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

Sensors, Journal Year: 2022, Volume and Issue: 22(16), P. 6195 - 6195

Published: Aug. 18, 2022

Blood pressure (BP) monitoring can be performed either invasively via arterial catheterization or non-invasively through a cuff sphygmomanometer. However, for conscious individuals, traditional cuff-based BP devices are often uncomfortable, intermittent, and impractical frequent measurements. Continuous non-invasive (NIBP) is currently gaining attention in the human health area due to its promising potentials assessing status of an individual, enabled by machine learning (ML), various purposes such as early prediction disease intervention treatment. This review presents development measuring tool called sphygmomanometer brief, summarizes state-of-the-art NIBP sensors, identifies extended works on continuous using commercial devices. Moreover, predictive techniques including pulse arrival time, transit wave velocity, ML elaborated basis bio-signals acquisition from these sensors. Additionally, different values (systolic BP, diastolic mean pressure) models adopted several reported studies compared terms international validation standards developed Advancement Medical Instrumentation (AAMI) British Hypertension Society (BHS) clinically-approved monitors. Finally, challenges possible solutions implementation realization technology addressed.

Language: Английский

---

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

Anesthesia & Analgesia, Journal Year: 2023, Volume and Issue: unknown

Published: Dec. 28, 2023

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

Language: Английский

---

Estimation of Blood Pressure by Image-Free, Wearable Ultrasound

Artery Research, Journal Year: 2024, Volume and Issue: 30(1)

Published: May 13, 2024

Abstract 1.28 billion adults worldwide have high pressure, and only 21% of people it under control. If blood pressure (BP) is not diagnosed treated properly, then there a risk for cardiovascular diseases, the main cause mortality. Ultrasound has emerged as potential medical imaging system to monitor health. It comfortable, noninvasive, safe, very well-established well-known technology. However, are currently no commercial single ultrasound systems directly quantify vascular parameters, without need complex algorithms, additional software-based solutions, energy demands that limit portable prolonged measurements. In this paper, we present steps design an image-free novel device continuously extract vital with focus on BP. Moreover, BP waveforms amplified toward periphery (i.e., from aorta radial artery), applied mathematical models specific site measurement, accurately We validated these algorithms in silico , vitro ex vivo, where tissue artery phantoms help emulate human physiology. young subjects, pulse (PP) correlation 0.978 mean difference (– 2.85 ± 2.57) mmHg at were achieved. The vivo PP was 0.986, (1.72 3.29) mmHg. Soon thereafter measurements stiffness, their analysis will be performed corroborate accuracy developed proof-of-concept device.

Language: Английский

---

Advancement in the Cuffless and Noninvasive Measurement of Blood Pressure: A Review of the Literature and Open Challenges

Bioengineering, Journal Year: 2022, Volume and Issue: 10(1), P. 27 - 27

Published: Dec. 24, 2022

Hypertension is a chronic condition that one of the prominent reasons behind cardiovascular disease, brain stroke, and organ failure. Left unnoticed untreated, deterioration in health could even result mortality. If it can be detected early, with proper treatment, undesirable outcomes avoided. Until now, gold standard invasive way measuring blood pressure (BP) using catheter. Additionally, cuff-based noninvasive methods are too cumbersome or inconvenient for frequent measurement BP. With advancement sensor technology, signal processing techniques, machine learning algorithms, researchers trying to find perfect relationships between biomedical signals changes This paper literature review studies conducted on cuffless BP signals. Relevant articles were selected specific criteria, then traditional techniques discussed along motivation use algorithms. The focused progression different rather than comparing performance among studies. survey concluded deep proved most accurate all techniques. On other side, this accuracy has several disadvantages, such as lack interpretability, computationally extensive, validation protocol, collaboration professionals. continuing work by progressing potential solution these challenges. Finally, future research directions have been provided encounter

Language: Английский

---

Wearable cuffless blood pressure monitoring: From flexible electronics to machine learning

Wearable electronics., Journal Year: 2024, Volume and Issue: 1, P. 78 - 90

Published: May 17, 2024

Hypertension significantly contributes to the widespread occurrence of cardiovascular disease globally. Routine portable blood pressure monitoring is crucial for prevention and screening hypertension. Nevertheless, bulky nature cuff sphygmomanometers commonly used in clinical settings causes discomfort patients. Wearable cuffless has received significant attention as a result. Advances flexible electronics machine learning have provided new impetus development wearable monitoring, offering potential solutions these challenges. Here, we review theoretical foundations, sensors back-end signal processing from full-process perspective, particularly emphasizes developments introduced by learning. Flexible mechanical sensors, optical ultrasonic electrodes efficiently capture signals related pressure, while enabled accurately analyzes raw into waveforms. Finally, future challenges opportunities are envisioned.

Language: Английский

---

Towards Ultrasound Wearable Technology for Cardiovascular Monitoring: From Device Development to Clinical Validation

IEEE Reviews in Biomedical Engineering, Journal Year: 2024, Volume and Issue: 18, P. 93 - 112

Published: June 6, 2024

The advent of flexible, compact, energy-efficient, robust, and user-friendly wearables has significantly impacted the market growth, with an estimated value 61.30 billion USD in 2022. Wearable sensors have revolutionized in-home health monitoring by warranting continuous measurements vital parameters. Ultrasound is used to non-invasively, safely, continuously record next generation smart ultrasonic devices for healthcare integrates microelectronics stretchable patches body-conformable devices. They offer not only wearability, user comfort, but also higher tracking accuracy immediate changes cardiovascular Moreover, due fixed adhesion skin, errors derived from probe placement or patient movement are mitigated, even though at correct anatomical location still critical requires a user's skill knowledge. In this review, steps required bring wearable systems into medical (technologies, device development, signal-processing, in-lab validation, and, finally, clinical validation) discussed. vascular ultrasound its future research directions many possibilities modernizing assessment quality personalized care home monitoring.

Language: Английский

---

Screen-Printable Iontronic Pressure Sensor with Thermal Expansion Microspheres for Pulse Monitoring

ACS Applied Materials & Interfaces, Journal Year: 2024, Volume and Issue: 16(30), P. 39561 - 39571

Published: July 23, 2024

Constructing microstructures to improve the sensitivity of flexible pressure sensors is an effective approach. However, preparation usually involves inverted molds or subtractive manufacturing methods, which are difficult in large-scale (e.g., screen printing) preparation. To solve this problem, we introduced thermally expandable microspheres for printing fabricate sensors. Thermally can be constructed into by simple heating after printing, simplifies microstructure fabrication step. In addition, added also used as ionic liquid reservoir materials further increase capacitance change and sensitivity. The prepared exhibited superior performance, including ultrahigh (Smax = 49999.5 kPa–1) wide detection range (0–350 kPa). Even 30,000 cycles at a high 300 kPa low 30 kPa, sensor showed minimal signal degradation, demonstrating long-term cycling stability. order verify practical potential sensors, performed human radial artery beat experiments using these variations intensity 3D pulse wave observed very clearly, important health monitoring. above demonstrates that our strategy provide approach high-performance

Language: Английский

---

Innovations in Quantitative Rapid Testing: Early Prediction of Health Risks

Current Problems in Cardiology, Journal Year: 2025, Volume and Issue: unknown, P. 103000 - 103000

Published: Feb. 1, 2025

Language: Английский

---

AI for the hemodynamic assessment of critically ill and surgical patients: focus on clinical applications

Annals of Intensive Care, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 24, 2025

Abstract Several artificial intelligence (AI)-driven tools have emerged for the hemodynamic evaluation of critically ill and surgical patients. This article provides an overview current developments potential clinical applications machine learning (ML) blood pressure measurements, hypotension prediction, profiling, echocardiography. ML algorithms shown promise in enabling continuous, non-invasive monitoring by analyzing pulse oximetry waveforms, though these methods require periodic calibration with traditional oscillometric brachial cuffs. Additionally, a variety models been trained to forecast impending hypotension. However, research indicates that often primarily rely on mean arterial pressure, leading questions about their added predictive value. The issue false-positive alerts is also significant can result unwarranted interventions. In terms proposed automatically classify patients into specific endotypes. evidence suggests tend replicate conventional profiles found medical textbooks or depicted advanced monitors. raises practical utility, especially given occasional discrepancies could impact treatment decisions. Point-of-care ultrasound (POCUS) has gained traction evaluating cardiac function experiencing circulatory shock. now embedded some POCUS systems assist recognizing images, guiding users optimal imaging, automating reducing variability key echocardiographic measurements. These capabilities are beneficial novice operators, potentially enhancing accuracy confidence decision-making. conclusion, while several AI-based technologies show refining assessment both patients, value varies. Comprehensive validation studies real-world testing essential identify which innovations will genuinely contribute improving quality care.

Language: Английский

---

A finger on the pulse of cardiovascular health: estimating blood pressure with smartphone photoplethysmography-based pulse waveform analysis

BioMedical Engineering OnLine, Journal Year: 2025, Volume and Issue: 24(1)

Published: March 20, 2025

Smartphone photoplethysmography (PPG) offers a cost-effective and accessible method for continuous blood pressure (BP) monitoring, but faces persistent challenges with accuracy interpretability. This study addresses these limitations through series of strategies. Data quality was enhanced to improve the performance traditional statistical models, while SHapley Additive exPlanations (SHAP) analysis ensured transparency in machine learning models. Waveform features were analyzed establish theoretical connections BP measures, feature engineering techniques applied enhance prediction model Bland–Altman conducted, results compared against reference devices using multiple international standards evaluate method's feasibility. collected from 127 participants demonstrated strong correlations between smartphone-derived digital waveform those devices. The mean absolute errors (MAE) systolic (SBP), diastolic (DBP), pulse (PP) linear regression models 7.75, 6.35, 4.49 mmHg, respectively. Random forest further improved values 7.34, 5.79, 4.45 mmHg. Feature importance identified key contributions time-domain, frequency-domain, curvature-domain, demographic features. However, revealed systematic biases, barely meet established standards. These findings suggest that smartphone PPG technology shows promise, significant advancements are required before it can replace measurement

Language: Английский

---