A Continuous Non-Invasive Blood Pressure Prediction Method Based on Deep Sparse Residual U-Net Combined with Improved Squeeze and Excitation Skip Connections.

Arterial blood pressure (ABP) serves as a pivotal clinical metric in cardiovascular health assessments, with the precise forecasting of continuous blood pressure assuming a critical role in both preventing and treating cardiovascular diseases. This study proposes a novel continuous non-invasive blood pressure prediction model, DSRUnet, based on deep sparse residual U-net combined with improved SE skip connections, which aim to enhance the accuracy of using photoplethysmography (PPG) signals for continuous blood pressure prediction. The model first introduces a sparse residual connection approach for path contraction and expansion, facilitating richer information fusion and feature expansion to better capture subtle variations in the original PPG signals, thereby enhancing the network's representational capacity and predictive performance and mitigating potential degradation in the network performance. Furthermore, an enhanced SE-GRU module was embedded in the skip connections to model and weight global information using an attention mechanism, capturing the temporal features of the PPG pulse signals through GRU layers to improve the quality of the transferred feature information and reduce redundant feature learning. Finally, a deep supervision mechanism was incorporated into the decoder module to guide the lower-level network to learn effective feature representations, alleviating the problem of gradient vanishing and facilitating effective training of the network. The proposed DSRUnet model was trained and tested on the publicly available UCI-BP dataset, with the average absolute errors for predicting systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean blood pressure (MBP) being 3.36 ± 6.61 mmHg, 2.35 ± 4.54 mmHg, and 2.21 ± 4.36 mmHg, respectively, meeting the standards set by the Association for the Advancement of Medical Instrumentation (AAMI), and achieving Grade A according to the British Hypertension Society (BHS) Standard for SBP and DBP predictions. Through ablation experiments and comparisons with other state-of-the-art methods, the effectiveness of DSRUnet in blood pressure prediction tasks, particularly for SBP, which generally yields poor prediction results, was significantly higher. The experimental results demonstrate that the DSRUnet model can accurately utilize PPG signals for real-time continuous blood pressure prediction and obtain high-quality and high-precision blood pressure prediction waveforms. Due to its non-invasiveness, continuity, and clinical relevance, the model may have significant implications for clinical applications in hospitals and research on wearable devices in daily life.

Validation of oscillometric ratio and maximum gradient methods for non-invasive blood pressure measurement with intra-arterial blood pressure measurements as reference.

Most non-invasive blood pressure (BP) measurements are carried out using instruments which implement either the Ratio or the Maximum Gradient oscillometric method, mostly during cuff deflation, but more rarely during cuff inflation. Yet, there is little published literature on the relative advantages and accuracy of these two methods. In this study of 40 lightly sedated individuals aged 64.1 ± 9.6 years, we evaluate and compare the performance of the oscillometric ratio (K) and gradient (Grad) methods for the non-invasive estimation of mean pressure, SBP and DBP with reference to invasive intra-arterial values. There was no significant difference between intra-arterial estimates of mean pressure made via Korotkoff sounds (MP-OWE) or the gradient method (MP-Grad). However, 17.7% of MP-OWE and 15% of MP-Grad were in error by more than 10 mmHg. SBP-K and SBP-Grad underestimated SBP by 14 and 18 mmHg, whilst accurately estimating DBP with mean errors of 0.4 ±â€Š5.0 and 1.7 ±â€Š6.1 mmHg, respectively. Relative to the reference standard SBP-K, SBP-Grad and DBP-Grad were estimated with a mean error of -4.5 ±â€Š6.6 and 1.4 ±â€Š5.6 mmHg, respectively, noting that using the full range of recommended ratios introduces errors of 12 and 7 mmHg in SBP and DBP, respectively. We also show that it is possible to find ratios which minimize the root mean square error (RMSE) and the mean error for any particular individual cohort. We developed linear models for estimating SBP and SBP-K from a range of demographic and non-invasive OWE variables with resulting mean errors of 0.15 ±â€Š5.6 and 0.3 ±â€Š5.7 mmHg, acceptable according to the Universal standard.

Blood Pressure Lowering in Patients With Central Hypertension: A Randomized Clinical Trial.

BACKGROUND: Cuff blood pressure (BP) is recommended for guiding hypertension management. However, central BP has been proposed as a superior clinical measurement. This study aimed to determine whether controlling hypertension as measured by central BP was beneficial in reducing left ventricular mass index beyond control of standard cuff hypertension. METHODS: This multicenter, open-label, blinded-end point trial was conducted in individuals treated for uncomplicated hypertension with controlled cuff BP (<140/90 mm Hg) but elevated central BP (≥0.5 SD above age- and sex-specific normal values). Participants were randomized to 24-months intervention with spironolactone 25 mg/day (n=148) or usual care control (n=153). The primary outcome was change in left ventricular mass index measured by cardiac MRI. Cuff and central BPs were measured by clinic, 7-day home and 24-hour ambulatory BPs. RESULTS: At 24-months, there was a greater reduction in left ventricular mass index (-3.2 [95% CI, -5.0 to -1.3] g/m2; P=0.001) with intervention compared with control. Cuff and central BPs were lowered by a similar magnitude across all BP measurement modes (eg, clinic cuff systolic BP, -6.16 [-9.60 to -2.72] mm Hg and clinic central systolic BP, -4.96 [-8.06 to -1.86] mm Hg; P≥0.48 all). Secondary analyses found that changes in left ventricular mass index correlated to changes in BP, with the magnitude of effect nearly identical for BP measured by cuff (eg, 24-hour systolic BP, ß, 0.17 [0.02-0.31] g/m2) or centrally (24-hour systolic BP, ß, 0.16 [0.01-0.32] g/m2). CONCLUSIONS: Among individuals with central hypertension, spironolactone had beneficial effects in reducing LV mass. Secondary analyses showed that changes in LV mass were equally well associated with lower measured standard cuff BP and central BP. REGISTRATION: URL: https://www.anzctr.org.au/; Unique identifier: ACTRN12613000053729.

Hypertension Trends and Disparities Over 12 Years in a Large Health System: Leveraging the Electronic Health Records.

BACKGROUND: The digital transformation of medical data enables health systems to leverage real-world data from electronic health records to gain actionable insights for improving hypertension care. METHODS AND RESULTS: We performed a serial cross-sectional analysis of outpatients of a large regional health system from 2010 to 2021. Hypertension was defined by systolic blood pressure ≥140 mm Hg, diastolic blood pressure ≥90 mm Hg, or recorded treatment with antihypertension medications. We evaluated 4 methods of using blood pressure measurements in the electronic health record to define hypertension. The primary outcomes were age-adjusted prevalence rates and age-adjusted control rates. Hypertension prevalence varied depending on the definition used, ranging from 36.5% to 50.9% initially and increasing over time by ≈5%, regardless of the definition used. Control rates ranged from 61.2% to 71.3% initially, increased during 2018 to 2019, and decreased during 2020 to 2021. The proportion of patients with a hypertension diagnosis ranged from 45.5% to 60.2% initially and improved during the study period. Non-Hispanic Black patients represented 25% of our regional population and consistently had higher prevalence rates, higher mean systolic and diastolic blood pressure, and lower control rates compared with other racial and ethnic groups. CONCLUSIONS: In a large regional health system, we leveraged the electronic health record to provide real-world insights. The findings largely reflected national trends but showed distinctive regional demographics and findings, with prevalence increasing, one-quarter of the patients not controlled, and marked disparities. This approach could be emulated by regional health systems seeking to improve hypertension care.

Blood pressure and the hypertension care cascade in The Gambia: Findings from a nationwide survey.

Community treatment of hypertension in sub-Saharan Africa is hampered by gaps at several stages of the care cascade. We compared blood pressure (BP) levels (systolic, diastolic and pulse pressures) in four groups of participants by hypertension and treatment status. We conducted a nationally representative survey of adults 35 years and older using a multistage sampling strategy based on the 2013 Gambia Population and Housing Census. The BP measurements were taken in triplicate 5 min apart, and the average of the last two measurements was used for analysis. Systolic and diastolic BP levels and pulse pressure were compared by hypertension status using mean and 95% confidence intervals (CI). 53.1% of the sample were normotensive with mean systolic BP (SBP) of 119.2 mmHg (95% CI, 118.7-119.6) and diastolic BP (DBP) of 78.1 mmHg (77.8-78.3). Among individuals with hypertension, mean SBP was 148.7 mmHg (147.7-149.7) among those unaware of their hypertension, 152.2 mmHg (151.0-153.5) among treated individuals and was highest in untreated individuals at 159.3 mmHg (157.3-161.2). The findings were similar for DBP levels, being 93.9 mmHg (93.4-94.4) among the unaware, 95.1 mmHg (94.4-95.8) among the treated and highest at 99.1 mmHg (98.1-100.2) in untreated participants. SBP and DBP were higher in men, and SBP was as expected higher in those aged ≥55 years. BP level was similar in urban and rural areas. Our data shows high BP levels among participants with hypertension including those receiving treatment. Efforts to reduce the health burden of hypertension will require inputs at all levels of the care cascade.

One size does not fit all: universal cuff overestimates oscillometric blood pressure in persons with large arm circumference.

OBJECTIVE: Some brachial cuffs for oscillometric blood pressure (BP) measurement are claimed to cover a wide range of upper-arm circumferences; however, their validation is rarely conducted. Our aim was to compare oscillometric BP measurements obtained with a universal cuff with those obtained with an appropriately sized cuff. METHODS: We utilised the Microlife B6 Connect monitor, conducting oscillometric BP measurements in a random sequence with both a universal cuff (recommended for arm circumferences from 22 to 42 cm) and an appropriately sized cuff (medium for circumference 22-32 cm and large for 32-42 cm). We included 91 individuals with an arm circumference of 22-32 cm and 64 individuals with an arm circumference of 32-42 cm. RESULTS: For arm circumferences > 32 cm, systolic and diastolic BP measured with the universal cuff was higher than that measured with the large cuff (systolic 6.4 mmHg, 95% confidence interval [CI]). 3.9-8.8, diastolic 2.4 mmHg, 95%CI, 1.2-3.7, p < 0.001 for both). Overestimation of BP with the universal cuff was statistically significant after correcting for the sequence of measurements. No statistical difference was found between the universal cuff and medium cuff for circumferences in the 22-32 cm range. The bladder size in the universal cuff matched the dimensions of the medium-sized cuff; however, the cuff was larger. CONCLUSION: Overestimation of BP measured with a universal cuff in persons with large arm circumferences is clinically important. It poses the risk of unnecessary initiation or intensification of antihypertensive medication in persons using the universal cuff.

What is the context?Clinical guidelines recommend individualisation of the size of the cuff used for blood pressure measurement according to the circumference of the upper arm.Many blood pressure monitors are sold with a single "universal" cuff claimed to cover a wide range of upper arm sizes.We compared blood pressure obtained with the Microlife B6 Connect monitor and a "universal" cuff with the results obtained with individual sized cuffs (medium size for arm circumference between 22 and 32 cm and large size for arm circumference between 32 and 42 cm).What is new?In persons with large upper arm circumference is the systolic blood pressure 6.4 mmHg higher and the diastolic blood pressure 2.4 mmHg higher with the universal cuff than with the individual-sized large cuff.What is the impact?The universal cuff overestimates blood pressure in persons with large arm circumference.

Validation of a Suprasystolic Cuff System for Static and Dynamic Representation of the Central Pressure Waveform.

BACKGROUND: Noninvasive pulse waveform analysis is valuable for central cardiovascular assessment, yet controversies persist over its validity in peripheral measurements. Our objective was to compare waveform features from a cuff system with suprasystolic blood pressure hold with an invasive aortic measurement. METHODS AND RESULTS: This study analyzed data from 88 subjects undergoing concurrent aortic catheterization and brachial pulse waveform acquisition using a suprasystolic blood pressure cuff system. Oscillometric blood pressure (BP) was compared with invasive aortic systolic BP and diastolic BP. Association between cuff and catheter waveform features was performed on a set of 15 parameters inclusive of magnitudes, time intervals, pressure-time integrals, and slopes of the pulsations. The evaluation covered both static (subject-averaged values) and dynamic (breathing-induced fluctuations) behaviors. Peripheral BP values from the cuff device were higher than catheter values (systolic BP-residual, 6.5 mm Hg; diastolic BP-residual, 12.4 mm Hg). Physiological correction for pressure amplification in the arterial system improved systolic BP prediction (r2=0.83). Dynamic calibration generated noninvasive BP fluctuations that reflect those invasively measured (systolic BP Pearson R=0.73, P<0.001; diastolic BP Pearson R=0.53, P<0.001). Static and dynamic analyses revealed a set of parameters with strong associations between catheter and cuff (Pearson R>0.5, P<0.001), encompassing magnitudes, timings, and pressure-time integrals but not slope-based parameters. CONCLUSIONS: This study demonstrated that the device and methods for peripheral waveform measurements presented here can be used for noninvasive estimation of central BP and a subset of aortic waveform features. These results serve as a benchmark for central cardiovascular assessment using suprasystolic BP cuff-based devices and contribute to preserving system dynamics in noninvasive measurements.

Assessment and management of exaggerated blood pressure response to standing and orthostatic hypertension: consensus statement by the European Society of Hypertension Working Group on Blood Pressure Monitoring and Cardiovascular Variability.

Recent evidence suggests that an exaggerated blood pressure (BP) response to standing (ERTS) is associated with an increased risk of adverse outcomes, both in young and old individuals. In addition, ERTS has been shown to be an independent predictor of masked hypertension. In the vast majority of studies reporting on the prognostic value of orthostatic hypertension (OHT), the definition was based only on systolic office BP measurements. This consensus statement provides recommendations on the assessment and management of individuals with ERTS and/or OHT. ERTS is defined as an orthostatic increase in SBP at least 20 mmHg and OHT as an ERTS with standing SBP at least 140 mmHg. This statement recommends a standardized methodology to assess ERTS, by considering body and arm position, and the number and timing of BP measurements. ERTS/OHT should be confirmed in a second visit, to account for its limited reproducibility. The second assessment should evaluate BP changes from the supine to the standing posture. Ambulatory BP monitoring is recommended in most individuals with ERTS/OHT, especially if they have high-normal seated office BP. Implementation of lifestyle changes and close follow-up are recommended in individuals with ERTS/OHT and normotensive seated office BP. Whether antihypertensive treatment should be administered in the latter is unknown. Hypertensive patients with ERTS/OHT should be managed as any other hypertensive patient. Standardized standing BP measurement should be implemented in future epidemiological and interventional studies.

Maintenance of Normal Blood Pressure From Middle to Older Age: Results From the Atherosclerosis Risk in Communities Study.

BACKGROUND: It is unknown whether maintaining normal blood pressure (BP) from middle to older age is associated with improved health outcomes. METHODS: We estimated the proportion of Atherosclerosis Risk in Communities study participants who maintained normal BP from 1987 to 1989 (visit 1) through 1996 to 1998 and 2011 to 2013 (over 4 and 5 visits, respectively). Normal BP was defined as systolic BP <120 mm Hg and diastolic BP <80 mm Hg, without antihypertensive medication. We estimated the risk of cardiovascular disease, dementia, and poor physical functioning after visit 5. In exploratory analyses, we examined participant characteristics associated with maintaining normal BP. RESULTS: Among 2699 participants with normal BP at baseline (mean age 51.3 years), 47.1% and 15.0% maintained normal BP through visits 4 and 5, respectively. The hazard ratios comparing participants who maintained normal BP through visit 4 but not visit 5 and through visit 5 versus those who did not maintain normal BP through visit 4 were 0.80 (95% CI, 0.63-1.03) and 0.60 (95% CI, 0.42-0.86), respectively, for cardiovascular disease, and 0.85 (95% CI, 0.71-1.01) and 0.69 (95% CI, 0.54-0.90), respectively, for poor physical functioning. Maintaining normal BP through visit 5 was more common among participants with normal body mass index versus obesity at visit 1, those with normal body mass index at visits 1 and 5, and those with overweight at visit 1 and overweight or normal body mass index at visit 5, compared with those with obesity at visits 1 and 5. CONCLUSIONS: Maintaining normal BP was associated with a lower risk of cardiovascular disease and poor physical functioning.

Finger cuff versus invasive and noninvasive arterial pressure measurement in pregnant patients with obesity.

BACKGROUND: Pregnant patients with obesity may have compromised noninvasive blood pressure (NIBP) measurement. We assessed the accuracy and trending ability of the ClearSight™ finger cuff (FC) with invasive arterial monitoring (INV) and arm NIBP, in obese patients having cesarean delivery. METHODS: Participants were aged ≥18 years, ≥34 weeks gestation, and body mass index (BMI) ≥ 40 kg m-2. FC, INV, and NIBP measurements were obtained across 5-min intervals. The primary outcome was agreement of FC measurements with those of the reference standard INV, using modified Bland-Altman plots. Secondary outcomes included comparisons between FC and NIBP and NIBP versus INV, with four-quadrant plots performed to report discordance rates and evaluate trending ability. RESULTS: Twenty-three participants had a median (IQR) BMI of 45 kg m-2 (44-48). When comparing FC and INV the mean bias (SD, 95% limits of agreement) for systolic blood pressure (SBP) was 16 mmHg (17, -17.3 to 49.3 mmHg), for diastolic blood pressure (DBP) -0.2 mmHg (10.5, -20.7 to 20.3), and for mean arterial pressure (MAP) 5.2 mmHg (11.1, -16.6 to 27.0 mmHg). Discordance occurred in 54 (26%) pairs for SBP, 41 (23%) for DBP, and 41 (21.7%) for MAP. Error grid analysis showed 92.1% of SBP readings in Zone A (no-risk zone). When comparing NIBP and INV, the mean bias (95% limits of agreement) for SBP was 13.0 mmHg (16.7, -19.7 to 29.3), for DBP 5.9 mmHg (11.9, -17.4 to 42.0), and for MAP 8.2 mmHg (11.9, -15.2 to 31.6). Discordance occurred in SBP (84 of 209, 40.2%), DBP (74 of 187, 39.6%), and MAP (63 of 191, 33.0%). CONCLUSIONS: The FC and NIBP techniques were not adequately in agreement with INV. Trending capability was better for FC than NIBP. Clinically important differences may occur in the setting of the perfusion-dependent fetus.

Association Between Orthostatic Hypertension and Frailty Among Older Patients With Hypertension.

BACKGROUND: Frailty frequently coexists with hypertension in older patients. We aimed to evaluate the association between frailty and positional change in blood pressure, especially orthostatic hypertension. METHODS: Participants were recruited from 12 University hospitals in South Korea. Using a digital device, trained research nurses measured blood pressure in the supine and standing positions. Physical frailty was evaluated using the Korean version of the FRAIL questionnaire, gait speed, and handgrip strength. Orthostatic hypertension was defined as a ≥20-mm Hg increase in systolic blood pressure within 3 minutes of standing and upright systolic blood pressure of ≥140 mm Hg. RESULTS: We analyzed the data of 2065 participants who had been enrolled until December 31, 2022. The mean age was 73.2±5.6 years, and 52.0% were female. The mean blood pressure was 137.1±14.9/75.1±9.7 mm Hg. Among the participants, 1886 (91.3%) showed normal response after standing, but 94 (4.6%) had orthostatic hypertension, and 85 (4.1%) had orthostatic hypotension. Orthostatic hypertension was associated with female sex, obesity, cognitive function, physical frailty, and lower quality of life. In the multivariable analysis, body mass index and frailty status were independently associated with orthostatic hypertension. CONCLUSIONS: Orthostatic hypertension is associated with physical frailty, cognitive impairment, and low quality of life in older patients with hypertension. Therefore, evaluation of orthostatic blood pressure changes to confirm orthostatic hypertension or hypotension in frail older adults will serve as an important diagnostic procedure in vulnerable patients. Further studies are required to identify the underlying mechanisms of this association.

Association of postexercise blood pressure with cardiovascular outcomes and mortality: The CARDIA study.

Postexercise blood pressure (BP) may be a better predictor of cardiovascular risk than office BP, but there is a lack of data supporting this claim. We hypothesized that postexercise BP may be an important prognostic marker. Our aim was to evaluate the association of postexercise BP with major adverse cardiovascular events (MACE) and all-cause mortality. A total of 2581 participants (median age, 46 years; 55.9% women) from the Coronary Artery Risk Development in Young Adults study at year 20 (2005-2006) who underwent a graded exercise treadmill test using a modified Balke graded protocol were included. Postexercise BP was measured at baseline. Cox models were used to estimate the associations of postexercise BP with MACE and all-cause mortality. Participants were followed up until December 31, 2021. In the entire population, postexercise systolic BP showed no significant association with MACE or all-cause mortality, while postexercise diastolic BP was associated with MACE (hazard ratios [HR], 1.27 [95% CI, 1.06-1.52], per 10 mmHg increase) and all-cause mortality (HR, 1.26 [95% CI, 1.05-1.51], per 10 mmHg increase). In the normal BP group, postexercise systolic BP was not significantly associated with MACE or all-cause mortality, and postexercise diastolic BP was strongly associated with MACE (HR, 1.57 [95% CI, 1.18-2.09], per 10 mmHg increase). In this population-based cohort study, postexercise diastolic BP was significantly associated with the risk of MACE and all-cause mortality. Among individuals with normal BP, postexercise diastolic BP could identify those at a higher risk of cardiovascular events.

Systolic and diastolic blood pressure time in target range and cardiovascular outcomes in patients with hypertension and pre-frailty or frailty status.

In patients with hypertension and pre-frailty or frailty, the influence of systolic (SBP) and diastolic blood pressure (DBP) time in target range (TTR) on clinical outcomes is unclear. Thus, we conducted a post hoc analysis of the Systolic Blood Pressure Intervention Trial (SPRINT). Classifying 4208 participants into frail and non-frail groups using a frailty index, the study calculated blood pressure time in target range (BP-TTR) for the first three months using the Rosendaal method. The primary endpoint included a composite of nonfatal myocardial infarction (MI), acute coronary syndromes, stroke, acute decompensated heart failure (ADHF), and cardiovascular death. Relationships between BP-TTR and outcomes were analyzed using Kaplan-Meier curves, Cox models, and restricted cubic spline curves, with subgroup analysis for further insights. In a median follow-up of 3.17 years, primary outcomes occurred in 6.7% of participants. Kaplan-Meier analysis showed that a lower systolic blood pressure time in target range (SBP-TTR) (0%-25%) correlated with an increased cumulative incidence of the primary outcome (p < .001), nonfatal MI (P = .021), stroke (P = .004), and cardiovascular death (P = .002). A higher SBP-TTR (75%-<100%) was linked to a reduced risk of these outcomes. The restricted cubic spline (RCS) curve revealed a linear association between SBP-TTR and the primary outcome (non-linear P = .704). Similar patterns were observed for diastolic blood pressure time in target range (DBP-TTR). Subgroup analysis showed that the protective effect of higher SBP-TTR was less pronounced at low DBP-TTR levels (P for interaction = .023). In conclusion, this study highlights the importance of maintaining BP within the target range to mitigate cardiovascular risks in this population.

Comparisons of an automated oscillometric device with a hybrid manual auscultatory device for the Korea National Health and Nutrition Examination Survey.

This study evaluated an oscillometric device (OD), Microlife WatchBP Office AFIB, and a hybrid manual auscultatory device (AD), Greenlight 300TM, to determine a suitable blood pressure (BP) measurement device for the Korea National Health and Nutrition Examination Survey in a mercury-free context. Adhering to the 2018 Universal Standard's suggested consensus, the study involved 800 subjects (mean age 51.2 ± 17.5 years; 44.3% male), who underwent triplicate BP measurements following 5 min of rest in a randomized order (OD-first: 398 participants; AD-first: 402 participants). BP difference was calculated as OD value minus AD value, with results stratified by measurement sequence. The overall BP difference and tolerable error probability were -1.1 ± 6.5/-2.6 ± 4.9 mmHg and 89.2%/92.5% for systolic/diastolic BP (SBP/DBP), respectively. Lin's concordance correlation coefficient was 0.907/0.844 for SBP/DBP (OD-first/AD-first: 0.925/0.892 for SBP, 0.842/0.845 for DBP). The overall agreement for hypertension (BP ≥ 140 and/or 90 mmHg) was 0.71 (p < 0.0001), and the OD underestimated the overall hypertension prevalence by 5.1%. Analysis of the AD-first data revealed a lower level of agreement compared to the OD-first data; however, the observed blood pressure difference adhered to Criterion 1 of the 2018 Universal Standard. Microlife met the Criterion 1 of 2018 Universal Standard but underestimated the prevalence of hypertension. The BP discrepancy increased with higher BP levels, male sex, and smaller AC. With increasing age, the discrepancy decreased for SBP and increased for DBP.

A flexible multimodal pulse sensor for wearable continuous blood pressure monitoring.

Monitoring of arterial blood pressure via cuffless pulse waveform measurement at the wrist has an important clinical value for the early diagnosis and prevention of cardiovascular disease. However, accurate measurement of the radial pulse waveform is challenging owing to its subtle, wideband, and preload-dependent variation characteristics. Evidence shows that uncertainties or variations of wearing pressure and skin temperature can cause artifact signals in wrist pulse measurements, thus degrading blood pressure estimate accuracy and hindering precise clinical diagnosis. Herein, we report a flexible multisensory pulse sensor utilizing natural piezo-thermic transduction of human skin in conjunction with thin-film thermistors for the accurately measuring radial artery pulse waves with high fidelity and good anti-artifact performance. The flexible pulse sensor achieved a wide pressure measuring range (228.2 kPa), low detection limit (4 Pa), good linearity (R2 = 0.999), low hysteresis (2.45%), fast response (88 ms), and good durability and stability, thereby enabling accurate pulse measurement with high fidelity. The pulse sensor also monolithically integrated the simultaneous detections of skin temperature and wearing pressure for resisting artifact effects in pulse measurements. Through the fusion of multiple features extracted from the pulse waveform, wearing pressure, skin temperature and user's personal physical characteristics using an efficient multilayer perceptron, blood pressure is accurately estimated and good generalizability is achieved.

MEMS Fingertip Strain Plethysmography for Cuffless Estimation of Blood Pressure.

OBJECTIVE: To develop a cuffless method for estimating blood pressure (BP) from fingertip strain plethysmography (SPG) recordings. METHODS: A custom-built micro-electromechanical systems (MEMS) strain sensor is employed to record heartbeat-induced vibrations at the fingertip. An XGboost regressor is then trained to relate SPG recordings to beat-to-beat systolic BP (SBP), diastolic BP (DBP), mean arterial pressure (MAP) values. For this purpose, each SPG segment in this setup is represented by a feature vector consisting of cardiac time interval, amplitude features, statistical properties, and demographic information of the subjects. In addition, a novel concept, coined geometric features, are introduced and incorporated into the feature space to further encode the dynamics in SPG recordings. The performance of the regressor is assessed on 32 healthy subjects through 5-fold cross-validation (5-CV) and leave-subject-out cross validation (LSOCV). RESULTS: Mean absolute errors (MAEs) of 3.88 mmHg and 5.45 mmHg were achieved for DBP and SBP estimations, respectively, in the 5-CV setting. LSOCV yielded MAEs of 8.16 mmHg for DBP and 16.81 mmHg for SBP. Through feature importance analysis, 3 geometric and 26 integral-related features introduced in this work were identified as primary contributors to BP estimation. The method exhibited robustness against variations in blood pressure level (normal to critical) and body mass index (underweight to obese), with MAE ranges of [1.28, 4.28] mmHg and [2.64, 7.52] mmHg, respectively. CONCLUSION: The findings suggest high potential for SPG-based BP estimation at the fingertip. SIGNIFICANCE: This study presents a fundamental step towards the augmentation of optical sensors that are susceptible to dark skin tones.

CiGNN: A Causality-Informed and Graph Neural Network Based Framework for Cuffless Continuous Blood Pressure Estimation.

Causalityholds profound potentials to dissipate confusion and improve accuracy in cuffless continuous blood pressure (BP) estimation, an area often neglected in current research. In this study, we propose a two-stage framework, CiGNN, that seamlessly integrates causality and graph neural network (GNN) for cuffless continuous BP estimation. The first stage concentrates on the generation of a causal graph between BP and wearable features from the the perspective of causal inference, so as to identify features that are causally related to BP variations. This stage is pivotal for the identification of novel causal features from the causal graph beyond pulse transit time (PTT). We found these causal features empower better tracking in BP changes compared to PTT. For the second stage, a spatio-temporal GNN (STGNN) is utilized to learn from the causal graph obtained from the first stage. The STGNN can exploit both the spatial information within the causal graph and temporal information from beat-by-beat cardiac signals for refined cuffless continuous BP estimation. We evaluated the proposed method with three datasets that include 305 subjects (102 hypertensive patients) with age ranging from 20-90 and BP at different levels, with the continuous Finapres BP as references. The mean absolute difference (MAD) for estimated systolic blood pressure (SBP) and diastolic blood pressure (DBP) were 3.77 mmHg and 2.52 mmHg, respectively, which outperformed comparison methods. In all cases including subjects with different age groups, while doing various maneuvers that induces BP changes at different levels and with or without hypertension, the proposed CiGNN method demonstrates superior performance for cuffless continuous BP estimation. These findings suggest that the proposed CiGNN is a promising approach in elucidating the causal mechanisms of cuffless BP estimation and can substantially enhance the precision of BP measurement.

Visit-to-visit blood pressure variability and progression of white matter hyperintensities over 14 years.

Purpose: There is evidence that blood pressure variability (BPV) is associated with cerebral small vessel disease (SVD) and may therefore increase the risk of stroke and dementia. It remains unclear if BPV is associated with SVD progression over years. We examined whether visit-to-visit BPV is associated with white matter hyperintensity (WMH) progression over 14 years and MRI markers after 14 years.Materials and methods: We included participants with SVD from the Radboud University Nijmegen Diffusion tensor Magnetic resonance-imaging Cohort (RUNDMC) who underwent baseline assessment in 2006 and follow-up in 2011, 2015 and 2020. BPV was calculated as coefficient of variation (CV) of BP at all visits. Association between WMH progression rates over 14 years and BPV was examined using linear-mixed effects (LME) model. Regression models were used to examine association between BPV and MRI markers at final visit in participants.Results: A total of 199 participants (60.5 SD 6.6 years) who underwent four MRI scans and BP measurements were included, with mean follow-up of 13.7 (SD 0.5) years. Systolic BPV was associated with higher progression of WMH (ß = 0.013, 95% CI 0.005 - 0.022) and higher risk of incident lacunes (OR: 1.10, 95% CI 1.01-1.21). There was no association between systolic BPV and grey and white matter volumes, Peak Skeleton of Mean Diffusivity (PSMD) or microbleed count after 13.7 years.Conclusions: Visit-to-visit systolic BPV is associated with increased progression of WMH volumes and higher risk of incident lacunes over 14 years in participants with SVD. Future studies are needed to examine causality of this association.

High blood pressure (BP) is very common, especially among older individuals. BP is not constant but tends to go up and down over time.Earlier studies have shown that when your BP fluctuates more, this can give a higher risk of dementia, stroke, cardiovascular events and even mortality. Large BP fluctuations are likely damaging for your brain, but it remains unknown if it leads to progression of brain damage over a longer period of time.This study examined if fluctuations in BP over 14 years are associated with progression of brain damage in older individuals with a mean age of 60.5 years.The results indicate that markers of brain damage progress more in participants with more variation in BP.This suggests that fluctuations in BP can cause damage in your brain to progress more.However, it is difficult to determine based on these results if BP fluctuations are a cause or a result of brain damage. More research is needed to determine what the temporal order of this association is.If variations in BP can indeed damage the brain, we need to focus not only on lowering BP, but also on keeping BP stable when considering treatments.