Applications of artificial intelligence for hypertension management

Tsoi, Kelvin K.; Yiu, Karen; Lee, Helen; Cheng, Hao‐Min; Wang, Tzung‐Dau; Tay, Jam-Chin; Teo, Boon Wee; Turana, Yuda; Soenarta, Arieska Ann; Sogunuru, Guru Prasad; Siddique, Saulat; Chia, Yook Chin; Shin, Jinho; Wang, Ji‐Guang; Kario, Kazuomi

doi:10.1111/jch.14180

Cited by 38 publications

(22 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…(1))], hypertension affects around 1.13 billion people globally, resulting in millions of fatalities each year (2). In developed countries, hypertension affects about one-third of the individuals in the United States [(US); (3)], 26.3 million (37.5%) people in Japan (4), 30.5% of Koreans (5), and 30.1% of the French (6).…”

Section: Introductionmentioning

confidence: 99%

“…Hypertension, one of the most frequent chronic disorders found in almost every country, has become a worldwide public health issue. According to data from the World Health Organization's Global Health Observatory [(GHO; ( 1 ))], hypertension affects around 1.13 billion people globally, resulting in millions of fatalities each year ( 2 ). In developed countries, hypertension affects about one-third of the individuals in the United States [(US); ( 3 )], 26.3 million (37.5%) people in Japan ( 4 ), 30.5% of Koreans ( 5 ), and 30.1% of the French ( 6 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Follow-up management service and health outcomes of hypertensive patients in China: A cross-sectional analysis from the national health service survey in Jiangsu province

Peng

Shi²,

Zhu³

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

BackgroundHypertension is a major cause of early mortality worldwide. Health follow-up management services can encourage patients with hypertension to improve their health behavior and outcomes. However, a lack of studies on the relationship between specific factors of follow-up management and both subjective and objective health outcome among hypertensive patients exists. The current study investigated the relationship between service content, frequency, mode, and institutions of follow-up management and health outcomes among Chinese hypertensives.MethodsData were obtained from the sixth National Health Service Survey (NHSS) of Jiangsu Province, which was conducted in 2018. Descriptive statistics were used to analyze the sample characteristics and the utilization of follow-up management services. Both multiple linear regression and logistic regression were used to estimate the association of follow-up management service and other factors with hypertensives' subjective and objective health outcomes.ResultSome respondents (19.30%) reported hypertension, and 75.36% of these patients obtained follow-up management services. Hypertensive patients' subjective health outcome self-reported health status and objective health outcome blood pressure (BP) control were found to be significantly associated with follow-up management services. The outcomes were both significantly improved by a high frequency of management services, a high level of follow-up providers, the mode of visiting healthcare facilities and/or calling, and receiving instructions on medication use. However, inquiring about patients' symptoms was negatively associated with self-reported health status and BP control. In addition, BP measurement was significantly and positively associated with hypertensive patients' self-reported health status; the patients receiving lifestyle guidance were more likely to have their BP levels under control.ConclusionsHypertension management strategies should further focus on the frequency of healthcare follow-up management via categorization of the follow-up services and appropriate adjustment of service delivery modes to optimize health follow-up management for hypertensives further improve their outcomes. Meanwhile, complementary policies are also needed to address other socioeconomic factors that can promote good health conditions for hypertension patients.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Follow-up management service and health outcomes of hypertensive patients in China: A cross-sectional analysis from the national health service survey in Jiangsu province

Peng

Shi²,

Zhu³

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Physiological signals can be collected through wearable devices 24 hours a day, 7 days a week, producing big amounts of data, which are analysed through Artificial Intelligence (AI) algorithms more and more frequently, in order to provide useful information for the so-called decision-making processes [20], [21], thus supporting human choices in different fields, from Industry 4.0 [22], [23] to eHealth [24]. The purposes can be different: emotion classification [25], activity recognition [26], hypertension management [27], fall detection [28], smart living environments and well-being assessment [29], and so on. In order to be able to develop robust models, capable to provide reliable information, data quality is fundamental [30]; in this perspective, not only hardware and acquisition options (e.g.…”

Section: Introductionmentioning

confidence: 99%

The importance of physiological data variability in wearable devices for digital health applications

et al. 2022

View full text Add to dashboard Cite

<p>This paper aims at characterizing the variability of physiological data collected through a wearable device (Empatica E4), given that both intra- and inter-subject variability play a pivotal role in digital health applications, where Artificial Intelligence (AI) techniques have become popular. Inter-beat intervals (IBIs), ElectroDermal Activity (EDA) and Skin Temperature (SKT) signals have been considered and variability has been evaluated in terms of general statistics (mean and standard deviation) and coefficient of variation. Results show that both intra- and inter-subject variability values are significant, especially when considering those parameters describing how the signals vary over time. Moreover, EDA seems to be the signal characterized by the highest variability, followed by IBIs, contrary to SKT that results more stable.<br />This variability could affect AI algorithms in classifying signals according to particular discriminants (e.g. emotions, daily activities, etc.), taking into account the dual role of variability: hindering a net distinction between classes, but also making algorithms more robust for deep learning purposes thanks to the consideration of a wide test population. Indeed, it is worthy to note that variability plays a fundamental role in the whole measurement chain, characterizing data reliability and impacting on the final results accuracy and consequently on decision-making processes.</p>

show abstract

“…Artificial Intelligence (AI) and digital medicine are emerging approaches to address the challenge of hypertension management. [ 14,15 ] However, many of the tools in those categories are based on big data that train population‐derived models to treat individuals. This inherently challenges the ability to truly personalize treatment.…”

Section: Introductionmentioning

confidence: 99%

Harnessing CURATE.AI for N‐of‐1 Optimization Analysis of Combination Therapy in Hypertension Patients: A Retrospective Case Series

Truong

Tan

Chew

et al. 2021

Advanced Therapeutics

View full text Add to dashboard Cite

Hypertension is a global public health challenge that imposes a significant burden on patients and healthcare systems. Conventional treatment involves dose escalation of an antihypertensive drug, and if the desired response is not achieved, patients are prescribed another drug, often in combination with other therapies. Importantly, drug synergy is dose‐, time‐ and patient‐dependent. Coupled with the challenges of intra‐ and inter‐individual variability, standard care can lead to sub‐optimal outcomes, additional visits, and adherence issues. Furthermore, these factors can cause the additional complication of patients being misperceived as refractory to regimens that are sub‐optimally administered. A scalable strategy that can longitudinally optimize patient response would be a powerful advance for chronic disease management. This four‐patient case series reports the application of CURATE.AI as a mechanism‐independent and disease‐agnostic platform for a retrospective N‐of‐1 (personalized) dose optimization using each patient's own data, including drug doses and corresponding changes in blood pressures. This approach may enable the rapid prediction of treatment response and the identification of optimal doses that may yield improved outcomes. CURATE.AI can be implemented in clinical workflows without creating additional burden of extensive data collection. The findings from this study support the prospective validation of CURATE.AI to optimize hypertension management.

show abstract

Applications of artificial intelligence for hypertension management

Abstract: This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

Cited by 38 publications

References 45 publications

Follow-up management service and health outcomes of hypertensive patients in China: A cross-sectional analysis from the national health service survey in Jiangsu province

Follow-up management service and health outcomes of hypertensive patients in China: A cross-sectional analysis from the national health service survey in Jiangsu province

The importance of physiological data variability in wearable devices for digital health applications

Harnessing CURATE.AI for N‐of‐1 Optimization Analysis of Combination Therapy in Hypertension Patients: A Retrospective Case Series

Contact Info

Product

Resources

About