Assessing Machine Learning for Diagnostic Classification of Hypertension Types Identified by Ambulatory Blood Pressure Monitoring
Ontology highlight
ABSTRACT:
SUBMITTER: Tran T
PROVIDER: S-EPMC11250845 | biostudies-literature | 2024 Mar
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Guidelines recommend measuring out-of-clinic blood pressure (BP) to identify masked hypertension (MHT) defined by out-of-clinic BP in the hypertensive range among individuals with clinic-measured BP not in the hypertensive range. The aim of this study was to determine the overlap between ambulatory BP monitoring (ABPM) and home BP monitoring (HBPM) for the detection of MHT. We analyzed data from 333 community-dwelling adults not taking antihypertensive medication with clinic BP <140/90 mm Hg in the IDH study (Improving the Detection of Hypertension). Any MHT was defined by the presence of daytime MHT (mean daytime BP ≥135/85 mm Hg), 24-hour MHT (mean 24-hour BP ≥130/80 mm Hg), or nighttime MHT (mean nighttime BP ≥120/70 mm Hg). Home MHT was defined as mean BP ≥135/85 mm Hg on HBPM. The prevalence of MHT was 25.8% for any MHT and 11.1% for home MHT. Among participants with MHT on either ABPM or HBPM, 29.5% had MHT on both ABPM and HBPM; 61.1% had MHT only on ABPM; and 9.4% of participants had MHT only on HBPM. After multivariable adjustment and compared with participants without MHT on ABPM and HBPM, those with MHT on both ABPM and HBPM and only on ABPM had a higher left ventricular mass index (mean difference [SE], 12.7 [2.9] g/m2, P<0.001; and 4.9 [2.1] g/m2, P=0.022, respectively), whereas participants with MHT only on HBPM did not have an increased left ventricular mass index (mean difference [SE], -1.9 [4.8] g/m2, P=0.693). These data suggest that conducting ABPM will detect many individuals with MHT who have an increased cardiovascular disease risk.
| S-EPMC6207212 | biostudies-literature
Project description:This review portrays how ambulatory blood pressure (BP) monitoring was established and recommended as the method of choice for the assessment of BP and for the rational use of antihypertensive drugs. To establish much-needed diagnostic ambulatory BP thresholds, initial statistical approaches evolved into longitudinal studies of patients and populations, which demonstrated that cardiovascular complications are more closely associated with 24-hour and nighttime BP than with office BP. Studies cross-classifying individuals based on ambulatory and office BP thresholds identified white-coat hypertension, an elevated office BP in the presence of ambulatory normotension as a low-risk condition, whereas its counterpart, masked hypertension, carries a hazard almost as high as ambulatory combined with office hypertension. What clinically matters most is the level of the 24-hour and the nighttime BP, while other BP indexes derived from 24-hour ambulatory BP recordings, on top of the 24-hour and nighttime BP level, add little to risk stratification or hypertension management. Ambulatory BP monitoring is cost-effective. Ambulatory and home BP monitoring are complimentary approaches. Their interchangeability provides great versatility in the clinical implementation of out-of-office BP measurement. We are still waiting for evidence from randomized clinical trials to prove that out-of-office BP monitoring is superior to office BP in adjusting antihypertensive drug treatment and in the prevention of cardiovascular complications. A starting research line, the development of a standardized validation protocol for wearable BP monitoring devices, might facilitate the clinical applicability of ambulatory BP monitoring.
| S-EPMC7803442 | biostudies-literature
Project description: Not available
| S-EPMC1767663 | biostudies-literature
Project description:AbstractAmbulatory blood pressure monitoring (ABPM) has become indispensable in the current management of hypertension. ABPM is particularly useful in the accurate diagnosis of hypertension. Its diagnostic thresholds had been recently established based on hard clinical outcomes. Cross-classification of patients according to office and ambulatory blood pressure identifies white-coat, masked, and sustained hypertension. ABPM is also useful in cardiovascular (CV) risk assessment. It provides information on daytime and nighttime blood pressure and circadian rhythm, particularly nighttime blood pressure dipping. Nighttime blood pressure is predictive of CV risk independent of office and daytime blood pressure. Isolated nocturnal hypertension is a special form of masked hypertension, with normal daytime but elevated nocturnal blood pressure. It also helps in the evaluation of blood pressure fluctuation and variation, such as morning blood pressure surge and reading-to-reading blood pressure variability. ABPM may derive several other indexes, such as ambulatory blood pressure index and salt sensitivity index, which may be useful in CV evaluations.
| S-EPMC9276356 | biostudies-literature
Project description:Blood pressure (BP) measurements obtained during a twenty-four-hour ambulatory blood pressure monitoring (24 h ABPM) have not been reliably applied to extract arterial hemodynamics. We aimed to describe the hemodynamic profiles of different hypertension (HT) subtypes derived from a new method for total arterial compliance (Ct) estimation in a large group of individuals undergoing 24 h ABPM. A cross-sectional study was conducted, which included patients with suspected HT. Cardiac output, Ct, and total peripheral resistance (TPR) were derived through a two-element Windkessel model without having a pressure waveform. Arterial hemodynamics were analyzed according to HT subtypes in 7434 individuals (5523 untreated HT and 1950 normotensive controls [N]). The individuals mean age was 46.2 ± 13.0 years; 54.8% were male, and 22.1% were obese. In isolated diastolic hypertension (IDH), the cardiac index (CI) was greater than that in normotensive (N) controls (CI: IDH vs. N mean difference 0.10 L/m/m2; CI 95% 0.08 to 0.12; p value <0.001), with no significant clinical difference in Ct. Isolated systolic hypertension (ISH) and divergent systolic-diastolic hypertension (D-SDH) had lower Ct values than nondivergent HT subtype (Ct: divergent vs. nondivergent mean difference -0.20 mL/mmHg; CI 95% -0.21 to -0.19 mL/mmHg; p value <0.001). Additionally, D-SDH displayed the highest TPR (TPR: D-SDH vs. N mean difference 169.8 dyn*s/cm-5; CI 95% 149.3 to 190.3 dyn*s/cm-5; p value <0.001). A new method is provided for the simultaneous assessment of arterial hemodynamics with 24 h ABPM as a single diagnostic tool, which allows a comprehensive assessment of arterial function for hypertension subtypes. Main hemodynamic findings in arterial HT subtypes with regard to Ct and TPR. The 24 h ABPM profile reflects the state of Ct and TPR. Younger individuals with IDH present with a normal Ct and frequently increased CO. Patients with ND-SDH maintain an adequate Ct with a higher TPR, while subjects with D-SDH present with a reduced Ct, high PP and high TPR. Finally, the ISH subtype occurs in older individuals with significantly reduced Ct, high PP and a variable TPR proportional to the degree of arterial stiffness and MAP values. There was an observed increase in PP with age in relation to the changes in Ct (see also text). SBP: systolic blood pressure; DBP: diastolic blood pressure; MAP: mean arterial pressure; PP: pulse pressure; N: normotension; HT: hypertension; IDH: isolated diastolic hypertension; ND-SDH: nondivergent systole-diastolic hypertension; D-SDH: divergent systolic-diastolic hypertension; ISH: isolated systolic hypertension; Ct: total arterial compliance; TPR: total peripheral resistance; CO: cardiac output; 24 h ABPM: 24 h ambulatory blood pressure monitoring.
| S-EPMC10239728 | biostudies-literature
Project description:Women with a history of preeclampsia (hxPE) are at a four-fold higher risk for chronic hypertension after pregnancy compared with healthy pregnancy, but 'masked' hypertension cases are missed by clinical assessment alone. Twenty-four hour ambulatory blood pressure monitoring (ABPM) is the reference-standard for confirmation of hypertension diagnoses or detection of masked hypertension outside of clinical settings, whereas home blood pressure monitoring (HBPM) may represent a well-tolerated and practical alternative to ABPM in the postpartum period. The objectives of this study were to 1) assess concordance between ABPM and HBPM postpartum in women with a hxPE compared with healthy pregnancy controls and 2) evaluate HBPM in the detection of masked postpartum hypertension. Young women with a hxPE (N = 26) and controls (N = 36) underwent in-office, 24-h ABPM and 7-day HBPM 1-4 years postpartum. Chronic hypertension was more prevalent among women with a hxPE by all three blood pressure measures, but the prevalence of masked postpartum hypertension did not differ (36% vs 37%, P = 0.97). HBPM showed excellent agreement with ABPM (systolic: r = 0.78, intraclass coefficient [ICC] = 0.83; diastolic: r = 0.82, ICC = 0.88) and moderate concordance in classification of hypertension (κ = 0.54, P < 0.001). HBPM identified 21% of masked postpartum hypertension cases without false-positive cases, and HBPM measures among those with normotensive in-office readings could detect ABPM-defined masked hypertension (area under the curve [AUC] = 0.88 ± 0.06, P < 0.0001). The findings of the present study indicate that HBPM may be a useful screening modality prior or complementary to ABPM in the detection and management of postpartum hypertension.
| S-EPMC9645805 | biostudies-literature
Project description:The cumulative evidence in the past three decades situates ambulatory blood pressure monitoring (ABPM) as a central element in diagnosing and predicting the prognosis of subjects with hypertension. However, for various reasons, this diagnostic and prognostic importance has not been translated in equal measure into making decisions or guiding antihypertensive treatment. Mean 24-h, daytime, and night-time blood pressure estimates, the occurrence of divergent phenotypes between clinic measurements, and ABPM, as well as the main elements that determine blood pressure variability over 24 h, especially night-time dipping, are all elements that in addition to providing evidence for patient prognosis, can be used to guide antihypertensive treatment follow-up enabling greater precision in defining the effect of the drugs. In recent years, specific indices have been developed using 24-h monitoring, evaluate the duration of treatment action, the homogeneity of the effect over the monitoring period, and its possible effects on variability. In future controlled clinical trials on antihypertensive therapies it is necessary to evaluate the effects of those treatments on hard endpoints based on therapy guided by ABPM.
| S-EPMC6430151 | biostudies-literature
Project description:ObjectivesThe aim of this study was to evaluate the cost effectiveness of ambulatory blood pressure monitoring (ABPM) compared with home blood pressure monitoring (HBPM) and clinic blood pressure monitoring (CBPM) in diagnosing hypertension in Australia.MethodsA cohort-based Markov model was built from the Payer's perspective (Australian government) comparing lifetime costs and effectiveness of ABPM, HBPM and CBPM in people aged ≥ 35 years with suspected hypertension who have a CBPM between ≥ 140/90 mmHg and ≤ 180/110 mmHg using a sphygmomanometer and have not yet commenced antihypertensive treatment. The main outcome measures were incremental cost-effectiveness ratio (ICER) assessing cost per quality-adjusted life-year (QALY) and life-years (LYs) gained by ABPM versus HBPM and CBPM. Cost was measured in Australian dollars (A$).ResultsOver a lifetime model, ABPM had lower total costs (A$8,491) compared with HBPM (A$9,648) and CBPM (A$10,206) per person. ABPM was associated with a small but significant improvement in the quality and quantity of life for people with suspected hypertension with 12.872 QALYs and 17.449 LYs compared with 12.857 QALYs and 17.433 LYs with HBPM, and 12.850 QALYs and 17.425 LYs with CBPM. In the base-case analysis, ABPM dominated HBPM and CBPM. In scenario analyses, at 100% specificity of HBPM, ABPM no longer remained cost effective at a A$50,000/QALY threshold. However, in probabilistic sensitivity analysis, over 10,000 iterations, ABPM remained dominant.ConclusionABPM was the dominant strategy for confirming the diagnosis of hypertension among Australian adults aged ≥ 35 years old with suspected hypertension. The findings of this study are important for reimbursement decision makers to support policy change and for clinicians to make practice changes consistent with ABPM recommendations in primary care.
| S-EPMC9929017 | biostudies-literature
Project description:ObjectiveTo determine the relative accuracy of clinic measurements and home blood pressure monitoring compared with ambulatory blood pressure monitoring as a reference standard for the diagnosis of hypertension.DesignSystematic review with meta-analysis with hierarchical summary receiver operating characteristic models. Methodological quality was appraised, including evidence of validation of blood pressure measurement equipment.Data sourcesMedline (from 1966), Embase (from 1980), Cochrane Database of Systematic Reviews, DARE, Medion, ARIF, and TRIP up to May 2010. Eligibility criteria for selecting studies Eligible studies examined diagnosis of hypertension in adults of all ages using home and/or clinic blood pressure measurement compared with those made using ambulatory monitoring that clearly defined thresholds to diagnose hypertension.ResultsThe 20 eligible studies used various thresholds for the diagnosis of hypertension, and only seven studies (clinic) and three studies (home) could be directly compared with ambulatory monitoring. Compared with ambulatory monitoring thresholds of 135/85 mm Hg, clinic measurements over 140/90 mm Hg had mean sensitivity and specificity of 74.6% (95% confidence interval 60.7% to 84.8%) and 74.6% (47.9% to 90.4%), respectively, whereas home measurements over 135/85 mm Hg had mean sensitivity and specificity of 85.7% (78.0% to 91.0%) and 62.4% (48.0% to 75.0%).ConclusionsNeither clinic nor home measurement had sufficient sensitivity or specificity to be recommended as a single diagnostic test. If ambulatory monitoring is taken as the reference standard, then treatment decisions based on clinic or home blood pressure alone might result in substantial overdiagnosis. Ambulatory monitoring before the start of lifelong drug treatment might lead to more appropriate targeting of treatment, particularly around the diagnostic threshold.
| S-EPMC3122300 | biostudies-literature
Project description: Not available
| S-EPMC1127256 | biostudies-literature