Search results
Found 12943 matches for
Identification of heart failure subtypes using transformer-based deep learning modelling: a population-based study of 379,108 individuals.
BACKGROUND: Heart failure (HF) is a complex syndrome with varied presentations and progression patterns. Traditional classification systems based on left ventricular ejection fraction (LVEF) have limitations in capturing the heterogeneity of HF. We aimed to explore the application of deep learning, specifically a Transformer-based approach, to analyse electronic health records (EHR) for a refined subtyping of patients with HF. METHODS: We utilised linked EHR from primary and secondary care, sourced from the Clinical Practice Research Datalink (CPRD) Aurum, which encompassed health data of over 30 million individuals in the UK. Individuals aged 35 and above with incident reports of HF between January 1, 2005, and January 1, 2018, were included. We proposed a Transformer-based approach to cluster patients based on all clinical diagnoses, procedures, and medication records in EHR. Statistical machine learning (ML) methods were used for comparative benchmarking. The models were trained on a derivation cohort and assessed for their ability to delineate distinct clusters and prognostic value by comparing one-year all-cause mortality and HF hospitalisation rates among the identified subgroups in a separate validation cohort. Association analyses were conducted to elucidate the clinical characteristics of the derived clusters. FINDINGS: A total of 379,108 patients were included in the HF subtyping analysis. The Transformer-based approach outperformed alternative methods, delineating more distinct and prognostically valuable clusters. This approach identified seven unique HF patient clusters characterised by differing patterns of mortality, hospitalisation, and comorbidities. These clusters were labelled based on the dominant clinical features present at the initial diagnosis of HF: early-onset, hypertension, ischaemic heart disease, metabolic problems, chronic obstructive pulmonary disease (COPD), thyroid dysfunction, and late-onset clusters. The Transformer-based subtyping approach successfully captured the multifaceted nature of HF. INTERPRETATION: This study identified seven distinct subtypes, including COPD-related and thyroid dysfunction-related subgroups, which are two high-risk subgroups not recognised in previous subtyping analyses. These insights lay the groundwork for further investigations into tailored and effective management strategies for HF. FUNDING: British Heart Foundation, European Union - Horizon Europe, and Novo Nordisk Research Centre Oxford.
Measuring progress and projecting attainment on the basis of past trends of the health-related Sustainable Development Goals in 188 countries: an analysis from the Global Burden of Disease Study 2016.
BACKGROUND: The UN's Sustainable Development Goals (SDGs) are grounded in the global ambition of "leaving no one behind". Understanding today's gains and gaps for the health-related SDGs is essential for decision makers as they aim to improve the health of populations. As part of the Global Burden of Diseases, Injuries, and Risk Factors Study 2016 (GBD 2016), we measured 37 of the 50 health-related SDG indicators over the period 1990-2016 for 188 countries, and then on the basis of these past trends, we projected indicators to 2030. METHODS: We used standardised GBD 2016 methods to measure 37 health-related indicators from 1990 to 2016, an increase of four indicators since GBD 2015. We substantially revised the universal health coverage (UHC) measure, which focuses on coverage of essential health services, to also represent personal health-care access and quality for several non-communicable diseases. We transformed each indicator on a scale of 0-100, with 0 as the 2·5th percentile estimated between 1990 and 2030, and 100 as the 97·5th percentile during that time. An index representing all 37 health-related SDG indicators was constructed by taking the geometric mean of scaled indicators by target. On the basis of past trends, we produced projections of indicator values, using a weighted average of the indicator and country-specific annualised rates of change from 1990 to 2016 with weights for each annual rate of change based on out-of-sample validity. 24 of the currently measured health-related SDG indicators have defined SDG targets, against which we assessed attainment. FINDINGS: Globally, the median health-related SDG index was 56·7 (IQR 31·9-66·8) in 2016 and country-level performance markedly varied, with Singapore (86·8, 95% uncertainty interval 84·6-88·9), Iceland (86·0, 84·1-87·6), and Sweden (85·6, 81·8-87·8) having the highest levels in 2016 and Afghanistan (10·9, 9·6-11·9), the Central African Republic (11·0, 8·8-13·8), and Somalia (11·3, 9·5-13·1) recording the lowest. Between 2000 and 2016, notable improvements in the UHC index were achieved by several countries, including Cambodia, Rwanda, Equatorial Guinea, Laos, Turkey, and China; however, a number of countries, such as Lesotho and the Central African Republic, but also high-income countries, such as the USA, showed minimal gains. Based on projections of past trends, the median number of SDG targets attained in 2030 was five (IQR 2-8) of the 24 defined targets currently measured. Globally, projected target attainment considerably varied by SDG indicator, ranging from more than 60% of countries projected to reach targets for under-5 mortality, neonatal mortality, maternal mortality ratio, and malaria, to less than 5% of countries projected to achieve targets linked to 11 indicator targets, including those for childhood overweight, tuberculosis, and road injury mortality. For several of the health-related SDGs, meeting defined targets hinges upon substantially faster progress than what most countries have achieved in the past. INTERPRETATION: GBD 2016 provides an updated and expanded evidence base on where the world currently stands in terms of the health-related SDGs. Our improved measure of UHC offers a basis to monitor the expansion of health services necessary to meet the SDGs. Based on past rates of progress, many places are facing challenges in meeting defined health-related SDG targets, particularly among countries that are the worst off. In view of the early stages of SDG implementation, however, opportunity remains to take actions to accelerate progress, as shown by the catalytic effects of adopting the Millennium Development Goals after 2000. With the SDGs' broader, bolder development agenda, multisectoral commitments and investments are vital to make the health-related SDGs within reach of all populations. FUNDING: Bill & Melinda Gates Foundation.
Association between sleep duration and hypertension incidence: Systematic review and meta-analysis of cohort studies.
AIM: Sleep duration has been suggested to be associated with hypertension (HTN). However, evidence of the nature of the relationship and its direction has been inconsistent. Therefore, we performed a meta-analysis to assess the relationship between sleep duration and risk of HTN incidence, and to distinguish more susceptible populations. METHODS: PubMed, Embase, Scopus, Web of Science, and ProQuest were searched from January 2000 to May 2023 for cohort studies comparing short and long sleep durations with 7-8 hours of sleep for the risk of HTN incidence. Random-effect model (the DerSimonian-Laird method) was applied to pool risk ratios (RR) and 95% confidence interval (CI). RESULTS: We included sixteen studies ranging from 2.4 to 18 years of follow-up duration evaluating HTN incidence in 1,044,035 people. Short sleep duration was significantly associated with a higher risk of developing HTN (HR: 1.07, 95% CI: 1.06-1.09). The association was stronger when the sleep duration was less than 5 hours (HR: 1.11, 95% CI: 1.08-1.14). In contrast to males, females (HR: 1.07, 95% CI: 1.04-1.09) were more vulnerable to developing HTN due to short sleep duration. No significant difference between different follow-up durations and age subgroups was observed. Long sleep duration was not associated with an increased incidence of HTN. CONCLUSION: Short sleep duration was associated with higher risk of HTN incidence, however, there was no association between long sleep duration and incidence of HTN. These findings highlight the importance of implementing target-specific preventive and interventional strategies for vulnerable populations with short sleep duration to reduce the risk of HTN.
Global Challenges After a Global Challenge: Lessons Learned from the COVID-19 Pandemic.
Coronavirus disease 2019 (COVID-19) has affected not only individual lives but also the world and global systems, both natural and human-made. Besides millions of deaths and environmental challenges, the rapid spread of the infection and its very high socioeconomic impact have affected healthcare, economic status and wealth, and mental health across the globe. To better appreciate the pandemic's influence, multidisciplinary and interdisciplinary approaches are needed. In this chapter, world-leading scientists from different backgrounds share collectively their views about the pandemic's footprint and discuss challenges that face the international community.
Temporal trends in cross-country inequalities of stroke and subtypes burden from 1990 to 2021: a secondary analysis of the global burden of disease study 2021.
BACKGROUND: Stroke remains a significant global health challenge, with persistent disparities in burden across different countries and regions. This study aimed to assess the temporal trends in cross-country inequalities of stroke and its subtypes burden from 1990 to 2021. METHODS: We conducted a secondary analysis of the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2021. The age-standardised disability-adjusted life years (DALYs) rate (ASDR) was used to assess the burden of stroke and its subtypes (ischemic stroke, intracerebral haemorrhage, and subarachnoid haemorrhage) across 21 GBD regions and 204 countries. The slope index of inequality (SII) and the concentration index were calculated to quantify the absolute and relative cross-country inequalities in the burden of stroke and its subtypes, with negative values indicating a higher burden in lower socio-demographic index (SDI) countries, and positive values indicating a higher burden in higher SDI countries. Estimated annual percentage change (EAPC) was used to illustrate temporal trends at global and regional levels from 1990 to 2021. The inequality changing patterns from 1990 to 2021 were classified as worsening, improving, and shifting to higher burdens among higher or lower SDI countries. FINDINGS: From 1990 to 2021, the ASDR of total stroke decreased from 3078.95 (95% uncertainty interval [UI]: 2893.58, 3237.34) to 1886.20 (95% UI: 1738.99, 2017.90) per 100,000 population globally. While both absolute and relative inequalities increased, with a disproportionately higher burden shouldered by countries with lower SDI. The SII of total stroke exhibited a worsening inequality among lower SDI countries, increasing by 286.97 units from -2329.47 (95% confidence interval [CI]: -2857.50, -1801.43) in 1990 to -2616.44 (95% CI: -2987.33, -2245.56) in 2021. Similarly, the concentration index of total stroke increased by 0.03 from -0.0819 (95% CI: -0.1143, -0.0495) in 1990 to -0.1119 (95% CI: -0.1478, -0.0759) in 2021. The changing patterns from 1990 to 2021 were diverse across regions, yet most regions exhibited a worsening inequality among lower SDI countries in both SII and concentration index. Southern Sub-Saharan Africa showed the largest worsening inequality in SII (EAPC: -2.15, 95% CI: -2.71, -1.57) while Central Europe showed the largest worsening inequality in concentration index (EAPC: -0.51, 95% CI: -0.58, -0.44). In 2021, the highest negative SII was observed in Oceania and the highest negative concentration index was in the Caribbean. In terms of subtypes, ischemic stroke reported a worsening inequality among lower SDI countries in SII (EAPC: -2.13, 95% CI: -2.20, -2.05) while intracerebral haemorrhage showed an improving inequality in SII (EAPC: 0.44, 95% CI: 0.40, 0.47). SII in subarachnoid haemorrhage (EAPC: -0.18, 95% CI: -0.19, -0.17) and concentration index in ischemic stroke (EAPC: -0.25, 95% CI: -0.27, -0.23) presented a shift to higher burden among lower SDI countries from 1990 to 2021. INTERPRETATION: Although the burden of stroke and its subtypes decreased from 1990 to 2021, inequalities have persisted and even widened in some regions. Timely and effective prevention and management strategies for stroke and its subtypes are needed in specific areas to reduce the stroke burden and achieve equity in health outcomes. FUNDING: None.
Cardiovascular Risk Factors in Childhood and Adulthood and Cardiovascular Disease in Middle Age.
IMPORTANCE: Recent evidence suggests that childhood levels of serum lipids, blood pressure, body mass index (BMI), and smoking contribute to adult risk of cardiovascular disease (CVD). Evidence is lacking on whether this is independent of adult risk levels. OBJECTIVE: To quantify direct and indirect effects of childhood risk factors on adult CVD via adulthood risk factors using mediation analysis, and to quantify their relative importance during different life-course stages using a life-course approach. DESIGN, SETTING, AND PARTICIPANTS: This prospective cohort study followed participants from the US, Finland, and Australia from childhood (1970s-1990s) until 2019, with data on CVD risk factors in childhood and adulthood. Longitudinal childhood and adulthood risk factors were summarized to describe BMI, lipids, and blood pressure cumulatively. Childhood and adulthood smoking were assessed with questionnaires. Data analysis was performed May 2022 to August 2023. MAIN OUTCOMES AND MEASURES: The primary outcomes were fatal and nonfatal cardiovascular events in adulthood. Mediation analysis was used to estimate the direct and indirect effects of the childhood risk factors with CVD events, reported as incidence rate ratios (RRs) and 95% CIs. RESULTS: A total of 10 634 participants (4506 male participants [42.4%]; mean [SD] age at childhood visit, 13.3 [3.0] years; mean [SD] age at adulthood visit, 32.3 [6.0] years) were included in the cohort. The mean (SD) age at CVD event or censoring was 49.2 (7.0) years. The median (IQR) follow-up time was 23.6 (18.7-30.2) years. Childhood risk factors, (low-density lipoprotein cholesterol [LDL-C], total cholesterol [TC], triglycerides, systolic blood pressure [SBP], smoking, BMI, and a combined score of these) were associated with CVD. BMI (direct effect for incidence RR per 1 SD unit, 1.18; 95% CI, 1.05-1.34) and LDL-C (direct effect incidence RR, 1.16; 95% CI, 1.01-1.34) in particular were found to play an important role via direct pathways, whereas the indirect effects were larger for TC, triglycerides, SBP, and the combined score. Childhood smoking only affected CVD via adulthood smoking. Life-course models confirmed that for the risk of CVD, childhood BMI plays nearly as important role as adulthood BMI, whereas for the other risk factors and the combined score, adulthood was the more important period. CONCLUSIONS AND RELEVANCE: In this cohort study of 10 634 participants, childhood risk factors were found to be associated both directly and indirectly to adult CVD, with the largest direct effect seen for BMI and LDL-C. These findings suggest that intervention for childhood risk factors, in particular BMI, is warranted to reduce incidence of adult CVD as it cannot be fully mitigated by risk factor management in adulthood.
Gout and incidence of 12 cardiovascular diseases: a case-control study including 152 663 individuals with gout and 709 981 matched controls.
BACKGROUND: Gout, a common crystal arthropathy, is associated with increased risk of cardiovascular disease. We aimed to identify how this risk varies by individual cardiovascular disease across a broad spectrum of conditions. METHODS: In this matched case-control study, we used linked primary and secondary electronic health records from the UK Clinical Practice Research Datalink to assemble a cohort of individuals with a first-time diagnosis of gout between Jan 1, 2000 and Dec 31, 2017, who were aged 80 years or younger at diagnosis, and free of cardiovascular diseases up to 12 months after diagnosis. The control cohort comprised up to five control individuals per patient with gout, matched on age, sex, socioeconomic status, geographical region, and calendar time, randomly selected among individuals free of gout at any time before and during the study period. The cohorts were followed up until June 30, 2019. We investigated the incidence of 12 cardiovascular diseases and used Cox proportional hazards models to examine differences in people with and without gout, overall and by subgroups of sex, age, socioeconomic status, and year of study inclusion. We further adjusted models for known cardiovascular risk factors (blood pressure, BMI, smoking status, cholesterol, type 2 diabetes, chronic kidney disease, and history of hypertension). FINDINGS: We identified 152 663 individuals with gout (mean age 56·2 years [SD 13·3]; 120 324 [78·8%] men and 32 339 [21·2%] women) and 709 981 matched controls (mean age 56·5 years [13·2]; 561 002 [79·0%] men and 148 979 [21·0%] women). Of these individuals, 31 479 (20·6%) with gout and 106 520 (15·0%) without gout developed cardiovascular disease during a median follow-up of 6·5 years (IQR 3·1-10·5). Patients with gout had higher risk of cardiovascular diseases than matched controls (hazard ratio [HR] 1·58 [95% CI 1·52-1·63]). Excess risk of cardiovascular disease in gout was greater in women than men (women: HR 1·88 [1·75-2·02]; men: HR 1·49 [1·43-1·56]), and, among all age groups, was highest in younger individuals (HR in people aged <45 years: 2·22 [1·92-2·57]). Excess risk was observed across all 12 cardiovascular diseases investigated. Patients with gout had higher BMI than matched controls (mean difference 2·90 kg/m2 [95% CI 2·87-2·93]) and higher prevalence of chronic kidney disease, dyslipidaemia, history of hypertension, obesity, and type 2 diabetes. Adjusting for known cardiovascular risk factors attenuated but did not eliminate the excess risk of cardiovascular disease related to gout (adjusted HR 1·31 [1·27-1·36]). INTERPRETATION: Patients with gout had an excess risk of developing a broad range of cardiovascular diseases that extend beyond atherosclerotic diseases and include heart failure, arrhythmias, valve disease, and thromboembolic diseases. Excess risk was highest in women and younger individuals. These findings suggest that strategies to reduce cardiovascular risk in patients with gout need to evolve and be implemented in clinical practice. FUNDING: Research Foundation Flanders.
What Is New and Different in the 2024 European Society of Cardiology Guidelines for the Management of Elevated Blood Pressure and Hypertension?
In 2024, the European Society of Cardiology released a new guideline for the management of elevated blood pressure (BP) and hypertension. The guideline introduced a new BP categorization: (1) nonelevated (office BP <120/70 mm Hg) for which drug treatment is not recommended, (2) elevated (120-139/70-89 mm Hg) for which drug treatment is recommended based on cardiovascular disease risk and follow-up BP level, and (3) hypertension (≥140/90 mm Hg) for which prompt confirmation and drug treatment are recommended in most individuals. The initial default systolic BP treatment target is 120 to 129 mm Hg; however, relaxed targets (BP as low as reasonably achievable) are recommended in case of treatment intolerance, adults ≥85 years, symptomatic orthostasis, moderate-to-severe frailty, or limited life expectancy. Here, we summarize what is new and different in the 2024 European Society of Cardiology guidelines, relative to other major international hypertension guidelines in Europe and America. Our aim is to reconcile any uncertainty clinicians may have about implementing these various guidelines in patient care.