Sodium-based paracetamol: impact on blood pressure, cardiovascular events, and all-cause mortality.

BACKGROUND AND AIMS: Effervescent formulations of paracetamol containing sodium bicarbonate have been reported to associate with increased blood pressure and a higher risk of cardiovascular diseases and all-cause mortality. Given the major implications of these findings, the reported associations were re-examined. METHODS: Using linked electronic health records data, a cohort of 475 442 UK individuals with at least one prescription of paracetamol, aged between 60 and 90 years, was identified. Outcomes in patients taking sodium-based paracetamol were compared with those taking non-sodium-based formulations of the same. Using a deep learning approach, associations with systolic blood pressure (SBP), major cardiovascular events (myocardial infarction, heart failure, and stroke), and all-cause mortality within 1 year after baseline were investigated. RESULTS: A total of 460 980 and 14 462 patients were identified for the non-sodium-based and sodium-based paracetamol exposure groups, respectively (mean age: 74 years; 64% women). Analysis revealed no difference in SBP [mean difference -0.04 mmHg (95% confidence interval -0.51, 0.43)] and no association with major cardiovascular events [relative risk (RR) 1.03 (0.91, 1.16)]. Sodium-based paracetamol showed a positive association with all-cause mortality [RR 1.46 (1.40, 1.52)]. However, after further accounting of other sources of residual confounding, the observed association attenuated towards the null [RR 1.08 (1.01, 1.16)]. Exploratory analyses revealed dysphagia and related conditions as major sources of uncontrolled confounding by indication for this association. CONCLUSIONS: This study does not support previous suggestions of increased SBP and an elevated risk of cardiovascular events from short-term use of sodium bicarbonate paracetamol in routine clinical practice.

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.

Association between cardiometabolic disease multimorbidity and all-cause mortality in 2 million women and men registered in UK general practices.

BACKGROUND: Myocardial infarction (MI), stroke and diabetes share underlying risk factors and commonalities in clinical management. We examined if their combined impact on mortality is proportional, amplified or less than the expected risk separately of each disease and whether the excess risk is explained by their associated comorbidities. METHODS: Using large-scale electronic health records, we identified 2,007,731 eligible patients (51% women) and registered with general practices in the UK and extracted clinical information including diagnosis of myocardial infarction (MI), stroke, diabetes and 53 other long-term conditions before 2005 (study baseline). We used Cox regression to determine the risk of all-cause mortality with age as the underlying time variable and tested for excess risk due to interaction between cardiometabolic conditions. RESULTS: At baseline, the mean age was 51 years, and 7% (N = 145,910) have had a cardiometabolic condition. After a 7-year mean follow-up, 146,994 died. The sex-adjusted hazard ratios (HR) (95% confidence interval [CI]) of all-cause mortality by baseline disease status, compared to those without cardiometabolic disease, were MI = 1.51 (1.49-1.52), diabetes = 1.52 (1.51-1.53), stroke = 1.84 (1.82-1.86), MI and diabetes = 2.14 (2.11-2.17), MI and stroke = 2.35 (2.30-2.39), diabetes and stroke = 2.53 (2.50-2.57) and all three = 3.22 (3.15-3.30). Adjusting for other concurrent comorbidities attenuated these estimates, including the risk associated with having all three conditions (HR = 1.81 [95% CI 1.74-1.89]). Excess risks due to interaction between cardiometabolic conditions, particularly when all three conditions were present, were not significantly greater than expected from the individual disease effects. CONCLUSION: Myocardial infarction, stroke and diabetes were associated with excess mortality, without evidence of any amplification of risk in people with all three diseases. The presence of other comorbidities substantially contributed to the excess mortality risks associated with cardiometabolic disease multimorbidity.

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.

Learning multimorbidity patterns from electronic health records using Non-negative Matrix Factorisation.

Multimorbidity, or the presence of several medical conditions in the same individual, has been increasing in the population - both in absolute and relative terms. Nevertheless, multimorbidity remains poorly understood, and the evidence from existing research to describe its burden, determinants and consequences has been limited. Previous studies attempting to understand multimorbidity patterns are often cross-sectional and do not explicitly account for multimorbidity patterns' evolution over time; some of them are based on small datasets and/or use arbitrary and narrow age ranges; and those that employed advanced models, usually lack appropriate benchmarking and validations. In this study, we (1) introduce a novel approach for using Non-negative Matrix Factorisation (NMF) for temporal phenotyping (i.e., simultaneously mining disease clusters and their trajectories); (2) provide quantitative metrics for the evaluation of these clusters and trajectories; and (3) demonstrate how the temporal characteristics of the disease clusters that result from our model can help mine multimorbidity networks and generate new hypotheses for the emergence of various multimorbidity patterns over time. We trained and evaluated our models on one of the world's largest electronic health records (EHR) datasets, containing more than 7 million patients, from which over 2 million where relevant to, and hence included in this study.

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.

Diagnostic tests, drug prescriptions, and follow-up patterns after incident heart failure: A cohort study of 93,000 UK patients.

BACKGROUND: Effective management of heart failure is complex, and ensuring evidence-based practice presents a major challenge to health services worldwide. Over the past decade, the United Kingdom introduced a series of national initiatives to improve evidence-based heart failure management, including a landmark pay-for-performance scheme in primary care and a national audit in secondary care started in 2004 and 2007, respectively. Quality improvement efforts have been evaluated within individual clinical settings, but patterns of care across its continuum, although a critical component of chronic disease management, have not been studied. We have designed this study to investigate patients' trajectories of care around the time of diagnosis and their variation over time by age, sex, and socioeconomic status. METHODS AND FINDINGS: For this retrospective population-based study, we used linked primary and secondary health records from a representative sample of the UK population provided by the Clinical Practice Research Datalink (CPRD). We identified 93,074 individuals newly diagnosed with heart failure between 2002 and 2014, with a mean age of 76.7 years and of which 49% were women. We examined five indicators of care: (i) diagnosis care setting (inpatient or outpatient), (ii) posthospitalisation follow-up in primary care, (iii) diagnostic investigations, (iv) prescription of essential drugs, and (v) drug treatment dose. We used Poisson and linear regression models to calculate category-specific risk ratios (RRs) or adjusted differences and 95% confidence intervals (CIs), adjusting for year of diagnosis, age, sex, region, and socioeconomic status. From 2002 to 2014, indicators of care presented diverging trends. Outpatient diagnoses and follow-up after hospital discharge in primary care declined substantially (ranging from 56% in 2002 to 36% in 2014, RR 0.64 [0.62, 0.67] and 20% to 14%, RR 0.73 [0.65, 0.82], respectively). Primary care referral for diagnostic investigations and appropriate initiation of beta blockers and angiotensin-converting-enzyme inhibitors (ACE-Is) or angiotensin receptor blockers (ARBs) both increased significantly (37% versus 82%, RR 2.24 [2.15, 2.34] and 18% versus 63%, RR 3.48 [2.72, 4.43], respectively). Yet, the average daily dose prescribed remained below guideline recommendations (42% for ACE-Is or ARBs, 29% for beta blockers in 2014) and was largely unchanged beyond the first 30 days after diagnosis. Despite increasing rates of treatment initiation, the overall dose prescribed to patients in the 12 months following diagnosis improved little over the period of study (adjusted difference for the combined dose of beta blocker and ACE-I or ARB: +6% [+2%, +10%]). Women and patients aged over 75 years presented significant gaps across all five indicators of care. Our study was limited by the available clinical information, which did not include exact left ventricular ejection fraction values, investigations performed during hospital admissions, or information about follow-up in community heart failure clinics. CONCLUSIONS: Management of heart failure patients in the UK presents important shortcomings that affect screening, continuity of care, and medication titration and disproportionally impact women and older people. National reporting and incentive schemes confined to individual clinical settings have been insufficient to identify these gaps and address patients' long-term care needs.

Predicting the risk of emergency admission with machine learning: Development and validation using linked electronic health records.

BACKGROUND: Emergency admissions are a major source of healthcare spending. We aimed to derive, validate, and compare conventional and machine learning models for prediction of the first emergency admission. Machine learning methods are capable of capturing complex interactions that are likely to be present when predicting less specific outcomes, such as this one. METHODS AND FINDINGS: We used longitudinal data from linked electronic health records of 4.6 million patients aged 18-100 years from 389 practices across England between 1985 to 2015. The population was divided into a derivation cohort (80%, 3.75 million patients from 300 general practices) and a validation cohort (20%, 0.88 million patients from 89 general practices) from geographically distinct regions with different risk levels. We first replicated a previously reported Cox proportional hazards (CPH) model for prediction of the risk of the first emergency admission up to 24 months after baseline. This reference model was then compared with 2 machine learning models, random forest (RF) and gradient boosting classifier (GBC). The initial set of predictors for all models included 43 variables, including patient demographics, lifestyle factors, laboratory tests, currently prescribed medications, selected morbidities, and previous emergency admissions. We then added 13 more variables (marital status, prior general practice visits, and 11 additional morbidities), and also enriched all variables by incorporating temporal information whenever possible (e.g., time since first diagnosis). We also varied the prediction windows to 12, 36, 48, and 60 months after baseline and compared model performances. For internal validation, we used 5-fold cross-validation. When the initial set of variables was used, GBC outperformed RF and CPH, with an area under the receiver operating characteristic curve (AUC) of 0.779 (95% CI 0.777, 0.781), compared to 0.752 (95% CI 0.751, 0.753) and 0.740 (95% CI 0.739, 0.741), respectively. In external validation, we observed an AUC of 0.796, 0.736, and 0.736 for GBC, RF, and CPH, respectively. The addition of temporal information improved AUC across all models. In internal validation, the AUC rose to 0.848 (95% CI 0.847, 0.849), 0.825 (95% CI 0.824, 0.826), and 0.805 (95% CI 0.804, 0.806) for GBC, RF, and CPH, respectively, while the AUC in external validation rose to 0.826, 0.810, and 0.788, respectively. This enhancement also resulted in robust predictions for longer time horizons, with AUC values remaining at similar levels across all models. Overall, compared to the baseline reference CPH model, the final GBC model showed a 10.8% higher AUC (0.848 compared to 0.740) for prediction of risk of emergency admission within 24 months. GBC also showed the best calibration throughout the risk spectrum. Despite the wide range of variables included in models, our study was still limited by the number of variables included; inclusion of more variables could have further improved model performances. CONCLUSIONS: The use of machine learning and addition of temporal information led to substantially improved discrimination and calibration for predicting the risk of emergency admission. Model performance remained stable across a range of prediction time windows and when externally validated. These findings support the potential of incorporating machine learning models into electronic health records to inform care and service planning.

Blood Pressure and Risk of Vascular Dementia: Evidence From a Primary Care Registry and a Cohort Study of Transient Ischemic Attack and Stroke.

BACKGROUND AND PURPOSE: Vascular dementia is the second most common form of dementia but reliable evidence on age-specific associations between blood pressure (BP) and risk of vascular dementia is limited and some studies have reported negative associations at older ages. METHODS: In a cohort of 4.28 million individuals, free of known vascular disease and dementia and identified from linked electronic primary care health records in the United Kingdom (Clinical Practice Research Datalink), we related BP to time to physician-diagnosed vascular dementia. We further determined associations between BP and dementia in a prospective population-based cohort of incident transient ischemic attack and stroke (Oxford Vascular Study). RESULTS: For a median follow-up of 7.0 years, 11 114 initial presentations of vascular dementia were observed in the primary care cohort after exclusion of the first 4 years of follow-up. The association between usual systolic BP and risk of vascular dementia decreased with age (hazard ratio per 20 mm Hg higher systolic BP, 1.62; 95% confidence interval, 1.13-2.35 at 30-50 years; 1.26, 1.18-1.35 at 51-70 years; 0.97, 0.92-1.03 at 71-90 years; P trend=0.006). Usual systolic BP remained predictive of vascular dementia after accounting for effect mediation by stroke and transient ischemic attack. In the population-based cohort, prior systolic BP was predictive of 5-year risk of dementia with no evidence of negative association at older ages. CONCLUSIONS: BP is positively associated with risk of vascular dementia, irrespective of preceding transient ischemic attack or stroke. Previous reports of inverse associations in old age could not be confirmed.

Automatic denoising of functional MRI data: combining independent component analysis and hierarchical fusion of classifiers.

Many sources of fluctuation contribute to the fMRI signal, and this makes identifying the effects that are truly related to the underlying neuronal activity difficult. Independent component analysis (ICA) - one of the most widely used techniques for the exploratory analysis of fMRI data - has shown to be a powerful technique in identifying various sources of neuronally-related and artefactual fluctuation in fMRI data (both with the application of external stimuli and with the subject "at rest"). ICA decomposes fMRI data into patterns of activity (a set of spatial maps and their corresponding time series) that are statistically independent and add linearly to explain voxel-wise time series. Given the set of ICA components, if the components representing "signal" (brain activity) can be distinguished form the "noise" components (effects of motion, non-neuronal physiology, scanner artefacts and other nuisance sources), the latter can then be removed from the data, providing an effective cleanup of structured noise. Manual classification of components is labour intensive and requires expertise; hence, a fully automatic noise detection algorithm that can reliably detect various types of noise sources (in both task and resting fMRI) is desirable. In this paper, we introduce FIX ("FMRIB's ICA-based X-noiseifier"), which provides an automatic solution for denoising fMRI data via accurate classification of ICA components. For each ICA component FIX generates a large number of distinct spatial and temporal features, each describing a different aspect of the data (e.g., what proportion of temporal fluctuations are at high frequencies). The set of features is then fed into a multi-level classifier (built around several different classifiers). Once trained through the hand-classification of a sufficient number of training datasets, the classifier can then automatically classify new datasets. The noise components can then be subtracted from (or regressed out of) the original data, to provide automated cleanup. On conventional resting-state fMRI (rfMRI) single-run datasets, FIX achieved about 95% overall accuracy. On high-quality rfMRI data from the Human Connectome Project, FIX achieves over 99% classification accuracy, and as a result is being used in the default rfMRI processing pipeline for generating HCP connectomes. FIX is publicly available as a plugin for FSL.

ICA-based artefact removal and accelerated fMRI acquisition for improved resting state network imaging.

The identification of resting state networks (RSNs) and the quantification of their functional connectivity in resting-state fMRI (rfMRI) are seriously hindered by the presence of artefacts, many of which overlap spatially or spectrally with RSNs. Moreover, recent developments in fMRI acquisition yield data with higher spatial and temporal resolutions, but may increase artefacts both spatially and/or temporally. Hence the correct identification and removal of non-neural fluctuations is crucial, especially in accelerated acquisitions. In this paper we investigate the effectiveness of three data-driven cleaning procedures, compare standard against higher (spatial and temporal) resolution accelerated fMRI acquisitions, and investigate the combined effect of different acquisitions and different cleanup approaches. We applied single-subject independent component analysis (ICA), followed by automatic component classification with FMRIB's ICA-based X-noiseifier (FIX) to identify artefactual components. We then compared two first-level (within-subject) cleaning approaches for removing those artefacts and motion-related fluctuations from the data. The effectiveness of the cleaning procedures was assessed using time series (amplitude and spectra), network matrix and spatial map analyses. For time series and network analyses we also tested the effect of a second-level cleaning (informed by group-level analysis). Comparing these approaches, the preferable balance between noise removal and signal loss was achieved by regressing out of the data the full space of motion-related fluctuations and only the unique variance of the artefactual ICA components. Using similar analyses, we also investigated the effects of different cleaning approaches on data from different acquisition sequences. With the optimal cleaning procedures, functional connectivity results from accelerated data were statistically comparable or significantly better than the standard (unaccelerated) acquisition, and, crucially, with higher spatial and temporal resolution. Moreover, we were able to perform higher dimensionality ICA decompositions with the accelerated data, which is very valuable for detailed network analyses.

Study protocol: The Whitehall II imaging sub-study.

BACKGROUND: The Whitehall II (WHII) study of British civil servants provides a unique source of longitudinal data to investigate key factors hypothesized to affect brain health and cognitive ageing. This paper introduces the multi-modal magnetic resonance imaging (MRI) protocol and cognitive assessment designed to investigate brain health in a random sample of 800 members of the WHII study. METHODS/DESIGN: A total of 6035 civil servants participated in the WHII Phase 11 clinical examination in 2012-2013. A random sample of these participants was included in a sub-study comprising an MRI brain scan, a detailed clinical and cognitive assessment, and collection of blood and buccal mucosal samples for the characterisation of immune function and associated measures. Data collection for this sub-study started in 2012 and will be completed by 2016. The participants, for whom social and health records have been collected since 1985, were between 60-85 years of age at the time the MRI study started. Here, we describe the pre-specified clinical and cognitive assessment protocols, the state-of-the-art MRI sequences and latest pipelines for analyses of this sub-study. DISCUSSION: The integration of cutting-edge MRI techniques, clinical and cognitive tests in combination with retrospective data on social, behavioural and biological variables during the preceding 25 years from a well-established longitudinal epidemiological study (WHII cohort) will provide a unique opportunity to examine brain structure and function in relation to age-related diseases and the modifiable and non-modifiable factors affecting resilience against and vulnerability to adverse brain changes.

Resting-state fMRI in the Human Connectome Project.

Resting-state functional magnetic resonance imaging (rfMRI) allows one to study functional connectivity in the brain by acquiring fMRI data while subjects lie inactive in the MRI scanner, and taking advantage of the fact that functionally related brain regions spontaneously co-activate. rfMRI is one of the two primary data modalities being acquired for the Human Connectome Project (the other being diffusion MRI). A key objective is to generate a detailed in vivo mapping of functional connectivity in a large cohort of healthy adults (over 1000 subjects), and to make these datasets freely available for use by the neuroimaging community. In each subject we acquire a total of 1h of whole-brain rfMRI data at 3 T, with a spatial resolution of 2×2×2 mm and a temporal resolution of 0.7s, capitalizing on recent developments in slice-accelerated echo-planar imaging. We will also scan a subset of the cohort at higher field strength and resolution. In this paper we outline the work behind, and rationale for, decisions taken regarding the rfMRI data acquisition protocol and pre-processing pipelines, and present some initial results showing data quality and example functional connectivity analyses.

Systolic blood pressure, chronic obstructive pulmonary disease and cardiovascular risk.

OBJECTIVE: In individuals with complex underlying health problems, the association between systolic blood pressure (SBP) and cardiovascular disease is less well recognised. The association between SBP and risk of cardiovascular events in patients with chronic obstructive pulmonary disease (COPD) was investigated. METHODS AND ANALYSIS: In this cohort study, 39 602 individuals with a diagnosis of COPD aged 55-90 years between 1990 and 2009 were identified from validated electronic health records (EHR) in the UK. The association between SBP and risk of cardiovascular end points (composite of ischaemic heart disease, heart failure, stroke and cardiovascular death) was analysed using a deep learning approach. RESULTS: In the selected cohort (46.5% women, median age 69 years), 10 987 cardiovascular events were observed over a median follow-up period of 3.9 years. The association between SBP and risk of cardiovascular end points was found to be monotonic; the lowest SBP exposure group of <120 mm Hg presented nadir of risk. With respect to reference SBP (between 120 and 129 mm Hg), adjusted risk ratios for the primary outcome were 0.99 (95% CI 0.93 to 1.05) for SBP of <120 mm Hg, 1.02 (0.97 to 1.07) for SBP between 130 and 139 mm Hg, 1.07 (1.01 to 1.12) for SBP between 140 and 149 mm Hg, 1.11 (1.05 to 1.17) for SBP between 150 and 159 mm Hg and 1.16 (1.10 to 1.22) for SBP ≥160 mm Hg. CONCLUSION: Using deep learning for modelling EHR, we identified a monotonic association between SBP and risk of cardiovascular events in patients with COPD.

Stratification of diabetes in the context of comorbidities, using representation learning and topological data analysis.

Diabetes is a heterogenous, multimorbid disorder with a large variation in manifestations, trajectories, and outcomes. The aim of this study is to validate a novel machine learning method for the phenotyping of diabetes in the context of comorbidities. Data from 9967 multimorbid patients with a new diagnosis of diabetes were extracted from Clinical Practice Research Datalink. First, using BEHRT (a transformer-based deep learning architecture), the embeddings corresponding to diabetes were learned. Next, topological data analysis (TDA) was carried out to test how different areas in high-dimensional manifold correspond to different risk profiles. The following endpoints were considered when profiling risk trajectories: major adverse cardiovascular events (MACE), coronary artery disease (CAD), stroke (CVA), heart failure (HF), renal failure (RF), diabetic neuropathy, peripheral arterial disease, reduced visual acuity and all-cause mortality. Kaplan Meier curves were plotted for each derived phenotype. Finally, we tested the performance of an established risk prediction model (QRISK) by adding TDA-derived features. We identified four subgroups of patients with diabetes and divergent comorbidity patterns differing in their risk of future cardiovascular, renal, and other microvascular outcomes. Phenotype 1 (young with chronic inflammatory conditions) and phenotype 2 (young with CAD) included relatively younger patients with diabetes compared to phenotypes 3 (older with hypertension and renal disease) and 4 (older with previous CVA), and those subgroups had a higher frequency of pre-existing cardio-renal diseases. Within ten years of follow-up, 2592 patients (26%) experienced MACE, 2515 patients (25%) died, and 2020 patients (20%) suffered RF. QRISK3 model's AUC was augmented from 67.26% (CI 67.25-67.28%) to 67.67% (CI 67.66-67.69%) by adding specific TDA-derived phenotype and the distances to both extremities of the TDA graph improving its performance in the prediction of CV outcomes. We confirmed the importance of accounting for multimorbidity when risk stratifying heterogenous cohort of patients with new diagnosis of diabetes. Our unsupervised machine learning method improved the prediction of clinical outcomes.

Systolic Blood Pressure and Cardiovascular Risk in Patients With Diabetes: A Prospective Cohort Study.

BACKGROUND: Whether the association between systolic blood pressure (SBP) and risk of cardiovascular disease is monotonic or whether there is a nadir of optimal blood pressure remains controversial. We investigated the association between SBP and cardiovascular events in patients with diabetes across the full spectrum of SBP. METHODS: A cohort of 49 000 individuals with diabetes aged 50 to 90 years between 1990 and 2005 was identified from linked electronic health records in the United Kingdom. Associations between SBP and cardiovascular outcomes (ischemic heart disease, heart failure, stroke, and cardiovascular death) were analyzed using a deep learning approach. RESULTS: Over a median follow-up of 7.3 years, 16 378 cardiovascular events were observed. The relationship between SBP and cardiovascular events followed a monotonic pattern, with the group with the lowest baseline SBP of <120 mm Hg exhibiting the lowest risk of cardiovascular events. In comparison to the reference group with the lowest SBP (<120 mm Hg), the adjusted risk ratio for cardiovascular disease was 1.03 (95% CI, 0.97-1.10) for SBP between 120 and 129 mm Hg, 1.05 (0.99-1.11) for SBP between 130 and 139 mm Hg, 1.08 (1.01-1.15) for SBP between 140 and 149 mm Hg, 1.12 (1.03-1.20) for SBP between 150 and 159 mm Hg, and 1.19 (1.09-1.28) for SBP ≥160 mm Hg. CONCLUSIONS: Using deep learning modeling, we found a monotonic relationship between SBP and risk of cardiovascular outcomes in patients with diabetes, without evidence of a J-shaped relationship.

Hi-BEHRT: Hierarchical Transformer-Based Model for Accurate Prediction of Clinical Events Using Multimodal Longitudinal Electronic Health Records.

Electronic health records (EHR) represent a holistic overview of patients' trajectories. Their increasing availability has fueled new hopes to leverage them and develop accurate risk prediction models for a wide range of diseases. Given the complex interrelationships of medical records and patient outcomes, deep learning models have shown clear merits in achieving this goal. However, a key limitation of current study remains their capacity in processing long sequences, and long sequence modelling and its application in the context of healthcare and EHR remains unexplored. Capturing the whole history of medical encounters is expected to lead to more accurate predictions, but the inclusion of records collected for decades and from multiple resources can inevitably exceed the receptive field of the most existing deep learning architectures. This can result in missing crucial, long-term dependencies. To address this gap, we present Hi-BEHRT, a hierarchical Transformer-based model that can significantly expand the receptive field of Transformers and extract associations from much longer sequences. Using a multimodal large-scale linked longitudinal EHR, the Hi-BEHRT exceeds the state-of-the-art deep learning models 1% to 5% for area under the receiver operating characteristic (AUROC) curve and 1% to 8% for area under the precision recall (AUPRC) curve on average, and 2% to 8% (AUROC) and 2% to 11% (AUPRC) for patients with long medical history for 5-year heart failure, diabetes, chronic kidney disease, and stroke risk prediction. Additionally, because pretraining for hierarchical Transformer is not well-established, we provide an effective end-to-end contrastive pre-training strategy for Hi-BEHRT using EHR, improving its transferability on predicting clinical events with relatively small training dataset.

Investigating the association of environmental exposures and all-cause mortality in the UK Biobank using sparse principal component analysis.

Multicollinearity refers to the presence of collinearity between multiple variables and renders the results of statistical inference erroneous (Type II error). This is particularly important in environmental health research where multicollinearity can hinder inference. To address this, correlated variables are often excluded from the analysis, limiting the discovery of new associations. An alternative approach to address this problem is the use of principal component analysis. This method, combines and projects a group of correlated variables onto a new orthogonal space. While this resolves the multicollinearity problem, it poses another challenge in relation to interpretability of results. Standard hypothesis testing methods can be used to evaluate the association of projected predictors, called principal components, with the outcomes of interest, however, there is no established way to trace the significance of principal components back to individual variables. To address this problem, we investigated the use of sparse principal component analysis which enforces a parsimonious projection. We hypothesise that this parsimony could facilitate the interpretability of findings. To this end, we investigated the association of 20 environmental predictors with all-cause mortality adjusting for demographic, socioeconomic, physiological, and behavioural factors. The study was conducted in a cohort of 379,690 individuals in the UK. During an average follow-up of 8.05 years (3,055,166 total person-years), 14,996 deaths were observed. We used Cox regression models to estimate the hazard ratio (HR) and 95% confidence intervals (CI). The Cox models were fitted to the standardised environmental predictors (a) without any transformation (b) transformed with PCA, and (c) transformed with SPCA. The comparison of findings underlined the potential of SPCA for conducting inference in scenarios where multicollinearity can increase the risk of Type II error. Our analysis unravelled a significant association between average noise pollution and increased risk of all-cause mortality. Specifically, those in the upper deciles of noise exposure have between 5 and 10% increased risk of all-cause mortality compared to the lowest decile.

Targeted-BEHRT: Deep Learning for Observational Causal Inference on Longitudinal Electronic Health Records.

Observational causal inference is useful for decision-making in medicine when randomized clinical trials (RCTs) are infeasible or nongeneralizable. However, traditional approaches do not always deliver unconfounded causal conclusions in practice. The rise of "doubly robust" nonparametric tools coupled with the growth of deep learning for capturing rich representations of multimodal data offers a unique opportunity to develop and test such models for causal inference on comprehensive electronic health records (EHRs). In this article, we investigate causal modeling of an RCT-established causal association: the effect of classes of antihypertensive on incident cancer risk. We develop a transformer-based model, targeted bidirectional EHR transformer (T-BEHRT) coupled with doubly robust estimation to estimate average risk ratio (RR). We compare our model to benchmark statistical and deep learning models for causal inference in multiple experiments on semi-synthetic derivations of our dataset with various types and intensities of confounding. In order to further test the reliability of our approach, we test our model on situations of limited data. We find that our model provides more accurate estimates of relative risk least sum absolute error (SAE) from ground truth compared with benchmark estimations. Finally, our model provides an estimate of class-wise antihypertensive effect on cancer risk that is consistent with results derived from RCTs.

An Explainable Transformer-Based Deep Learning Model for the Prediction of Incident Heart Failure.

Predicting the incidence of complex chronic conditions such as heart failure is challenging. Deep learning models applied to rich electronic health records may improve prediction but remain unexplainable hampering their wider use in medical practice. We aimed to develop a deep-learning framework for accurate and yet explainable prediction of 6-month incident heart failure (HF). Using 100,071 patients from longitudinal linked electronic health records across the U.K., we applied a novel Transformer-based risk model using all community and hospital diagnoses and medications contextualized within the age and calendar year for each patient's clinical encounter. Feature importance was investigated with an ablation analysis to compare model performance when alternatively removing features and by comparing the variability of temporal representations. A post-hoc perturbation technique was conducted to propagate the changes in the input to the outcome for feature contribution analyses. Our model achieved 0.93 area under the receiver operator curve and 0.69 area under the precision-recall curve on internal 5-fold cross validation and outperformed existing deep learning models. Ablation analysis indicated medication is important for predicting HF risk, calendar year is more important than chronological age, which was further reinforced by temporal variability analysis. Contribution analyses identified risk factors that are closely related to HF. Many of them were consistent with existing knowledge from clinical and epidemiological research but several new associations were revealed which had not been considered in expert-driven risk prediction models. In conclusion, the results highlight that our deep learning model, in addition high predictive performance, can inform data-driven risk factor identification.