Cuffless Blood Pressure Monitor for Home and Hospital Use

Sensors, Год журнала: 2025, Номер 25(3), С. 640 - 640

Опубликована: Янв. 22, 2025

Cardiovascular diseases, particularly hypertension, pose a significant threat to global health, often referred as “silent killer”. Traditional cuff-based blood pressure monitors have limitations in terms of convenience and continuous monitoring capabilities. As an alternative, cuffless offer promising approach for the detection prevention hypertension. Despite their potential, achieving clinical performance standards remains challenge. This review focuses on principles device, current research development, devices that are currently approved medical devices. Then, we describe measures meet home requirements. In addition, provide thoughts validating accuracy hospital setting.

Язык: Английский

---

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

IEEE Reviews in Biomedical Engineering, Год журнала: 2024, Номер 18, С. 93 - 112

Опубликована: Июнь 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.

Язык: Английский

---

Non-Contact Optical Blood Pressure Biometry Using AI Analysis of Fundus Imaging

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Янв. 7, 2025

This study was developed to determine whether a machine learning model could be assess blood pressure with accuracy comparable arm cuff measurements. A deep based on the UK Biobank dataset and trained detect both systolic diastolic pressure. The hypothesis formulated after data collection before development of model. Comparison conducted between measurements, as ground truth, results from model, using Mean Absolute Error, Squared Coefficient Determination (R^2). Systolic measured 9.81 165.13 Error 0.36 R^2. Diastolic 6.00 58.21 0.30 improves existing research shows errors variability hand use fundus images may more indicative long-term hypertension. Additional trials in clinical settings necessary, well additional prospective studies validate results.

Язык: Английский

---

Objets connectés dans le domaine de l’hypertension artérielle

Archives des Maladies du Coeur et des Vaisseaux - Pratique, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

---

Non-Contact Blood Pressure Monitoring Using Radar Signals: A Dual-Stage Deep Learning Network

Bioengineering, Год журнала: 2025, Номер 12(3), С. 252 - 252

Опубликована: Март 2, 2025

Emerging radar sensing technology is revolutionizing cardiovascular monitoring by eliminating direct skin contact. This approach captures vital signs through electromagnetic wave reflections, enabling contactless blood pressure (BP) tracking while maintaining user comfort and privacy. We present a hierarchical neural framework that synergizes spatial temporal feature learning for radar-driven, BP monitoring. By employing advanced preprocessing techniques, the system subtle chest wall vibrations their second-order derivatives, feeding dual-channel inputs into network. Specifically, Stage 1 deploys convolutional depth-adjustable lightweight residual blocks to extract features from micro-motion characteristics, 2 employs transformer architecture establish correlations between these periodic dynamic variations. Drawing on intrinsic link systolic (SBP) diastolic (DBP) pressures, early estimates are used expand set second-stage network, boosting its predictive power. Validation achieved clinically acceptable errors (SBP: −1.09 ± 5.15 mmHg, DBP: −0.26 4.35 mmHg). Notably, this high degree of accuracy, combined with ability estimate at s intervals, closely approximates real-time, beat-to-beat monitoring, representing pivotal breakthrough in non-contact

Язык: Английский

---

Controversy in Hypertension: Pro-Side of the Argument Using Artificial Intelligence for Hypertension Diagnosis and Management

Hypertension, Год журнала: 2025, Номер unknown

Опубликована: Март 17, 2025

Hypertension presents the largest modifiable public health challenge due to its high prevalence, intimate relationship cardiovascular diseases, and complex pathogenesis pathophysiology. Low awareness of blood pressure elevation suboptimal hypertension diagnosis serve as major hurdles in effective management. Advances artificial intelligence have permitted integrative analysis large data sets including omics, clinical (with novel sensor wearable technologies), health-related, social, behavioral, environmental sources, hold transformative potential achieving large-scale, data-driven approaches toward personalized diagnosis, treatment, long-term However, although emerging science may advance concept precision discovery, drug targeting development, patient care, management, adoption at scale today is lacking. Recognizing that implementation intelligence–based solutions need evidence generation, this opinion statement examines a clinician-centric perspective state-of-art using management puts forward recommendations equitable care.

Язык: Английский

---

Cuffless Blood Pressure Measurement: Where Do We Actually Stand?

Hypertension, Год журнала: 2025, Номер unknown

Опубликована: Апрель 15, 2025

Cuffless blood pressure (BP) measurement offers considerable potential for clinical practice but is a challenging technological field. Many are investigating pulse wave analysis with or without arrival time in which machine learning applied to pulsatile waveforms obtained mobile devices (eg, wristbands, smartphones) estimate BP. These methods generally require individual user calibration cuff BP measurements demographics age, sex). This makes it difficult evaluate the method’s accuracy, and many studies claiming accuracy used inadequate testing procedures. Yet, publications regulatory-cleared continue rise, seemingly implying advancements. An update provided on flurry of activity cuffless technologies over last 2 3 years, covering need, latest devices, recent based time, progress developing validation standards other principles. Despite high volume research development, date, there no compelling evidence that can provide significant added value beyond demographic data calibration. Thus, reasonable at least be skeptical published future uncertain It important focus establishing robust requiring also pursuing calibration-free methodologies going forward.

Язык: Английский

---

Optimized machine learning for real-time, non-invasive blood pressure monitoring

The Journal of Supercomputing, Год журнала: 2025, Номер 81(7)

Опубликована: Май 3, 2025

Язык: Английский

---

Predicting blood pressure without a cuff using a unique multi-modal wearable device and machine learning algorithm

Computers in Biology and Medicine, Год журнала: 2025, Номер 192, С. 110357 - 110357

Опубликована: Май 12, 2025

Blood pressure is a critical risk factor for cardiovascular diseases (CVDs), yet most adults do not monitor it frequently enough to prevent serious complications. This in part because the traditional cuff-based method inconvenient, uncomfortable, and does allow continuous monitoring. To address these constraints, we developed unique multi-modal wearable device used random forest regression (RFR) algorithm that resulted model capable of accurate cuffless blood prediction. features two photoplethysmography (PPG) sensors bioimpedance (BioZ) measure pulse wave propagation along radial artery on wrist. The redundancy design enhances prediction accuracy. validate device, novel human subject study protocol was also allows an individual's rise safely repeatably by more than 40 mmHg (systolic pressure) from baseline measurements. In this study, using multiple pulsatile waveforms PPG BioZ as inputs into machine learning algorithm, showed had higher accuracy models single sensor. Specifically, training, validation, leaving one out data sets all mean absolute errors less 3.3 both systolic diastolic pressures (BPs). While results test were promising, subject-wise evaluation variability depending how well BP distribution matched training set. These findings demonstrate potential universal estimation, with further validation needed diverse populations. Thus, accompaniment RFR offers robust monitoring, providing practical solution long-term health management.

Язык: Английский

---

Towards ultrasound wearable technology for cardiovascular monitoring: from device development to clinical validation

Опубликована: Апрель 8, 2024

Язык: Английский

---