The Relevance of Calibration in Machine Learning-Based Hypertension Risk Assessment Combining Photoplethysmography and Electrocardiography DOI Creative Commons
Jesús Cano, Lorenzo Fácila, Juan M. Gracia-Baena

et al.

Biosensors, Journal Year: 2022, Volume and Issue: 12(5), P. 289 - 289

Published: May 1, 2022

The detection of hypertension (HT) is great importance for the early diagnosis cardiovascular diseases (CVDs), as subjects with high blood pressure (BP) are asymptomatic until advanced stages disease. present study proposes a classification model to discriminate between normotensive (NTS) and hypertensive (HTS) employing electrocardiographic (ECG) photoplethysmographic (PPG) recordings an alternative traditional cuff-based methods. A total 913 ECG, PPG BP from 69 were analyzed. Then, signal preprocessing, fiducial points extraction feature selection performed, providing 17 discriminatory features, such pulse arrival transit times, that fed machine-learning-based classifiers. main innovation proposed in this research uncovers relevance previous calibration obtain accurate HT risk assessment. This aspect has been assessed using both close distant time test measurements respect calibration. k-nearest neighbors-classifier provided best outcomes accuracy new before 51.48%. inclusion just one measurement into improved by 30%, reaching gradually more than 96% six measurements. Accuracy decreased distance calibration, but remained outstanding even days after Thus, use ECG combined subject can significantly improve discrimination NTS HTS individuals. strategy could be implemented wearable devices assessment well prevent CVDs.

Language: Английский

Ultra‐Thin Flexible Encapsulating Materials for Soft Bio‐Integrated Electronics DOI
Mingyu Sang, Kyubeen Kim, Jongwoon Shin

et al.

Advanced Science, Journal Year: 2022, Volume and Issue: 9(30)

Published: Aug. 28, 2022

Abstract Recently, bioelectronic devices extensively researched and developed through the convergence of flexible biocompatible materials electronics design that enables more precise diagnostics therapeutics in human health care opens up potential to expand into various fields, such as clinical medicine biomedical research. To establish an accurate stable bidirectional bio‐interface, protection against external environment high mechanical deformation is essential for wearable devices. In case implantable bioelectronics, special encapsulation optimized designs configurations provide electronic stability functionality are required accommodating organ properties, lifespans, functions biofluid environment. Here, this study introduces recent developments ultra‐thin encapsulations with novel can preserve or even improve electrical performance bio‐integrated by supporting safety from destruction contamination well optimizing use systems physiological environments. addition, a summary materials, methods, characteristics most widely used technologies introduced, thereby providing strategic selection appropriate choices recently bioelectronics.

Language: Английский

Citations

77
Wearable blood pressure sensors for cardiovascular monitoring and machine learning algorithms for blood pressure estimation DOI

Seongwook Min,

Jaehun An,

Jae Hee Lee

et al.

Nature Reviews Cardiology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 18, 2025

Language: Английский

Citations

2
Artificial Intelligence in Hypertension Management: An Ace up Your Sleeve DOI Creative Commons
Valeria Visco, Carmine Izzo, Costantino Mancusi

et al.

Journal of Cardiovascular Development and Disease, Journal Year: 2023, Volume and Issue: 10(2), P. 74 - 74

Published: Feb. 9, 2023

Arterial hypertension (AH) is a progressive issue that grows in importance with the increased average age of world population. The potential role artificial intelligence (AI) its prevention and treatment firmly recognized. Indeed, AI application allows personalized medicine tailored for each patient. Specifically, this article reviews benefits AH management, pointing out diagnostic therapeutic improvements without ignoring limitations innovative scientific approach. Consequently, we conducted detailed search on applications AH: articles (quantitative qualitative) reviewed paper were obtained by searching journal databases such as PubMed subject-specific professional websites, including Google Scholar. terms included intelligence, neural network, deep learning, machine big data, arterial hypertension, blood pressure, pressure measurement, cardiovascular disease, medicine. AI-based systems could help continuously monitor BP using wearable technologies; particular, can be estimated from photoplethysmograph (PPG) signal smartphone or smartwatch DL. Furthermore, thanks to ML algorithms, it possible identify new genes early diagnosis complications. Moreover, integrating omics-based technologies will lead definition trajectory hypertensive patient use most appropriate drug. However, not free technical issues biases, over/underfitting, “black-box” nature many data privacy. In conclusion, change clinical practice identifying trajectories new, care plans predicting patients’ risks necessary therapy adjustments due changes disease progression and/or response.

Language: Английский

Citations

41
Brazilian Guidelines for In-office and Out-of-office Blood Pressure Measurement – 2023 DOI Creative Commons
Audes D. M. Feitosa, Weimar Kunz Sebba Barroso, Décio Mion

et al.

Arquivos Brasileiros de Cardiologia, Journal Year: 2024, Volume and Issue: 121(4)

Published: Jan. 1, 2024

Language: Английский

Citations

11
Diretrizes Brasileiras de Medidas da Pressão Arterial Dentro e Fora do Consultório – 2023 DOI Creative Commons
Audes D. M. Feitosa, Weimar Kunz Sebba Barroso, Décio Mion

et al.

Arquivos Brasileiros de Cardiologia, Journal Year: 2024, Volume and Issue: 121(4)

Published: Jan. 1, 2024

Citations

9
A Review of Noninvasive Methodologies to Estimate the Blood Pressure Waveform DOI Creative Commons
Tasbiraha Athaya, Sunwoong Choi

Sensors, Journal Year: 2022, Volume and Issue: 22(10), P. 3953 - 3953

Published: May 23, 2022

Accurate estimation of blood pressure (BP) waveforms is critical for ensuring the safety and proper care patients in intensive units (ICUs) intraoperative hemodynamic monitoring. Normal cuff-based BP measurements can only provide systolic (SBP) diastolic (DBP). Alternatively, waveform be used to estimate a variety other physiological parameters provides additional information about patient’s health. As result, various techniques are being proposed accurately estimating waveforms. The purpose this review summarize current state knowledge regarding waveform, three methodologies (pressure-based, ultrasound-based, deep-learning-based) noninvasive research feasibility employing these strategies at home as well ICUs. Additionally, article will discuss physical concepts underlying both invasive measurements. We historical measurements, standard clinical procedures, more recent innovations Although technique has not been validated, it expected that precise, available near future due its enormous potential.

Language: Английский

Citations

37
Smartwatch-Based Blood Pressure Measurement Demonstrates Insufficient Accuracy DOI Creative Commons
Maarten Falter, Martijn Scherrenberg, Karen Driesen

et al.

Frontiers in Cardiovascular Medicine, Journal Year: 2022, Volume and Issue: 9

Published: July 11, 2022

Novel smartwatch-based cuffless blood pressure (BP) measuring devices are coming to market and receive FDA CE labels. These often insufficiently validated for clinical use. This study aims investigate a recently CE-cleared smartwatch using BP measurement in population with normotensive hypertensive individuals scheduled 24-h measurement.Patients that were ambulatory monitoring (ABPM) recruited received an additional Samsung Galaxy Watch Active 2 simultaneous on their opposite arm. After calibration, patients asked measure as much possible period. Manual activation of the is necessary BP. Accuracy was calculated sensitivity, specificity, positive negative predictive values ROC curves. Bland-Altman method Taffé methods used bias precision assessment. variability average real variability, standard deviation coefficient variation.Forty included. demonstrated proportional bias, which low systolic BPs overestimated, high underestimated. Diastolic all increasing toward lower BPs. Sensitivity specificity detecting and/or diastolic hypertension 83 41%, respectively. curves demonstrate area under curve (AUC) 0.78 0.93 hypertension. systematically higher ABPM measurements compared measurements.This demonstrates by show systematic calibration point, overestimating underestimating BPs, when investigated both patients. Standards traditional non-invasive sphygmomanometers not met, but these standards fully applicable devices, emphasizing urgent need new devices. The yet ready usage. Future studies needed further validate wearable also possibilities non-invasive, high-frequency monitoring.

Language: Английский

Citations

33
Wearable Two-Dimensional Nanomaterial-Based Flexible Sensors for Blood Pressure Monitoring: A Review DOI Creative Commons

Siti Nor Ashikin Ismail,

Nazrul Anuar Nayan, Muhammad Aniq Shazni Mohammad Haniff

et al.

Nanomaterials, Journal Year: 2023, Volume and Issue: 13(5), P. 852 - 852

Published: Feb. 24, 2023

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

Language: Английский

Citations

19
Recent Advances in Materials, Devices and Algorithms Toward Wearable Continuous Blood Pressure Monitoring DOI
Jian Li, Hongwei Chu, Zhenlin Chen

et al.

ACS Nano, Journal Year: 2024, Volume and Issue: 18(27), P. 17407 - 17438

Published: June 26, 2024

Continuous blood pressure (BP) tracking provides valuable insights into the health condition and functionality of heart, arteries, overall circulatory system humans. The rapid development in flexible wearable electronics has significantly accelerated advancement BP monitoring technologies. However, several persistent challenges, including limited sensing capabilities stability sensors, poor interfacial between sensors skin, low accuracy estimation, have hindered progress monitoring. To address these comprehensive innovations materials design, device development, optimization, modeling been pursued to improve performance systems. In this review, we highlight latest advancements systems toward continuous noninvasive with a primary focus on integration, theoretical algorithms. Existing potential solutions, further research directions are also discussed provide technical guidance for future ambulatory measurement enhanced capability, robustness, long-term accuracy.

Language: Английский

Citations

8
Flexible Optical Fiber Sensing: Materials, Methodologies, and Applications DOI Creative Commons
Jiulin Gan, Anping Yang, Qianyi Guo

et al.

Advanced Devices & Instrumentation, Journal Year: 2024, Volume and Issue: 5

Published: Jan. 1, 2024

Advances in stretchable and flexible sensors are meeting the demands of an expanding range applications, such as wearable healthcare, vivo monitoring, soft interactive robots. Unlike conventional rigid sensors, elastic material-based more adaptable to applied objects which involve dynamic irregular surfaces. Flexible optical fiber offer superior advantages over electronic including high sensitivity, rapid response time, biocompatibility, immunity electromagnetic interference, enhanced safety. These desirable features have propelled them become a prominent category, witnessing substantial advancements recent years. This technology has successfully facilitated diverse human health biological measurements, human-machine interfaces. In this review, we provide concise overview latest developments sensing, focusing on key aspects, preparation materials, methodologies, applications. Furthermore, valuable insights into potential challenges opportunities that lie ahead field sensing technology.

Language: Английский

Citations

7