Recent Advances in Non-Invasive Blood Pressure Monitoring and Prediction Using a Machine Learning Approach

Artificial Intelligence-Based Diagnostic Support System for Patent Ductus Arteriosus in Premature Infants

Background: Patent ductus arteriosus (PDA) is a prevalent congenital heart defect in premature infants, associated with significant morbidity and mortality. Accurate and timely diagnosis of PDA is crucial, given the vulnerability of this population. Methods: We introduce an artificial intelligence (AI)-based PDA diagnostic support system designed to assist medical professionals in diagnosing PDA in premature infants. This study utilized electronic health record (EHR) data from 409 premature infants spanning a decade at Severance Children's Hospital. Our system integrates a data viewer, data analyzer, and AI-based diagnosis supporter, facilitating comprehensive data presentation, analysis, and early symptom detection. Results: The system's performance was evaluated through diagnostic tests involving medical professionals. This early detection model achieved an accuracy rate of up to 84%, enabling detection up to 3.3 days in advance. In diagnostic tests, medical professionals using the system with the AI-based diagnosis supporter outperformed those using the system without the supporter. Conclusions: Our AI-based PDA diagnostic support system offers a comprehensive solution for medical professionals to accurately diagnose PDA in a timely manner in premature infants. The collaborative integration of medical expertise and technological innovation demonstrated in this study underscores the potential of AI-driven tools in advancing neonatal diagnosis and care.

Perioperative Patients With Hemodynamic Instability: Consensus Recommendations of the Anesthesia Patient Safety Foundation

In November of 2022, the Anesthesia Patient Safety Foundation held a Consensus Conference on Hemodynamic Instability with invited experts. The objective was to review the science and use expert consensus to produce best practice recommendations to address the issue of perioperative hemodynamic instability. After expert presentations, a modified Delphi process using discussions, voting, and feedback resulted in 17 recommendations regarding advancing the perioperative care of the patient at risk of, or with, hemodynamic instability. There were 17 high-level recommendations. These recommendations related to the following 7 domains: Current Knowledge (5 statements); Preventing Hemodynamic Instability-Related Harm During All Phases of Care (4 statements); Data-Driven Quality Improvement (3 statements); Informing Patients (2 statements); The Importance of Technology (1 statement); Launch a National Campaign (1 statement); and Advancing the Science (1 statement). A summary of the recommendations is presented in Table 1 .

Blood pressure estimation and classification using a reference signal-less photoplethysmography signal: a deep learning framework

The markers that help to predict th function of a cardiovascular system are hemodynamic parameters like blood pressure (BP), stroke volume, heart rate, and cardiac output. Continuous analysis of hemodynamic parameters such as BP can detect abnormalities earlier, preventing cardiovascular diseases (CVDs). However, sometimes due to motion artifacts, it becomes difficult to monitor the BP accurately and classify it. This work presents an optimized deep learning model having the capability to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP) and classify the BP stages simultaneously from the same network using only a single channel photoplethysmography (PPG) signal. The proposed model is designed by exploiting the deep learning framework of a convolutional neural network (CNN), exhibiting the inherent ability to extract features automatically. Moreover, the proposed framework utilizes the superlet transform method to transform a 1-D PPG signal into a 2-D super-resolution time-frequency (TF) spectrogram. A superlet transform separates the peaks related to true PPG signal components and motion artifacts components. Thus, the superlet provides a robust realtime approach to accurately estimating and classifying BP using a single PPG sensor signal and does not require additional ECG and PPG sensor signals for reference. Using a super-resolution spectrogram and CNN model makes the method profitable in motion artifact removal, feature selection, and extraction. Hence the proposed framework becomes less complex for deployment on wearable devices having limited battery resources. The performance of the proposed framework is demonstrated on the publicly available larger dataset MIMIC-III. This work obtained a mean absolute error (MAE) of 2.71 mmHg and 2.42 mmHg for SBP and DBP, respectively. The classification accuracy for the SBP prediction is about 96.79%, whereas it is 98.94% for DBP. From a motion artifact-affected PPG signal, SBP and DBP are estimated. Then the estimated BP is classified into three categories: normotension, prehypertension, and hypertension, and is compared with the state of art methods to show the effectiveness of the proposed optimized framework.

B3X: a novel efficient algorithm for accurate automated auscultatory blood pressure estimation

Objective.The auscultatory technique is still considered the most accurate method for non-invasive blood pressure (NIBP) measurement, although its reliability depends on operator's skills. Various methods for automated Korotkoff sounds analysis have been proposed for reliable estimation of systolic (SBP) and diastolic (DBP) blood pressures. To this aim, very complex methodologies have been presented, including some based on artificial intelligence (AI). This study proposes a relatively simple methodology, named B3X, to estimate SBP and DBP by processing Korotkoff sounds recordings acquired during an auscultatory NIBP measurement.Approach.The beat-by-beat change in morphology of adjacent Korotkoff sounds is evaluated via their cross-correlation. The time series of the beat-by-beat cross-correlation and its first derivative are analyzed to locate the timings of SBP and DBP values. Extensive tests were performed on a public database of 350 annotated measurements, and the performance was evaluated according to the BHS, AAMI/ANSI, and International Organization for Standardization (ISO) quality standards.Main results.The proposed approach achieved 'A' scores for SBP and DBP in the BHS grading system, and passed the quality tests of AAMI/ANSI and ISO standards. The B3X algorithm outperformed two well-established algorithms for oscillometric NIBP measurement in both SBP and DBP estimation. It also outperformed four AI-based algorithms in DBP estimation, while providing comparable performance for SBP, at the cost of a much lower computational burden. The full code of the B3X algorithm is provided in a public repository.Significance.The very good performances ensured by the proposed B3X algorithm, at a low computational cost and without the need for parameter training, support its direct implementation into clinical blood pressure (BP) monitoring devices. The results of this study pave the way for solving/overcoming the trade-off between the accuracy of the auscultatory technique and the objectivity of oscillatory measurements, by bringing an automated auscultatory BP measurement method in clinical practice.

Automatic Calibration of a Device for Blood Pressure Waveform Measurement

This article presents a prototype of a new, non-invasive, cuffless, self-calibrating blood pressure measuring device equipped with a pneumatic pressure sensor. The developed sensor has a double function: it measures the waveform of blood pressure and calibrates the device. The device was used to conduct proof-of-concept measurements on 10 volunteers. The main novelty of the device is the pneumatic pressure sensor, which works on the principle of a pneumatic nozzle flapper amplifier with negative feedback. The developed device does not require a cuff and can be used on arteries where cuff placement would be impossible (e.g., on the carotid artery). The obtained results showed that the systolic and diastolic pressure measurement errors of the proposed device did not exceed ±6.6% and ±8.1%, respectively.

Predicting blood pressure from face videos using face diagnosis theory and deep neural networks technique

Hypertension is a major cause of cardiovascular diseases. Accurate and convenient measurement of blood pressure are necessary for the detection, treatment, and control of hypertension. In recent years, face video based non-contact blood pressure prediction is a promising research topic. Interestingly, face diagnosis has been an important part of traditional Chinese medicine (TCM) for thousands of years. TCM practitioners observe some typical regions of the face to determine the health status of the Zang Fu organs (i.e., heart). However, the effectiveness of face diagnosis theory in conjunction with computer vision analysis techniques to predict blood pressure is unclear. We proposed an artificial intelligence framework for predicting blood pressure using deep convolutional neural networks in this study. First, we extracted pulse wave signals through 652 facial videos. Then, we trained and compared nine artificial neural networks and chose the best performed prediction model, with an overall true predict rate of 90%. We also investigated the impact of face reflex regions selection on blood pressure prediction model, and the five face regions outperformed. Our high effectiveness and stability framework may provide an objective and convenient computer-aided blood pressure prediction method for hypertension screening and disease prevention.

Estimating Blood Pressure during Exercise with a Cuffless Sphygmomanometer

Accurately measuring blood pressure (BP) is essential for maintaining physiological health, which is commonly achieved using cuff-based sphygmomanometers. Several attempts have been made to develop cuffless sphygmomanometers. To increase their accuracy and long-term variability, machine learning methods can be applied for analyzing photoplethysmogram (PPG) signals. Here, we propose a method to estimate the BP during exercise using a cuffless device. The BP estimation process involved preprocessing signals, feature extraction, and machine learning techniques. To ensure the reliability of the signals extracted from the PPG, we employed the skewness signal quality index and the RReliefF algorithm for signal selection. Thereafter, the BP was estimated using the long short-term memory (LSTM)-based neural network. Seventeen young adult males participated in the experiments, undergoing a structured protocol composed of rest, exercise, and recovery for 20 min. Compared to the BP measured using a non-invasive voltage clamp-type continuous sphygmomanometer, that estimated by the proposed method exhibited a mean error of 0.32 ± 7.76 mmHg, which is equivalent to the accuracy of a cuff-based sphygmomanometer per regulatory standards. By enhancing patient comfort and improving healthcare outcomes, the proposed approach can revolutionize BP monitoring in various settings, including clinical, home, and sports environments.

Continuous Blood Pressure Monitoring in Patients Having Surgery: A Narrative Review

Hypotension can occur before, during, and after surgery and is associated with postoperative complications. Anesthesiologists should thus avoid profound and prolonged hypotension. A crucial part of avoiding hypotension is accurate and tight blood pressure monitoring. In this narrative review, we briefly describe methods for continuous blood pressure monitoring, discuss current evidence for continuous blood pressure monitoring in patients having surgery to reduce perioperative hypotension, and expand on future directions and innovations in this field. In summary, continuous blood pressure monitoring with arterial catheters or noninvasive sensors enables clinicians to detect and treat hypotension immediately. Furthermore, advanced hemodynamic monitoring technologies and artificial intelligence-in combination with continuous blood pressure monitoring-may help clinicians identify underlying causes of hypotension or even predict hypotension before it occurs.

Wearable Two-Dimensional Nanomaterial-Based Flexible Sensors for Blood Pressure Monitoring: A Review

Flexible sensors have been extensively employed in wearable technologies for physiological monitoring given the technological advancement in recent years. Conventional sensors made of silicon or glass substrates may be limited by their rigid structures, bulkiness, and incapability for continuous monitoring of vital signs, such as blood pressure (BP). Two-dimensional (2D) nanomaterials have received considerable attention in the fabrication of flexible sensors due to their large surface-area-to-volume ratio, high electrical conductivity, cost effectiveness, flexibility, and light weight. This review discusses the transduction mechanisms, namely, piezoelectric, capacitive, piezoresistive, and triboelectric, of flexible sensors. Several 2D nanomaterials used as sensing elements for flexible BP sensors are reviewed in terms of their mechanisms, materials, and sensing performance. Previous works on wearable BP sensors are presented, including epidermal patches, electronic tattoos, and commercialized BP patches. Finally, the challenges and future outlook of this emerging technology are addressed for non-invasive and continuous BP monitoring.