Multi-morbidity and blood pressure trajectories in hypertensive patients: A multiple landmark cohort study.

BACKGROUND: Our knowledge of how to better manage elevated blood pressure (BP) in the presence of comorbidities is limited, in part due to exclusion or underrepresentation of patients with multiple chronic conditions from major clinical trials. We aimed to investigate the burden and types of comorbidities in patients with hypertension and to assess how such comorbidities and other variables affect BP levels over time. METHODS AND FINDINGS: In this multiple landmark cohort study, we used linked electronic health records from the United Kingdom Clinical Practice Research Datalink (CPRD) to compare systolic blood pressure (SBP) levels in 295,487 patients (51% women) aged 61.5 (SD = 13.1) years with first recorded diagnosis of hypertension between 2000 and 2014, by type and numbers of major comorbidities, from at least 5 years before and up to 10 years after hypertension diagnosis. Time-updated multivariable linear regression analyses showed that the presence of more comorbidities was associated with lower SBP during follow-up. In hypertensive patients without comorbidities, mean SBP at diagnosis and at 10 years were 162.3 mm Hg (95% confidence interval [CI] 162.0 to 162.6) and 140.5 mm Hg (95% CI 140.4 to 140.6), respectively; in hypertensive patients with ≥5 comorbidities, these were 157.3 mm Hg (95% CI 156.9 to 157.6) and 136.8 mm Hg (95% 136.4 to 137.3), respectively. This inverse association between numbers of comorbidities and SBP was not specific to particular types of comorbidities, although associations were stronger in those with preexisting cardiovascular disease. Retrospective analysis of recorded SBP showed that the difference in mean SBP 5 years before diagnosis between those without and with ≥5 comorbidities was -9 mm Hg (95% CI -9.7 to -8.3), suggesting that mean recorded SBP already differed according to the presence of comorbidity before baseline. Within 1 year after the diagnosis, SBP substantially declined, but subsequent SBP changes across comorbidity status were modest, with no evidence of a more rapid decline in those with more or specific types of comorbidities. We identified factors, such as prescriptions of antihypertensive drugs and frequency of healthcare visits, that can explain SBP differences according to numbers or types of comorbidities, but these factors only partly explained the recorded SBP differences. Nevertheless, some limitations have to be considered including the possibility that diagnosis of some conditions may not have been recorded, varying degrees of missing data inherent in analytical datasets extracted from routine health records, and greater measurement errors in clinical measurements taken in routine practices than those taken in well-controlled clinical study settings. CONCLUSIONS: BP levels at which patients were diagnosed with hypertension varied substantially according to the presence of comorbidities and were lowest in patients with multi-morbidity. Our findings suggest that this early selection bias of hypertension diagnosis at different BP levels was a key determinant of long-term differences in BP by comorbidity status. The lack of a more rapid decline in SBP in those with multi-morbidity provides some reassurance for BP treatment in these high-risk individuals.

Plasma lipids and risk of aortic valve stenosis: a Mendelian randomization study.

AIMS: Aortic valve stenosis is commonly considered a degenerative disorder with no recommended preventive intervention, with only valve replacement surgery or catheter intervention as treatment options. We sought to assess the causal association between exposure to lipid levels and risk of aortic stenosis. METHODS AND RESULTS: Causality of association was assessed using two-sample Mendelian randomization framework through different statistical methods. We retrieved summary estimations of 157 genetic variants that have been shown to be associated with plasma lipid levels in the Global Lipids Genetics Consortium that included 188 577 participants, mostly European ancestry, and genetic association with aortic stenosis as the main outcome from a total of 432 173 participants in the UK Biobank. Secondary negative control outcomes included aortic regurgitation and mitral regurgitation. The odds ratio for developing aortic stenosis per unit increase in lipid parameter was 1.52 [95% confidence interval (CI) 1.22-1.90; per 0.98 mmol/L] for low density lipoprotein (LDL)-cholesterol, 1.03 (95% CI 0.80-1.31; per 0.41 mmol/L) for high density lipoprotein (HDL)-cholesterol, and 1.38 (95% CI 0.92-2.07; per 1 mmol/L) for triglycerides. There was no evidence of a causal association between any of the lipid parameters and aortic or mitral regurgitation. CONCLUSION: Lifelong exposure to high LDL-cholesterol increases the risk of symptomatic aortic stenosis, suggesting that LDL-lowering treatment may be effective in its prevention.

Deep learning for electronic health records: A comparative review of multiple deep neural architectures.

Despite the recent developments in deep learning models, their applications in clinical decision-support systems have been very limited. Recent digitalisation of health records, however, has provided a great platform for the assessment of the usability of such techniques in healthcare. As a result, the field is starting to see a growing number of research papers that employ deep learning on electronic health records (EHR) for personalised prediction of risks and health trajectories. While this can be a promising trend, vast paper-to-paper variability (from data sources and models they use to the clinical questions they attempt to answer) have hampered the field's ability to simply compare and contrast such models for a given application of interest. Thus, in this paper, we aim to provide a comparative review of the key deep learning architectures that have been applied to EHR data. Furthermore, we also aim to: (1) introduce and use one of the world's largest and most complex linked primary care EHR datasets (i.e., Clinical Practice Research Datalink, or CPRD) as a new asset for training such data-hungry models; (2) provide a guideline for working with EHR data for deep learning; (3) share some of the best practices for assessing the "goodness" of deep-learning models in clinical risk prediction; (4) and propose future research ideas for making deep learning models more suitable for the EHR data. Our results highlight the difficulties of working with highly imbalanced datasets, and show that sequential deep learning architectures such as RNN may be more suitable to deal with the temporal nature of EHR.

Systolic Blood Pressure and Risk of Valvular Heart Disease: A Mendelian Randomization Study.

Importance: Modifiable risk factors for valvular heart disease remain largely unknown, which limits prevention and treatment. Objective: To assess the association between systolic blood pressure (BP) and major valvular heart disease. Design, Setting, and Participants: A UK Biobank population-based cohort of 502 602 men and women aged 40 to 96 years at baseline was evaluated through mendelian randomization using individual participant data. Inclusion criteria were valid genetic data and BP measurements. The participants were recruited between 2006 and 2010; data analysis was performed from June 2018 to January 2019. Exposures: Systolic BP was measured during clinical assessment and instruments for the genetic effect of high BP were identified from variants that were independently (linkage disequilibrium threshold of r2<0.1) associated with systolic BP with minor allele frequency greater than 0.01. A total of 130 single-nucleotide polymorphisms that have been shown to be associated with systolic BP in a genome-wide association meta-analysis involving 1 million participants of European ancestry were selected. Main Outcomes and Measures: Incident aortic stenosis, aortic regurgitation, and mitral regurgitation, individually and combined. Cases were largely based on hospital records linked to the UK Biobank with International Classification of Diseases and Health Related Problems, Tenth Revision codes. Results: Of the 502 602 individuals screened, 329 237 participants (177 741 [53.99%] women; mean [SD] age, 56.93 [7.99] years) had valid genetic data and BP measurements; of this cohort, 3570 individuals (1.08%) had a diagnosis of valvular heart disease (aortic stenosis, 1491 [0.45%]; aortic regurgitation, 634 [0.19%]; and mitral regurgitation, 1736 [0.53%]). Each genetically associated 20-mm Hg increment in systolic BP was associated with an increased risk of aortic stenosis (odds ratio [OR], 3.26; 95% CI, 1.50-7.10), aortic regurgitation (OR, 2.59; 95% CI, 0.75-8.92), and mitral regurgitation (OR, 2.19; 95% CI, 1.07-4.47), with no evidence for heterogeneity by type of valvular heart disease (P = .90). Sensitivity analyses confirmed the robustness of the association. Conclusions and Relevance: Lifetime exposure to elevated systolic BP appears to be associated with an increased risk of major valvular heart disease.

Long-Term Exposure to Elevated Systolic Blood Pressure in Predicting Incident Cardiovascular Disease: Evidence From Large-Scale Routine Electronic Health Records.

Background How measures of long-term exposure to elevated blood pressure might add to the performance of "current" blood pressure in predicting future cardiovascular disease is unclear. We compared incident cardiovascular disease risk prediction using past, current, and usual systolic blood pressure alone or in combination. Methods and Results Using data from UK primary care linked electronic health records, we applied a landmark cohort study design and identified 80 964 people, aged 50 years (derivation cohort=64 772; validation cohort=16 192), who, at study entry, had recorded blood pressure, no prior cardiovascular disease, and no previous antihypertensive or lipid-lowering prescriptions. We used systolic blood pressure recorded up to 10 years before baseline to estimate past systolic blood pressure (mean, time-weighted mean, and variability) and usual systolic blood pressure (correcting current values for past time-dependent blood pressure fluctuations) and examined their prospective relation with incident cardiovascular disease (first hospitalization for or death from coronary heart disease or stroke/transient ischemic attack). We used Cox regression to estimate hazard ratios and applied Bayesian analysis within a machine learning framework in model development and validation. Predictive performance of models was assessed using discrimination (area under the receiver operating characteristic curve) and calibration metrics. We found that elevated past, current, and usual systolic blood pressure values were separately and independently associated with increased incident cardiovascular disease risk. When used alone, the hazard ratio (95% credible interval) per 20-mm Hg increase in current systolic blood pressure was 1.22 (1.18-1.30), but associations were stronger for past systolic blood pressure (mean and time-weighted mean) and usual systolic blood pressure (hazard ratio ranging from 1.39-1.45). The area under the receiver operating characteristic curve for a model that included current systolic blood pressure, sex, smoking, deprivation, diabetes mellitus, and lipid profile was 0.747 (95% credible interval, 0.722-0.811). The addition of past systolic blood pressure mean, time-weighted mean, or variability to this model increased the area under the receiver operating characteristic curve (95% credible interval) to 0.750 (0.727-0.811), 0.750 (0.726-0.811), and 0.748 (0.723-0.811), respectively, with all models showing good calibration. Similar small improvements in area under the receiver operating characteristic curve were observed when testing models on the validation cohort, in sex-stratified analyses, or by using different landmark ages (40 or 60 years). Conclusions Using multiple blood pressure recordings from patients' electronic health records showed stronger associations with incident cardiovascular disease than a single blood pressure measurement, but their addition to multivariate risk prediction models had negligible effects on model performance.