SBP and DBP, respectively, of 5.67 mmHg and 3.95 mmHg. For SBP measurement, this result is an improvement compared to that reported in the literature. Furthermore, the trained XGBoost regression model fulfills the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) as well as grade A of the British Hypertension Society (BHS) standard.

Investigation of the barrier performance of disposable isolation gowns

Recent epidemics and pandemics highlighted the need for effective personal protective equipment, including isolation gowns. The most critical property of an isolation gown is its ability to keep liquids and viruses from passing through the gown. Liquid and viral barrier penetration can be measured using laboratory test methods. Association for the Advancement of Medical Instrumentation (AAMI) PB70 standard defines isolation gown barrier performance levels and requirements. In this study, 22 disposable isolation gown models from6manufacturers were tested for liquid and viral penetration resistance. Standard test methods were used to evaluate water and viral penetration. Test results were evaluated using AAMI PB70 barrier performance criteria for 4 protection levels. Seven of the 22 tested gown models did not pass liquid and viral penetration testing based on AAMI PB70 at the level claimed by the manufacturer. The majority of these failures occurred at the seam and/or tie attachment areas. The study findings underscore the need for improved processes surrounding activities such as premarket testing and postmarket evaluation of gowns according to standardized test methods by third-party laboratories. This study also supports the recent Food and Drug Administration guidance document that clarified the characteristics of isolation gowns considered to be class II and subject to Food and Drug Administration premarket review. Infection preventionists, hospital purchasers, and safety professionals should seek isolation gowns demonstrating conformance to industry standards from manufacturers.

Continuous blood pressure monitoring using photoplethysmography and electrocardiogram signals by random forest feature selection and GWO-GBRT prediction model

Blood pressure (BP) is an important indicator of a person's cardiovascular status, but accurate, continuous BP monitoring remains a challenge. To improve the monitoring performance of continuous BP using electrocardiogram (ECG) and photoplethysmography (PPG) signals, a continuous BP monitoring method based on random forest feature selection (RFFS) and a gray wolf optimization-gradient boosting regression tree (GWO-GBRT) prediction model is developed in this study. First, features in time, frequency, and time–frequency domains are extracted from PPG and ECG signals to supply comprehensive characteristics for BP monitoring. Then, the RFFS method is employed to select sensitive features highly correlated with BP from the candidate feature sets, which reduced redundant information and improved monitoring efficiency. Next, a hybrid prediction model of the gray wolf optimization (GWO) technique and gradient boosting regression tree (GBRT) algorithm is established to learn the dependency relationship between BP and sensitive features. And a new fitness function of GWO is designed to balance the monitoring accuracy and consistency. Finally, ablation and comparative experiments demonstrate the effectiveness and advancement of the proposed method, using the ECG and PPG signals of 150 people downloaded from the MIMIC-III database. The mean absolute error (MAE) and standard deviation (STD) of the proposed method in predicting systolic blood pressure were 2.91 mmHg and 3.97 mmHg, and those of diastolic blood pressure were 1.71 mmHg and 2.35 mmHg. Its monitoring accuracy has surpassed the Association for Advancement of Medical Instrumentation (AAMI) standard and reached the “A” level standard of the British Hypertension Society (BHS) protocol.

Analysis of alternate material Onyx™ for total knee arthroplasty instrumentation sets.

A 25-pound weight limit is currently set on containerized instrumentation sets by the Association of periOperative Registered Nurses (AORN) and the Association for the Advancement of Medical Instrumentation (AAMI), in order to reduce strain on the staff and ensure that the sets are not too crowded in order to preserve sterilization and drying of the instruments. This is pushing companies to reduce the weight and number of instrumentation sets for the operating room. One solution has been to explore the viability of new, lighter materials such as Onyx. The goal of this study is to evaluate the novel material Onyx as a viable material utilized in reusable total knee arthroplasty (TKA) instrumentation sets utilizing traditional steam sterilization as the sterilization method. Mechanical and biocompatibility tests according to the American Society for Testing Materials (ASTM) and International Organization for Standardization (ISO) 10,993 were run to evaluate the Onyx Material to see if it would be a viable alternative to the stainless and martensitic steel that is currently being utilized. Gross warping and cracking after 10 rounds of sterilization was observed. This was qualitatively worse in the Onyx without a carbon fiber component. The Onyx material did not meet biocompatibility standards for its application. Onyx was determined to not be a viable material for TKA instruments regarding multiple high-pressure and -temperature sterilizations and cytotoxic cell testing.

BPNet: A multi-modal fusion neural network for blood pressure estimation using ECG and PPG

This paper aims to address the problem of estimating blood pressure (BP) based on specific physiological signals. However, several issues exist in current works. Firstly, some methods produce biased models by training them on a skewed distribution and failing to consider the assumptions underlying regression analysis. Secondly, data leakage can occur when overlapping samples are present in the dataset. Finally, some methods concatenate Electrocardiogram (ECG) and Photoplethysmogram (PPG) signals without fully capturing their relationship. To overcome these limitations, this paper applies the BoxCox transformation to correct for skewed label distributions and creates a non-overlapping dataset. Additionally, a novel end-to-end model, the blood pressure network (BPNet), is proposed, which can accurately estimate blood pressure. The Multi-parameter Intelligent Monitoring in Intensive Care database (MIMIC) is utilized to develop and verify the model, which includes ECG, PPG, and invasive BP data from patients in intensive care units (ICUs). The BPNet is evaluated on the MIMIC II (942 subjects) and MIMIC-III (833 subjects) datasets. In MIMIC-II, the estimation error for systolic blood pressure (SBP) and diastolic blood pressure (DBP) is −0.17 ± 4.62 mmHg and −0.24 ± 2.95 mmHg, respectively. In MIMIC-III, the estimation error for SBP and DBP is −0.30 ± 5.78 mmHg and −0.25 ± 3.80 mmHg, respectively. The experimental results exceed the performance of existing methods and meet the accuracy standards established by the Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS). This demonstrates the effectiveness and accuracy of the proposed model, highlighting the potential for practical applications in clinical settings.

PPG Signals-Based Blood-Pressure Estimation Using Grid Search in Hyperparameter Optimization of CNN-LSTM.

Researchers commonly use continuous noninvasive blood-pressure measurement (cNIBP) based on photoplethysmography (PPG) signals to monitor blood pressure conveniently. However, the performance of the system still needs to be improved. Accuracy and precision in blood-pressure measurements are critical factors in diagnosing and managing patients' health conditions. Therefore, we propose a convolutional long short-term memory neural network (CNN-LSTM) with grid search ability, which provides a robust blood-pressure estimation system by extracting meaningful information from PPG signals and reducing the complexity of hyperparameter optimization in the proposed model. The multiparameter intelligent monitoring for intensive care III (MIMIC III) dataset obtained PPG and arterial-blood-pressure (ABP) signals. We obtained 75,226 signal segments, with 60,180 signals allocated for training data, 12,030 signals allocated for the validation set, and 15,045 signals allocated for the test data. During training, we applied five-fold cross-validation with a grid-search method to select the best model and determine the optimal hyperparameter settings. The optimized configuration of the CNN-LSTM layers consisted of five convolutional layers, one long short-term memory (LSTM) layer, and two fully connected layers for blood-pressure estimation. This study successfully achieved good accuracy in assessing both systolic blood pressure (SBP) and diastolic blood pressure (DBP) by calculating the standard deviation (SD) and the mean absolute error (MAE), resulting in values of 7.89 ± 3.79 and 5.34 ± 2.89 mmHg, respectively. The optimal configuration of the CNN-LSTM provided satisfactory performance according to the standards set by the British Hypertension Society (BHS), the Association for the Advancement of Medical Instrumentation (AAMI), and the Institute of Electrical and Electronics Engineers (IEEE) for blood-pressure monitoring devices.

Automatic and continuous blood pressure monitoring via an optical-fiber-sensor-assisted smartwatch

Automatic and continuous blood pressure monitoring is important for preventing cardiovascular diseases such as hypertension. The evaluation of medication effects and the diagnosis of clinical hypertension can both benefit from continuous monitoring. The current generation of wearable blood pressure monitors frequently encounters limitations with inadequate portability, electrical safety, limited accuracy, and precise position alignment. Here, we present an optical fiber sensor-assisted smartwatch for precise continuous blood pressure monitoring. A fiber adapter and a liquid capsule were used in the building of the blood pressure smartwatch based on an optical fiber sensor. The fiber adapter was used to detect the pulse wave signals, and the liquid capsule was used to expand the sensing area as well as the conformability to the body. The sensor holds a sensitivity of -213µw/kPa, a response time of 5 ms, and high reproducibility with 70,000 cycles. With the assistance of pulse wave signal feature extraction and a machine learning algorithm, the smartwatch can continuously and precisely monitor blood pressure. A wearable smartwatch featuring a signal processing chip, a Bluetooth transmission module, and a specially designed cellphone APP was also created for active health management. The performance in comparison with commercial sphygmomanometer reference measurements shows that the systolic pressure and diastolic pressure errors are -0.35 ± 4.68 mmHg and -2.54 ± 4.07 mmHg, respectively. These values are within the acceptable ranges for Grade A according to the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). The smartwatch assisted with an optical fiber is expected to offer a practical paradigm in digital health.

Nonlinear features of photoplethysmography signals for Non-invasive blood pressure estimation

ObjectiveContinuous monitoring of blood pressure (BP) plays an essential role in the prognosis and prevention of hypertension and related cardiovascular diseases. Moreover, the ever-increasing demand for portable continuous health monitoring systems coupled with promising capabilities of photoplethysmography (PPG) sensors for developing easy-to-use, portable wearable devices have motivated many researchers toward applying PPG signals for non-invasive health monitoring. Nonlinear nature of BP and proven capability of the Poincaré plot for analyzing dynamic behavior of nonlinear systems motivated us to use this powerful tool for BP estimation. This study aims to explore the dynamical behavior of PPG signals to assist feature extraction for machine-learning (ML) algorithms to estimate BP. We proposed a Poincaré-based feature extraction method for BP estimation with no need to extract precise local points on the PPG signal. MethodsFirst, a Poincaré plot of 10-s segments of the PPG signal was prepared. Then, three distinct time series were retrieved from Poincaré mapping of PPG signals; following this, numerous indices were extracted from the three time series. The F-Test feature selection method was applied to pick the most effective features. Finally, the picked features were fed into different ML algorithms for the estimation of BP. ResultsThe proposed method was validated using a subset of the Medical Information Mart for Intensive Care II (MIMIC-II) database containing ambulatory blood pressure (ABP) and PPG records. The performance evaluation was carried out in terms of mean absolute error (MAE), standard deviation (STD), and Pearson’s correlation coefficient. According to the results, application of the Gaussian process regression (GPR) led to the best performance for both systolic and diastolic BP (0.79 ± 3.08 and 1.38 ± 4.53 mmHg, respectively). Satisfying the criteria for Advancement of Medical Instrumentation (AAMI), it was rated as Grade A for systolic and diastolic BP measurements under terms of British Hypertension Society (BHS) standards, which confirms the efficiency of the Poincaré-based features for BP estimation. ConclusionThe results justify the usefulness of the proposed Poincaré-based features as a powerful tool in BP estimation scenarios.

Hybrid modeling on reconstitution of continuous arterial blood pressure using finger photoplethysmography

The continuous estimation of arterial blood pressure (ABP) waveforms directly from single-channel photoplethysmography (PPG) signals will predictably change the way to monitor blood pressure in the future. This article proposed a new hybrid mathematical model for continuous blood pressure monitoring by investigating the relationship between the finger PPG signal and the radial ABP signal based on a public database. Considering potential damping factors and wave propagation/reflection in blood circulation, we combined the electrical network model with the tube-load model. The optimal range of model parameters was obtained through the system identification method to realize the individualized continuous blood pressure measurements. Compared with the invasive measurement, the hybrid model performed superior blood pressure estimation with high consistency. The estimated ABP waveforms correlated highly with the reference waveforms with an average correlation coefficient of 0.96. The mean absolute error/standard deviation of the estimated systolic blood pressure (SBP), mean arterial blood pressure (MAP), and diastolic blood pressure (DBP) were 3.0/4.4, 2.1/3.0 and 2.1/3.2 mmHg, respectively. The results met the requirements of the Association for the Advancement of Medical Instrumentation (AAMI). The hybrid model is expected to be embedded in small wearable devices to directly estimate the continuous blood pressure waveforms at the radial artery site through the PPG signals, pioneering the synchronous non-sensing monitoring on blood pressure and blood flow.

A deep learning method for continuous noninvasive blood pressure monitoring using photoplethysmography

Objective. The aim of this study is to investigate continuous blood pressure waveform estimation from a plethysmography (PPG) signal, thus providing more human cardiovascular status information than traditional cuff-based methods. Approach. The proposed method utilizes the feature extraction ability of a convolution neural network to estimate blood pressure (BP) from PPG signals without the need for waveform analysis and signal feature extraction. Main results. The network achieved mean absolute errors and standard deviations of 2.55 ± 3.92 mmHg for systolic BP (SBP), 1.66 ± 2.76 mmHg for diastolic BP (DBP), and 2.52 ± 3.02 mmHg for overall pressure waveform. The results meet the best levels of the protocols of the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). Significance. The proposed method shows promise for noninvasive continuous BP monitoring in hospital wards and daily life, which can assist in clinical diagnosis, disease treatment, and rehabilitation.

KD-Informer: A Cuff-Less Continuous Blood Pressure Waveform Estimation Approach Based on Single Photoplethysmography.

Ambulatory blood pressure (BP) monitoring plays a critical role in the early prevention and diagnosis of cardiovascular diseases. However, cuff-based inflatable devices cannot be used for continuous BP monitoring, while pulse transit time or multi-parameter-based methods require more bioelectrodes to acquire electrocardiogram signals. Thus, estimating the BP waveforms only based on photoplethysmography (PPG) signals for continuous BP monitoring has essential clinical values. Nevertheless, extracting useful features from raw PPG signals for fine-grained BP waveform estimation is challenging due to the physiological variation and noise interference. For single PPG analysis utilizing deep learning methods, the previous works depend mainly on stacked convolution operation, which ignores the underlying complementary time-dependent information. Thus, this work presents a novel Transformer-based method with knowledge distillation (KD-Informer) for BP waveform estimation. Meanwhile, we integrate the prior information of PPG patterns, selected by a novel backward elimination algorithm, into the knowledge transfer branch of the KD-Informer. With these strategies, the model can effectively capture the discriminative features through a lightweight architecture during the learning process. Then, we further adopt an effective transfer learning technique to demonstrate the excellent generalization capability of the proposed model using two independent multicenter datasets. Specifically, we first fine-tuned the KD-Informer with a large and high-quality dataset (Mindray dataset) and then transferred the pre-trained model to the target domain (MIMIC dataset). The experimental test results on the MIMIC dataset showed that the KD-Informer exhibited an estimation error of 0.02 ± 5.93 mmHg for systolic BP (SBP) and 0.01 ± 3.87 mmHg for diastolic BP (DBP), which complied with the association for the advancement of medical instrumentation (AAMI) standard. These results demonstrate that the KD-Informer has high reliability and elegant robustness to measure continuous BP waveforms.