10-Year Risk Equations for Incident Heart Failure in the General Population

Incident heart failure in chronic kidney disease: proteomics informs biology and risk stratification

BACKGROUND AND AIMS

Incident heart failure (HF) among individuals with chronic kidney disease (CKD) incurs hospitalizations that burden patients and health care systems. There are few preventative therapies, and the Pooled Cohort equations to Prevent Heart Failure (PCP-HF) perform poorly in the setting of CKD. New drug targets and better risk stratification are urgently needed.

METHODS

In this analysis of incident HF, SomaScan V4.0 (4638 proteins) was analysed in 2906 participants of the Chronic Renal Insufficiency Cohort (CRIC) with validation in the Atherosclerosis Risk in Communities (ARIC) study. The primary outcome was 14-year incident HF (390 events); secondary outcomes included 4-year HF (183 events), HF with reduced ejection fraction (137 events), and HF with preserved ejection fraction (165 events). Mendelian randomization and Gene Ontology were applied to examine causality and pathways. The performance of novel multi-protein risk models was compared to the PCP-HF risk score.

RESULTS

Over 200 proteins were associated with incident HF after adjustment for estimated glomerular filtration rate at P < 1 × 10-5. After adjustment for covariates including N-terminal pro-B-type natriuretic peptide, 17 proteins remained associated at P < 1 × 10-5. Mendelian randomization associations were found for six proteins, of which four are druggable targets: FCG2B, IGFBP3, CAH6, and ASGR1. For the primary outcome, the C-statistic (95% confidence interval [CI]) for the 48-protein model in CRIC was 0.790 (0.735, 0.844) vs. 0.703 (0.644, 0.762) for the PCP-HF model (P = .001). C-statistic (95% CI) for the protein model in ARIC was 0.747 (0.707, 0.787).

CONCLUSIONS

Large-scale proteomics reveal novel circulating protein biomarkers and potential mediators of HF in CKD. Proteomic risk models improve upon the PCP-HF risk score in this population.

Pitfalls in Developing Machine Learning Models for Predicting Cardiovascular Diseases: Challenge and Solutions

In recent years, there has been explosive development in artificial intelligence (AI), which has been widely applied in the health care field. As a typical AI technology, machine learning models have emerged with great potential in predicting cardiovascular diseases by leveraging large amounts of medical data for training and optimization, which are expected to play a crucial role in reducing the incidence and mortality rates of cardiovascular diseases. Although the field has become a research hot spot, there are still many pitfalls that researchers need to pay close attention to. These pitfalls may affect the predictive performance, credibility, reliability, and reproducibility of the studied models, ultimately reducing the value of the research and affecting the prospects for clinical application. Therefore, identifying and avoiding these pitfalls is a crucial task before implementing the research. However, there is currently a lack of a comprehensive summary on this topic. This viewpoint aims to analyze the existing problems in terms of data quality, data set characteristics, model design, and statistical methods, as well as clinical implications, and provide possible solutions to these problems, such as gathering objective data, improving training, repeating measurements, increasing sample size, preventing overfitting using statistical methods, using specific AI algorithms to address targeted issues, standardizing outcomes and evaluation criteria, and enhancing fairness and replicability, with the goal of offering reference and assistance to researchers, algorithm developers, policy makers, and clinical practitioners.

Cost Effectiveness of Endovascular Ultrasound Renal Denervation in Patients with Resistant Hypertension

BACKGROUND

Resistant hypertension (rHTN) is defined as blood pressure (BP) of ≥ 140/90 mmHg despite treatment with at least three antihypertensive medications, including a diuretic. Endovascular ultrasound renal denervation (uRDN) aims to control BP alongside conventional BP treatment with antihypertensive medication. This analysis assesses the cost effectiveness of the addition of the Paradise uRDN System compared with standard of care alone in patients with rHTN from the perspective of the United Kingdom (UK) health care system.

METHODS

Using RADIANCE-HTN TRIO trial data, we developed a state-transition model. Baseline risk was calculated using Framingham and Prospective Cardiovascular Münster (PROCAM) risk equations to estimate the long-term cardiovascular risks in patients treated with the Paradise uRDN System, based on the observed systolic BP (SBP) reduction following uRDN. Relative risks sourced from a meta-analysis of randomised controlled trials were then used to project cardiovascular events in patients with baseline SBP ('control' patients); utility and mortality inputs and costs were derived from UK data. Costs and outcomes were discounted at 3.5% per annum. Modelled outcomes were validated against trial meta-analyses and the QRISK3 algorithm and real-world evidence of RDN effectiveness. One-way and probabilistic sensitivity analyses were conducted to assess the uncertainty surrounding the model inputs and sensitivity of the model results to changes in parameter inputs. Results were reported as incremental cost-effectiveness ratios (ICERs).

RESULTS

A mean reduction in office SBP of 8.5 mmHg with uRDN resulted in an average improvement in both absolute life-years (LYs) and quality-adjusted life-years (QALYs) gained compared with standard of care alone (0.73 LYs and 0.67 QALYs). The overall base-case ICER with uRDN was estimated at £5600 (€6500) per QALY gained (95% confidence interval £5463-£5739 [€6341-€6661]); modelling demonstrated > 99% probability that the ICER is below the £20,000-£30,000 (€23,214-€34,821) per QALYs gained willingness-to-pay threshold in the UK. Results were consistent across sensitivity analyses and validation checks.

CONCLUSIONS

Endovascular ultrasound RDN with the Paradise system offers patients with rHTN, clinicians, and healthcare systems a cost-effective treatment option alongside antihypertensive medication.

Ten-Year Risk Equations for Incident Heart Failure in Established Atherosclerotic Cardiovascular Disease Populations

BACKGROUND

Ten-year risk equations for incident heart failure (HF) are available for the general population, but not for patients with established atherosclerotic cardiovascular disease (ASCVD), which is highly prevalent in HF cohorts. This study aimed to develop and validate 10-year risk equations for incident HF in patients with known ASCVD.

METHODS AND RESULTS

Ten-year risk equations for incident HF were developed using the United Kingdom Biobank cohort (recruitment 2006-2010) including participants with established ASCVD but free from HF at baseline. Model performance was validated using the Australian Baker Heart and Diabetes Institute Biobank cohort (recruitment 2000-2011) and compared with the performance of general population risk models. Incident HF occurred in 13.7% of the development cohort (n=31 446, median 63 years, 35% women, follow-up 10.7±2.7 years) and in 21.3% of the validation cohort (n=1659, median age 65 years, 25% women, follow-up 9.4±3.7 years). Predictors of HF included in the sex-specific models were age, body mass index, systolic blood pressure (treated or untreated), glucose (treated or untreated), cholesterol, smoking status, QRS duration, kidney disease, myocardial infarction, and atrial fibrillation. ASCVD-HF equations had good discrimination and calibration in development and validation cohorts, with superior performance to general population risk equations.

CONCLUSIONS

ASCVD-specific 10-year risk equations for HF outperform general population risk models in individuals with established ASCVD. The ASCVD-HF equations can be calculated from readily available clinical data and could facilitate screening and preventative treatment decisions in this high-risk group.

Blood pressure and heart failure: focused on treatment

Heart failure (HF) remains a significant global health burden, and hypertension is known to be the primary contributor to its development. Although aggressive hypertension treatment can prevent heart changes in at-risk patients, determining the optimal blood pressure (BP) targets in cases diagnosed with HF is challenging owing to insufficient evidence. Notably, hypertension is more strongly associated with HF with preserved ejection fraction than with HF with reduced ejection fraction. Patients with acute hypertensive HF exhibit sudden symptoms of acute HF, especially those manifested with severely high BP; however, no specific vasodilator therapy has proven beneficial for this type of acute HF. Since the majority of medications used to treat HF contribute to lowering BP, and BP remains one of the most important hemodynamic markers, targeted BP management is very concerned in treatment strategies. However, no concrete guidelines exist, prompting a trend towards optimizing therapies to within tolerable ranges, rather than setting explicit BP goals. This review discusses the connection between BP and HF, explores its pathophysiology through clinical studies, and addresses its clinical significance and treatment targets.

Clustering of Cardiovascular Risk Factors and Heart Failure in Older Adults from the Brazilian Far North

Given the aging global population, identifying heart failure (HF) phenotypes has become crucial, as distinct disease characteristics can influence treatment and prognosis in older adults. This study aimed to analyze the association between clustering of cardiovascular risk factors and HF in older adults. A cross-sectional epidemiological study was conducted with 1322 older adults (55% women, mean age 70.4) seen in primary health care. Diagnosis of HF was performed by a cardiologist based on diagnostic tests and medical history. Cardiovascular risk factors included hypertension, diabetes, hypercholesterolemia, and smoking. Using logistic regression, potential associations were tested. Individual risk factor analysis showed that older adults with hypertension, diabetes, or hypercholesterolemia had up to 7.6 times higher odds to have HF. The cluster where older adults had only one risk factor instead of none increased the odds of HF by 53.0%. Additionally, the odds of older patients having HF ranged from 3.59 times for the two-risk factor cluster to 20.61 times for the simultaneous presence of all four factors. The analysis of clusters substantially increasing HF risk in older adults revealed the importance of individualizing subgroups with distinct HF pathophysiologies. The clinical significance of these clusters can be beneficial in guiding a more personalized therapeutic approach.

Prediction of incident chronic kidney disease in community-based electronic health records: a systematic review and meta-analysis

Background

Chronic kidney disease (CKD) is a major global health problem and its early identification would allow timely intervention to reduce complications. We performed a systematic review and meta-analysis of multivariable prediction models derived and/or validated in community-based electronic health records (EHRs) for the prediction of incident CKD in the community.

Methods

Ovid Medline and Ovid Embase were searched for records from 1947 to 31 January 2024. Measures of discrimination were extracted and pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using Prediction model Risk Of Bias ASsessment Tool (PROBAST) and certainty in effect estimates by Grading of Recommendations, Assessment, Development and Evaluation (GRADE).

Results

Seven studies met inclusion criteria, describing 12 prediction models, with two eligible for meta-analysis including 2 173 202 patients. The Chronic Kidney Disease Prognosis Consortium (CKD-PC) (summary c-statistic 0.847; 95% CI 0.827-0.867; 95% PI 0.780-0.905) and SCreening for Occult REnal Disease (SCORED) (summary c-statistic 0.811; 95% CI 0.691-0.926; 95% PI 0.514-0.992) models had good model discrimination performance. Risk of bias was high in 64% of models, and driven by the analysis domain. No model met eligibility for meta-analysis if studies at high risk of bias were excluded, and certainty of effect estimates was 'low'. No clinical utility analyses or clinical impact studies were found for any of the models.

Conclusions

Models derived and/or externally validated for prediction of incident CKD in community-based EHRs demonstrate good prediction performance, but assessment of clinical usefulness is limited by high risk of bias, low certainty of evidence and a lack of impact studies.

Contemporary American and European Guidelines for Heart Failure Management: JACC: Heart Failure Guideline Comparison

This review serves to compare contemporary clinical practice recommendations for the management of heart failure (HF), as codified in the 2021 European Society of Cardiology (ESC) guideline, the 2022 American College of Cardiology (ACC)/American Heart Association (AHA)/Heart Failure Society of America (HFSA) guideline, and the 2023 focused update of the 2021 ESC document. Overall, these guidelines aim to solidify significant advances throughout the HF continuum since the publication of previous full guideline iterations (2013 and 2016 for the ACC/AHA and ESC, respectively). All guidelines provide new recommendations for an increasingly complex landscape of HF care, with focus on primary HF prevention, HF stages, rapid initiation and optimization of evidence-based pharmacotherapies, overlapping cardiac and noncardiac comorbidities, device-based therapies, and management pathways for special groups of patients, including those with cardiac amyloidosis. Importantly, the ACC/AHA/HFSA document features special emphasis on HF risk prediction and screening, cost/value, social determinants of health, and health care disparities. The review discusses major similarities and differences between these recent guidelines and guideline updates, as well as their potential downstream implications for clinical care.

A polygenic risk score of atrial fibrillation improves prediction of lifetime risk for heart failure

AIMS

Heart failure (HF) has shared genetic architecture with its risk factors: atrial fibrillation (AF), body mass index (BMI), coronary heart disease (CHD), systolic blood pressure (SBP), and type 2 diabetes (T2D). We aim to assess the association and risk prediction performance of risk-factor polygenic risk scores (PRSs) for incident HF and its subtypes in bi-racial populations.

METHODS AND RESULTS

Five PRSs were constructed for AF, BMI, CHD, SBP, and T2D in White participants of the Atherosclerosis Risk in Communities (ARIC) study. The associations between PRSs and incident HF and its subtypes were assessed using Cox models, and the risk prediction performance of PRSs was assessed using C statistics. Replication was performed in the ARIC study Black and Cardiovascular Health Study (CHS) White participants. In 8624 ARIC study Whites, 1922 (31% cumulative incidence) HF cases developed over 30 years of follow-up. PRSs of AF, BMI, and CHD were associated with incident HF (P < 0.001), where PRSAF showed the strongest association [hazard ratio (HR): 1.47, 95% confidence interval (CI): 1.41-1.53]. Only the addition of PRSAF to the ARIC study HF risk equation improved C statistics for 10 year risk prediction from 0.812 to 0.829 (∆C: 0.017, 95% CI: 0.009-0.026). The PRSAF was associated with both incident HF with reduced ejection fraction (HR: 1.43, 95% CI: 1.27-1.60) and incident HF with preserved ejection fraction (HR: 1.46, 95% CI: 1.33-1.62). The associations between PRSAF and incident HF and its subtypes, as well as the improved risk prediction, were replicated in the ARIC study Blacks and the CHS Whites (P < 0.050). Protein analyses revealed that N-terminal pro-brain natriuretic peptide and other 98 proteins were associated with PRSAF.

CONCLUSIONS

The PRSAF was associated with incident HF and its subtypes and had significant incremental value over an established HF risk prediction equation.

Serum metabolomics improves risk stratification for incident heart failure

AIMS

Prediction and early detection of heart failure (HF) is crucial to mitigate its impact on quality of life, survival, and healthcare expenditure. Here, we explored the predictive value of serum metabolomics (168 metabolites detected by proton nuclear magnetic resonance [1H-NMR] spectroscopy) for incident HF.

METHODS AND RESULTS

Leveraging data of 68 311 individuals and >0.8 million person-years of follow-up from the UK Biobank cohort, we (i) fitted per-metabolite Cox proportional hazards models to assess individual metabolite associations, and (ii) trained and validated elastic net models to predict incident HF using the serum metabolome. We benchmarked discriminative performance against a comprehensive, well-validated clinical risk score (Pooled Cohort Equations to Prevent HF [PCP-HF]). During a median follow-up of ≈12.3 years, several metabolites showed independent association with incident HF (90/168 adjusting for age and sex, 48/168 adjusting for PCP-HF). Performance-optimized risk models effectively retained key predictors representing highly correlated clusters (≈80% feature reduction). Adding metabolomics to PCP-HF improved predictive performance (Harrel's C: 0.768 vs. 0.755, ΔC = 0.013, [95% confidence interval [CI] 0.004-0.022], continuous net reclassification improvement [NRI]: 0.287 [95% CI 0.200-0.367], relative integrated discrimination improvement [IDI]: 17.47% [95% CI 9.463-27.825]). Models including age, sex and metabolomics performed almost as well as PCP-HF (Harrel's C: 0.745 vs. 0.755, ΔC = 0.010 [95% CI -0.004 to 0.027], continuous NRI: 0.097 [95% CI -0.025 to 0.217], relative IDI: 13.445% [95% CI -10.608 to 41.454]). Risk and survival stratification was improved by integrating metabolomics.

CONCLUSION

Serum metabolomics improves incident HF risk prediction over PCP-HF. Scores based on age, sex and metabolomics exhibit similar predictive power to clinically-based models, potentially offering a cost-effective, standardizable, and scalable single-domain alternative.

N-Terminal Pro-Brain Type Natriuretic Peptide Predicts Cardiovascular Events Independently of Arterial Stiffness, Assessed By Carotid-to-Femoral Pulse Wave Velocity, in Apparently Healthy Subjects

AIM

This study aimed to evaluate whether N-terminal pro-brain natriuretic peptide (NT-proBNP) and carotid-to-femoral pulse wave velocity (PWV) carried independent prognostic value in predicting cardiovascular events in apparently healthy individuals beyond traditional risk factors.

METHODS

A total of 1,872 participants aged 41, 51, 61, or 71 years from the MONItoring of trends and determinants in CArdiovascular disease (MONICA) study were included. Traditional risk factors were assessed, including: smoking status; mean systolic and diastolic blood pressure; body mass index; fasting plasma glucose; serum triglycerides; total, high-density, and low-density lipoprotein cholesterol; NT-proBNP; and PWV. The principal endpoint that was assessed during 16 years of follow-up was a composite of major adverse cardiovascular events (MACE). The secondary endpoints were cardiovascular mortality (CVM), hospitalisation for coronary artery disease (CAD), and a composite of hospitalisation for heart failure (HF) or atrial fibrillation (AF).

RESULTS

At baseline, NT-proBNP was associated with PWV (β=0.14; p<0.001), but not after adjustment for traditional risk factors (β=-0.01; p=0.67). In models including traditional risk factors and PWV, NT-proBNP was associated with all four outcomes (HRMACE=1.33, 95% CI 1.16-1.52; HRCVM=2.02, 95% CI 1.65-2.48; HRCAD=1.29, 95% CI 1.07-1.55; and HRHF or AF=1.79, 95% CI 1.40-2.28). In the same model, PWV was only associated with CVM (HRCVM=1.20, 95% CI 1.01-1.41). No interactions between NT-proBNP and PWV were found. N-terminal pro-brain natriuretic peptide significantly improved net reclassification (NRI) for MACE (NRI=0.12; p=0.03), CVM (NRI=0.33; p<0.001), and HF or AF (NRI=0.33; p<0.001) beyond traditional risk factors, while PWV did not aid in net reclassification improvement for any endpoint.

CONCLUSIONS

In apparently healthy individuals, NT-proBNP and PWV predicted cardiovascular events independently. N-terminal pro-brain natriuretic peptide improved reclassification for the prediction of MACE, CVM, and hospitalisation for HF or AF beyond traditional risk factors, while PWV did not.

Metabolomic Association and Risk Prediction With Heart Failure in Older Adults

BACKGROUND

Older adults have markedly increased risks of heart failure (HF), specifically HF with preserved ejection fraction (HFpEF). Identifying novel biomarkers can help in understanding HF pathogenesis and improve at-risk population identification. This study aimed to identify metabolites associated with incident HF, HFpEF, and HF with reduced ejection fraction and examine risk prediction in older adults.

METHODS

Untargeted metabolomic profiling was performed in Black and White adults from the ARIC study (Atherosclerosis Risk in Communities) visit 5 (n=3719; mean age, 75 years). We applied Cox regressions to identify metabolites associated with incident HF and its subtypes. The metabolite risk score (MRS) was constructed and examined for associations with HF, echocardiographic measures, and HF risk prediction. Independent samples from visit 3 (n=1929; mean age, 58 years) were used for replication.

RESULTS

Sixty metabolites (hazard ratios range, 0.79-1.49; false discovery rate, <0.05) were associated with incident HF after adjusting for clinical risk factors, eGFR, and NT-proBNP (N-terminal pro-B-type natriuretic peptide). Mannonate, a hydroxy acid, was replicated (hazard ratio, 1.36 [95% CI, 1.19-1.56]) with full adjustments. MRS was associated with an 80% increased risk of HF per SD increment, and the highest MRS quartile had 8.7× the risk of developing HFpEF than the lowest quartile. High MRS was also associated with unfavorable values of cardiac structure and function. Adding MRS over clinical risk factors and NT-proBNP improved 5-year HF risk prediction C statistics from 0.817 to 0.850 (∆C, 0.033 [95% CI, 0.017-0.047]). The association between MRS and incident HF was replicated after accounting for clinical risk factors (P<0.05).

CONCLUSIONS

Novel metabolites associated with HF risk were identified, elucidating disease pathways, specifically HFpEF. An MRS was associated with HF risk and improved 5-year risk prediction in older adults, which may assist at at-risk population identification.

Development and Validation of the American Heart Association's PREVENT Equations

BACKGROUND

Multivariable equations are recommended by primary prevention guidelines to assess absolute risk of cardiovascular disease (CVD). However, current equations have several limitations. Therefore, we developed and validated the American Heart Association Predicting Risk of CVD EVENTs (PREVENT) equations among US adults 30 to 79 years of age without known CVD.

METHODS

The derivation sample included individual-level participant data from 25 data sets (N=3 281 919) between 1992 and 2017. The primary outcome was CVD (atherosclerotic CVD and heart failure). Predictors included traditional risk factors (smoking status, systolic blood pressure, cholesterol, antihypertensive or statin use, and diabetes) and estimated glomerular filtration rate. Models were sex-specific, race-free, developed on the age scale, and adjusted for competing risk of non-CVD death. Analyses were conducted in each data set and meta-analyzed. Discrimination was assessed using the Harrell C-statistic. Calibration was calculated as the slope of the observed versus predicted risk by decile. Additional equations to predict each CVD subtype (atherosclerotic CVD and heart failure) and include optional predictors (urine albumin-to-creatinine ratio and hemoglobin A1c), and social deprivation index were also developed. External validation was performed in 3 330 085 participants from 21 additional data sets.

RESULTS

Among 6 612 004 adults included, mean±SD age was 53±12 years, and 56% were women. Over a mean±SD follow-up of 4.8±3.1 years, there were 211 515 incident total CVD events. The median C-statistics in external validation for CVD were 0.794 (interquartile interval, 0.763-0.809) in female and 0.757 (0.727-0.778) in male participants. The calibration slopes were 1.03 (interquartile interval, 0.81-1.16) and 0.94 (0.81-1.13) among female and male participants, respectively. Similar estimates for discrimination and calibration were observed for atherosclerotic CVD- and heart failure-specific models. The improvement in discrimination was small but statistically significant when urine albumin-to-creatinine ratio, hemoglobin A1c, and social deprivation index were added together to the base model to total CVD (ΔC-statistic [interquartile interval] 0.004 [0.004-0.005] and 0.005 [0.004-0.007] among female and male participants, respectively). Calibration improved significantly when the urine albumin-to-creatinine ratio was added to the base model among those with marked albuminuria (>300 mg/g; 1.05 [0.84-1.20] versus 1.39 [1.14-1.65]; P=0.01).

CONCLUSIONS

PREVENT equations accurately and precisely predicted risk for incident CVD and CVD subtypes in a large, diverse, and contemporary sample of US adults by using routinely available clinical variables.

Use of Clinical and Echocardiographic Evaluation to Assess the Risk of Heart Failure

BACKGROUND

Clinical and echocardiographic features predict incident heart failure (HF), but the optimal strategy for combining them is unclear.

OBJECTIVES

This study sought to define an effective means of using echocardiography in HF risk evaluation.

METHODS

The same clinical and echocardiographic evaluation was obtained in 2 groups with HF risk factors: a training group (n = 926, followed to 7 years) and a validation group (n = 355, followed to 10 years). Clinical risk was categorized as low, intermediate, and high using 4-year ARIC (Atherosclerosis Risk In Communities) HF risk score cutpoints of 9% and 33%. A risk stratification algorithm based on clinical risk and echocardiographic markers of stage B HF (SBHF) (abnormal global longitudinal strain [GLS], diastolic dysfunction, or left ventricular hypertrophy) was developed using a classification and regression tree analysis and was validated.

RESULTS

HF developed in 12% of the training group, including 9%, 18%, and 73% of low-, intermediate-, and high-risk patients. HF occurred in 8.6% of stage A HF and 19.4% of SBHF (P < 0.001), but stage A HF with clinical risk of ≥9% had similar outcome to SBHF. Abnormal GLS (HR: 2.92 [95% CI: 1.95-4.37]; P < 0.001) was the strongest independent predictor of HF. Normal GLS and diastolic function reclassified 61% of the intermediate-risk group into the low-risk group (HF incidence: 12%). In the validation group, 11% developed HF over 4.5 years; 4%, 17%, and 39% of low-, intermediate-, and high-risk groups. Similar results were obtained after exclusion of patients with known coronary artery disease. The echocardiographic parameters also provided significant incremental value to the ARIC score in predicting new HF admission (C-statistic: 0.78 [95% CI: 0.71-0.84] vs 0.83 [95% CI: 0.77-0.88]; P = 0.027).

CONCLUSIONS

Clinical risk assessment is adequate to classify low and high HF risk. Echocardiographic evaluation reclassifies 61% of intermediate-risk patients.

Prioritizing the primary prevention of heart failure: Measuring, modifying and monitoring risk

With the rising incidence of heart failure (HF) and increasing burden of morbidity, mortality, and healthcare expenditures, primary prevention of HF targeting individuals in at-risk HF (Stage A) and pre-HF (Stage B) Stages has become increasingly important with the goal to decrease progression to symptomatic (Stage C) HF. Identification of risk based on traditional risk factors (e.g., cardiovascular health which can be assessed with the American Heart Association's Life's Essential 8 framework), adverse social determinants of health, inherited risk of cardiomyopathies, and identification of risk-enhancing factors, such as patients with viral disease, exposure to cardiotoxic chemotherapy, and history of adverse pregnancy outcomes should be the first step in evaluation for HF risk. Next, use of guideline-endorsed risk prediction tools such as Pooled Cohort Equations to Prevent Heart Failure provide quantification of absolute risk of HF based in traditional risk factors. Risk reduction through counseling on traditional risk factors is a core focus of implementation of prevention and may include the use of novel therapeutics that target specific pathways to reduce risk of HF, such as mineralocorticoid receptor agonists (e.g., fineronone), angiotensin-receptor/neprolysin inhibitors, and sodium glucose co-transporter-2 inhibitors. These interventions may be limited in at-risk populations who experience adverse social determinants and/or individuals who reside in rural areas. Thus, strategies like telemedicine may improve access to preventive care. Gaps in the current knowledge base for risk-based prevention of HF are highlighted to outline future research that may target approaches for risk assessment and risk-based prevention with the use of artificial intelligence, genomics-enhanced strategies, and pragmatic trials to develop a guideline-directed medical therapy approach to reduce risk among individuals with Stage A and Stage B HF.

Incident Heart Failure Risk Reclassification With Race-Independent Estimated Glomerular Filtration Rate: A National Heart, Lung, and Blood Institute Pooled Cohorts Analysis

BACKGROUND

This study compared the predictive value of the race-independent creatinine- and cystatin C-based estimated glomerular filtration rate (eGFRcr-cys) and the race-dependent creatinine-based eGFR (eGFRcr) for incident heart failure (HF).

METHODS

This study combined the participant-level data from ARIC (Atherosclerosis Risk in Communities) (visit 4) and MESA (Multi-Ethnic Study of Atherosclerosis) (visit 1) to calculate eGFRcr-cys and eGFRcr. The primary outcome of the study was adjudicated incident HF over a follow-up period of 10 years. Multivariable Cox models were used to assess the risk of incident HF with the quartiles of eGFRcr-cys and eGFRcr.

RESULTS

Among 15,615 individuals (median age: 62 [57-68] years; 55.0% females; 23.9% Black), the median eGFRcr-cys and eGFRcr were 91.4 (79.4, 102.0) mL/min/1.73m2 and 84.7 (72.0, 94.7) mL/min/1.73m2, respectively. Compared with the fourth quartile of eGFRcr-cys, the hazard ratio for incident HF was 1.02 (95% CI:0.80-1.30) in the third quartile, 1.02 (95% CI:0.80-1.30) in the second quartile, and 1.47 (95% CI:1.16-1.86) in the first quartile. Compared with the 4th quartile of the eGFRcr, the risk of incident HF was similar in the 3rd (HRadj:0.90 [95% CI:0.73-1.12]), 2nd (HRadj: 0.96 [95% CI:0.77-1.20]), and 1st (HRadj:1.15 [95% CI:0.93-1.44]) quartiles. C-statistics were similar for the multivariable-adjusted Cox models for incident HF using eGFRcr (0.80 [0.79-0.81]) and eGFRcr-cys (0.80 [0.79-0.82]).

CONCLUSION

The eGFRcr and eGFRcr-cys had comparable predictive values for incident HF.

Sex-specific differences in risk factors, comorbidities, diagnostic challenges, optimal management, and prognostic outcomes of heart failure with preserved ejection fraction: A comprehensive literature review

Due to hormonal variations, heart failure with preserved ejection fraction (HFpEF) remains prevalent in women and affects almost half of the heart failure (HF) patients. Given the yearly death rate of 10-30% and the unavailability of medications targeting HFpEF, the need arises for a better understanding of the fundamental mechanisms of this syndrome. This comprehensive review explores sex-specific differences in traditional risk factors; female-specific factors that may impact HFpEF development and response to therapy, including variations in hormone levels that may occur pre- and post-menopausal or during pregnancy; and disparities in comorbidities, clinical presentation, and diagnostic challenges. Lastly, the review addresses prognostic outcomes, noting that women with HFpEF have a poor quality of life but a higher survival rate. It also discusses novel biomarkers and precision medicine, emphasizing their potential to improve early detection and personalized treatment.

Novel Prediction Equations for Absolute Risk Assessment of Total Cardiovascular Disease Incorporating Cardiovascular-Kidney-Metabolic Health: A Scientific Statement From the American Heart Association

Cardiovascular-kidney-metabolic (CKM) syndrome is a novel construct recently defined by the American Heart Association in response to the high prevalence of metabolic and kidney disease. Epidemiological data demonstrate higher absolute risk of both atherosclerotic cardiovascular disease (CVD) and heart failure as an individual progresses from CKM stage 0 to stage 3, but optimal strategies for risk assessment need to be refined. Absolute risk assessment with the goal to match type and intensity of interventions with predicted risk and expected treatment benefit remains the cornerstone of primary prevention. Given the growing number of therapies in our armamentarium that simultaneously address all 3 CKM axes, novel risk prediction equations are needed that incorporate predictors and outcomes relevant to the CKM context. This should also include social determinants of health, which are key upstream drivers of CVD, to more equitably estimate and address risk. This scientific statement summarizes the background, rationale, and clinical implications for the newly developed sex-specific, race-free risk equations: PREVENT (AHA Predicting Risk of CVD Events). The PREVENT equations enable 10- and 30-year risk estimates for total CVD (composite of atherosclerotic CVD and heart failure), include estimated glomerular filtration rate as a predictor, and adjust for competing risk of non-CVD death among adults 30 to 79 years of age. Additional models accommodate enhanced predictive utility with the addition of CKM factors when clinically indicated for measurement (urine albumin-to-creatinine ratio and hemoglobin A1c) or social determinants of health (social deprivation index) when available. Approaches to implement risk-based prevention using PREVENT across various settings are discussed.

Differences in predictors of incident heart failure according to atherosclerotic cardiovascular disease status

AIMS

Heart failure (HF) is a common cause of morbidity and mortality, related to a broad range of sociodemographic, lifestyle, cardiometabolic, and comorbidity risk factors, which may differ according to the presence of atherosclerotic cardiovascular disease (ASCVD). We assessed the association between incident HF with baseline status across these domains, overall and separated according to ASCVD status.

METHODS AND RESULTS

We included 5758 participants from the Baker Biobank cohort without HF at baseline enrolled between January 2000 and December 2011. The primary endpoint was incident HF, defined as hospital admission or HF-related death, determined through linkage with state-wide administrative databases (median follow-up 12.2 years). Regression models were fitted adjusted for sociodemographic variables, alcohol intake, smoking status, measures of adiposity, cardiometabolic profile measures, and individual comorbidities. During 65 987 person-years (median age 59 years, 38% women), incident HF occurred among 784 participants (13.6%) overall. Rates of incident HF were higher among patients with ASCVD (624/1929, 32.4%) compared with those without ASCVD (160/3829, 4.2%). Incident HF was associated with age, socio-economic status, alcohol intake, smoking status, body mass index (BMI), waist circumference, waist-hip ratio, systolic blood pressure (SBP), and low- and high-density lipoprotein cholesterol (LDL-C and HDL-C), with non-linear relationships observed for age, alcohol intake, BMI, waist circumference, waist-hip ratio, SBP, LDL-C, and HDL-C. Risk factors for incident HF were largely consistent regardless of ASCVD status, although diabetes status had a greater association with incident HF among patients without ASCVD.

CONCLUSIONS

Incident HF is associated with a broad range of baseline sociodemographic, lifestyle, cardiometabolic, and comorbidity factors, which are mostly consistent regardless of ASCVD status. These data could be useful in efforts towards developing risk prediction models that can be used in patients with ASCVD.

Preventing new-onset heart failure: Intervening at stage A

Heart failure (HF) prevention is an urgent public health need with national and global implications. Stage A HF patients do not show HF symptoms or structural heart disease but are at risk of HF development. There are no unique recommendations on detecting Stage A patients. Patients in Stage A are heterogeneous; many patients have different combinations of risk factors and, therefore, have markedly different absolute risks for HF. Comprehensive strategies to prevent HF at Stage A include intensive blood pressure lowering, adequate glycemic and lipid management, and heart-healthy behaviors (adopting Life's Essential 8). First and foremost, it is imperative to improve public awareness of HF risk factors and implement healthy lifestyle choices very early. In addition, recognize the HF risk-enhancing factors, which are nontraditional cardiovascular (CV) risk factors that identify individuals at high risk for HF (genetic susceptibility for HF, atrial fibrillation, chronic kidney disease, chronic liver disease, chronic inflammatory disease, sleep-disordered breathing, adverse pregnancy outcomes, radiation therapy, a history of cardiotoxic chemotherapy exposure, and COVID-19). Early use of biomarkers, imaging markers, and echocardiography (noninvasive measures of subclinical systolic and diastolic dysfunction) may enhance risk prediction among individuals without established CV disease and prevent chemotherapy-induced cardiomyopathy. Efforts are needed to address social determinants of HF risk for primordial HF prevention.Central illustrationPolicies developed by organizations such as the American Heart Association, American College of Cardiology, and the American Diabetes Association to reduce CV disease events must go beyond secondary prevention and encompass primordial and primary prevention.

Machine learning identification of risk factors for heart failure in patients with diabetes mellitus with metabolic dysfunction associated steatotic liver disease (MASLD): the Silesia Diabetes-Heart Project

BACKGROUND

Diabetes mellitus (DM), heart failure (HF) and metabolic dysfunction associated steatotic liver disease (MASLD) are overlapping diseases of increasing prevalence. Because there are still high numbers of patients with HF who are undiagnosed and untreated, there is a need for improving efforts to better identify HF in patients with DM with or without MASLD. This study aims to develop machine learning (ML) models for assessing the risk of the HF occurrence in patients with DM with and without MASLD.

RESEARCH DESIGN AND METHODS

In the Silesia Diabetes-Heart Project (NCT05626413), patients with DM with and without MASLD were analyzed to identify the most important HF risk factors with the use of a ML approach. The multiple logistic regression (MLR) classifier exploiting the most discriminative patient's parameters selected by the χ2 test following the Monte Carlo strategy was implemented. The classification capabilities of the ML models were quantified using sensitivity, specificity, and the percentage of correctly classified (CC) high- and low-risk patients.

RESULTS

We studied 2000 patients with DM (mean age 58.85 ± SD 17.37 years; 48% women). In the feature selection process, we identified 5 parameters: age, type of DM, atrial fibrillation (AF), hyperuricemia and estimated glomerular filtration rate (eGFR). In the case of MASLD( +) patients, the same criterion was met by 3 features: AF, hyperuricemia and eGFR, and for MASLD(-) patients, by 2 features: age and eGFR. Amongst all patients, sensitivity and specificity were 0.81 and 0.70, respectively, with the area under the receiver operating curve (AUC) of 0.84 (95% CI 0.82-0.86).

CONCLUSION

A ML approach demonstrated high performance in identifying HF in patients with DM independently of their MASLD status, as well as both in patients with and without MASLD based on easy-to-obtain patient parameters.

Deep learning-based prognostic model using non-enhanced cardiac cine MRI for outcome prediction in patients with heart failure

OBJECTIVES

To evaluate the performance of a deep learning-based multi-source model for survival prediction and risk stratification in patients with heart failure.

METHODS

Patients with heart failure with reduced ejection fraction (HFrEF) who underwent cardiac magnetic resonance between January 2015 and April 2020 were retrospectively included in this study. Baseline electronic health record data, including clinical demographic information, laboratory data, and electrocardiographic information, were collected. Short-axis non-contrast cine images of the whole heart were acquired to estimate the cardiac function parameters and the motion features of the left ventricle. Model accuracy was evaluated using the Harrell's concordance index. All patients were followed up for major adverse cardiac events (MACEs), and survival prediction was assessed using Kaplan-Meier curves.

RESULTS

A total of 329 patients were evaluated (age 54 ± 14 years; men, 254) in this study. During a median follow-up period of 1041 days, 62 patients experienced MACEs and their median survival time was 495 days. When compared with conventional Cox hazard prediction models, deep learning models showed better survival prediction performance. Multi-data denoising autoencoder (DAE) model reached the concordance index of 0.8546 (95% CI: 0.7902-0.8883). Furthermore, when divided into phenogroups, the multi-data DAE model could significantly discriminate between the survival outcomes of the high-risk and low-risk groups compared with other models (p < 0.001).

CONCLUSIONS

The proposed deep learning (DL) model based on non-contrast cardiac cine magnetic resonance imaging could independently predict the outcome of patients with HFrEF and showed better prediction efficiency than conventional methods.

CLINICAL RELEVANCE STATEMENT

The proposed multi-source deep learning model based on cardiac magnetic resonance enables survival prediction in patients with heart failure.

KEY POINTS

• A multi-source deep learning model based on non-contrast cardiovascular magnetic resonance (CMR) cine images was built to make robust survival prediction in patients with heart failure. • The ground truth definition contains electronic health record data as well as DL-based motion data, and cardiac motion information is extracted by optical flow method from non-contrast CMR cine images. • The DL-based model exhibits better prognostic value and stratification performance when compared with conventional prediction models and could aid in the risk stratification in patients with HF.

Efficacy of bariatric intervention as a bridge to cardiac transplant

BACKGROUND

Many patients with heart failure (HF) are denied cardiac transplants due to inability to meet transplantation body mass index (BMI) criteria. Bariatric intervention, including surgery, medication, and weight loss guidance, may help patients lose weight and become eligible for transplantation.

OBJECTIVE

We aim to contribute to the literature on the safety and efficacy of bariatric intervention on patients with obesity and HF who are awaiting cardiac transplantation.

SETTING

University hospital, United States.

METHODS

This was a mixed retrospective/prospective study. Eighteen patients with HF and BMI >35 kg/m2 were reviewed. Patients were divided based on whether they underwent bariatric surgery or nonsurgical intervention and whether they had left ventricular assist devices or other advanced heart failure therapy including inotropic support, guideline-directed medical therapy, and/or temporary mechanical circulatory support. Weight, BMI, and left ventricular ejection fraction (LVEF) were collected before bariatric intervention and 6 months after bariatric intervention.

RESULTS

No patients were lost to follow-up. Bariatric surgery led to statistically significant decreases in weight and BMI when compared with nonsurgical patients. At 6 months after intervention, surgical patients lost an average of 18.6 kg and decreased their BMI by 6.4 kg/m2 while nonsurgical patients lost 1.9 kg and decreased their BMI by .7 kg/m2. After bariatric intervention, surgical patients had an average LVEF increase of 5.9% and nonsurgical patients had an average decrease of 5.9%, although these findings lacked statistical significance.

CONCLUSION

Our study suggests that bariatric intervention among patients with HF and obesity is a safe and effective method of weight and BMI reduction.

Prediction models for heart failure in the community: A systematic review and meta-analysis

AIMS

Multivariable prediction models can be used to estimate risk of incident heart failure (HF) in the general population. A systematic review and meta-analysis was performed to determine the performance of models.

METHODS AND RESULTS

From inception to 3 November 2022 MEDLINE and EMBASE databases were searched for studies of multivariable models derived, validated and/or augmented for HF prediction in community-based cohorts. Discrimination measures for models with c-statistic data from ≥3 cohorts were pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using PROBAST. We included 36 studies with 59 prediction models. In meta-analysis, the Atherosclerosis Risk in Communities (ARIC) risk score (summary c-statistic 0.802, 95% confidence interval [CI] 0.707-0.883), GRaph-based Attention Model (GRAM; 0.791, 95% CI 0.677-0.885), Pooled Cohort equations to Prevent Heart Failure (PCP-HF) white men model (0.820, 95% CI 0.792-0.843), PCP-HF white women model (0.852, 95% CI 0.804-0.895), and REverse Time AttentIoN model (RETAIN; 0.839, 95% CI 0.748-0.916) had a statistically significant 95% PI and excellent discrimination performance. The ARIC risk score and PCP-HF models had significant summary discrimination among cohorts with a uniform prediction window. 77% of model results were at high risk of bias, certainty of evidence was low, and no model had a clinical impact study.

CONCLUSIONS

Prediction models for estimating risk of incident HF in the community demonstrate excellent discrimination performance. Their usefulness remains uncertain due to high risk of bias, low certainty of evidence, and absence of clinical effectiveness research.

Race as a Component of Cardiovascular Disease Risk Prediction Algorithms

PURPOSE OF REVIEW

Several prediction algorithms include race as a component to account for race-associated variations in disease frequencies. This practice has been questioned recently because of the risk of perpetuating race as a biological construct and diverting attention away from the social determinants of health (SDoH) for which race might be a proxy. We evaluated the appropriateness of including race in cardiovascular disease (CVD) prediction algorithms, notably the pooled cohort equations (PCE).

RECENT FINDINGS

In a recent investigation, we reported substantial and biologically implausible differences in absolute CVD risk estimates upon using PCE for predicting CVD risk in Black and White persons with identical risk factor profiles, which might result in differential treatment decisions based solely on their race. We recommend the development of raceless CVD risk prediction algorithms that obviate race-associated risk misestimation and racializing treatment practices, and instead incorporate measures of SDoH that mediate race-associated risk differences.

Development of a tool to predict the risk of incident heart failure in a general population: the HUNT for HF risk score

AIMS

Currently, no incident heart failure (HF) risk score that is in regular use in a general population is available. We aimed to develop this and compare with existing HF risk scores.

METHODS AND RESULTS

Participants in the third wave (2006-08) of the population-based Trøndelag Health Study 3 (HUNT3) were included if they reported no previous HF. Any hospital diagnoses captured during follow-up (until the end of 2018) of HF, cardiomyopathy, or hypertensive heart disease were assessed by an experienced cardiologist. Valid HF events were defined as symptoms/signs of HF and objective evidence of structural/functional abnormality of the heart at rest. The model was compared with slightly modified HF risk scores (the Health Aging and Body Composition HF risk score, the Framingham HF risk score, the Pooled Cohort equations to Prevent HF risk score, and NORRISK 2). Among 36 511 participants (mean ± SD age of 57.9 ± 13.3 years, 55.4% female), with a mean follow-up of 10.2 ± 1.3 years, 1366 developed HF (incidence rate of 3.66 per 1000 participant years). Out of the 38 relevant clinical variables assessed, we identified 12 (atrial fibrillation being the strongest) that independently predicted an HF event. The final model demonstrated good discrimination (C statistics = 0.904) and calibration, was stable in internal validation, and performed well compared with existing risk scores. The model identified that, at enrolment, 31 391 (86%), 2386 (7%), 1246 (3%), and 1488 (4%) had low, low-intermediate, high-intermediate, and high 10-year HF risk, respectively.

CONCLUSIONS

Twelve clinical variables independently predicted 10-year HF risk. The model may serve well as the foundation of a practical, online risk score for HF in general practice.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT04648852.

The AHA/ACC/HFSA 2022 Heart Failure Guidelines: Changing the Focus to Heart Failure Prevention

The prevalence of heart failure (HF) in the United States (U.S.) is estimated at over 6 million adults, with the incidence continuing to increase. A large proportion of the U.S. population is also at risk of HF due to the high prevalence of established HF risk factors, such as hypertension, diabetes, and obesity. Many individuals have multiple risk factors, placing them at even higher risk. In addition, these risk factors disproportionately impact various racial and ethnic groups. Recognizing the rising health and economic burden of HF in the U.S., the 2022 American Heart Association / American College of Cardiology / Heart Failure Society of America (AHA/ACC/HFSA) Heart Failure Guideline placed a strong emphasis on prevention of HF. The purpose of this review is to highlight the role of both primary and secondary prevention in HF, as outlined by the recent guideline, and address the role of the preventive cardiology community in reducing the prevalence of HF in at-risk individuals.

Serum cholesterol levels and the risk of brain natriuretic peptide-diagnosed heart failure in postmenopausal women: a population-based prospective cohort study

OBJECTIVE

Hormonal changes during menopause can disturb serum cholesterol which is closely associated with cardiovascular disease. This study investigated the prospective association between serum cholesterol and heart failure (HF) risk in postmenopausal women.

METHODS

We analyzed data from 1,307 Japanese women, aged 55 to 94 years. All women had no history of HF, and their baseline brain natriuretic peptide (BNP) levels were less than 100 pg/mL. During the follow-ups conducted every 2 years, HF was diagnosed among women who developed BNP of 100 pg/mL or greater. Cox proportional hazard models were applied to calculate hazard ratios and 95% CI of HF for women per their baseline total cholesterol, low-density lipoprotein cholesterol, and high-density lipoprotein cholesterol (HDL-C) levels. The Cox regression models were adjusted for age, body mass index, smoking, alcohol drinking, hypertension, diabetes, cardiac murmurs, arrhythmia, stroke or ischemic heart disease, chronic kidney disease, and lipid-lowering agent use.

RESULTS

Within an 8-year median follow-up, 153 participants developed HF. In the multivariable-adjusted model, women with total cholesterol of 240 mg/dL or greater (compared with 160-199 mg/dL) and HDL-C of 100 mg/dL or greater (compared with 50-59 mg/dL) showed an increased risk of HF: hazard ratios (95% CI) = 1.70 (1.04-2.77) and 2.70 (1.10-6.64), respectively. The results remained significant after further adjusting for baseline BNP. No associations were observed with low-density lipoprotein cholesterol.

CONCLUSIONS

Total cholesterol of 240 mg/dL or greater and HDL-C of 100 mg/dL or greater were positively associated with the risk of HF in postmenopausal Japanese women.

Trajectories of renal biomarkers and new-onset heart failure in the general population: Findings from the PREVEND study

AIMS

Renal dysfunction is one of the most critical risk factors for developing heart failure (HF). However, the association between repeated measures of renal function and incident HF remains unclear. Therefore, this study investigated the longitudinal trajectories of urinary albumin excretion (UAE) and serum creatinine and their association with new-onset HF and all-cause mortality.

METHODS AND RESULTS

Using group-based trajectory analysis, we estimated trajectories of UAE and serum creatinine in 6881 participants from the Prevention of Renal and Vascular End-stage Disease (PREVEND) study and their association with new-onset HF and all-cause death during the 11-years of follow-up. Most participants had stable low UAE or serum creatinine. Participants with persistently higher UAE or serum creatinine were older, more often men, and more often had comorbidities, such as diabetes, a previous myocardial infarction or dyslipidaemia. Participants with persistently high UAE had a higher risk of new-onset HF or all-cause mortality, whereas stable serum creatinine trajectories showed a linear association for new-onset HF and no association with all-cause mortality.

CONCLUSION

Our population-based study identified different but often stable longitudinal patterns of UAE and serum creatinine. Patients with persistently worse renal function, such as higher UAE or serum creatinine, were at a higher risk of HF or mortality.

Proteomic cardiovascular risk assessment in chronic kidney disease

AIMS

Chronic kidney disease (CKD) is widely prevalent and independently increases cardiovascular risk. Cardiovascular risk prediction tools derived in the general population perform poorly in CKD. Through large-scale proteomics discovery, this study aimed to create more accurate cardiovascular risk models.

METHODS AND RESULTS

Elastic net regression was used to derive a proteomic risk model for incident cardiovascular risk in 2182 participants from the Chronic Renal Insufficiency Cohort. The model was then validated in 485 participants from the Atherosclerosis Risk in Communities cohort. All participants had CKD and no history of cardiovascular disease at study baseline when ∼5000 proteins were measured. The proteomic risk model, which consisted of 32 proteins, was superior to both the 2013 ACC/AHA Pooled Cohort Equation and a modified Pooled Cohort Equation that included estimated glomerular filtrate rate. The Chronic Renal Insufficiency Cohort internal validation set demonstrated annualized receiver operating characteristic area under the curve values from 1 to 10 years ranging between 0.84 and 0.89 for the protein and 0.70 and 0.73 for the clinical models. Similar findings were observed in the Atherosclerosis Risk in Communities validation cohort. For nearly half of the individual proteins independently associated with cardiovascular risk, Mendelian randomization suggested a causal link to cardiovascular events or risk factors. Pathway analyses revealed enrichment of proteins involved in immunologic function, vascular and neuronal development, and hepatic fibrosis.

CONCLUSION

In two sizeable populations with CKD, a proteomic risk model for incident cardiovascular disease surpassed clinical risk models recommended in clinical practice, even after including estimated glomerular filtration rate. New biological insights may prioritize the development of therapeutic strategies for cardiovascular risk reduction in the CKD population.

ACC/AHA/HFSA 2022 and ESC 2021 guidelines on heart failure comparison

The 2022 American College of Cardiology/American Heart Association/Heart Failure Society of America (ACC/AHA/HFSA) and the 2021 European Society of Cardiology (ESC) both provide evidence-based guides for the diagnosis and treatment of heart failure (HF). In this review, we aimed to compare recommendations suggested by these guidelines highlighting the differences and latest evidence mentioned in each of the guidelines. While the staging of HF depends on left ventricular ejection fraction, the Universal Definition of HF, suggested in 2021, is described in 2022 ACC/AHA/HFSA guidelines. Both guidelines recommend invasive and non-invasive tests to diagnose. Despite being identical in the backbone, some differences exist in medical therapy and devices, which can be partially attributed to the recent trials published that are presented in the American guidelines. The recommendation of implantable cardioverter defibrillator for prevention in HF with reduced ejection fraction (HFrEF) patients, made by ACC/AHA/HFSA guidelines, is among the bold differences. It seems that ACC/AHA/HFSA guidelines emphasize the quality of life, cost-effectiveness, and optimization of care given to patients. On the other hand, the ESC guidelines provide recommendations for certain comorbidities. This comparison can guide clinicians in choosing the proper approach for their own settings and the writing committees in addressing the differences in order to have better consistency in future guidelines.

Predicting heart failure onset in the general population using a novel data-mining artificial intelligence method

We aimed to identify combinations of clinical factors that predict heart failure (HF) onset using a novel limitless-arity multiple-testing procedure (LAMP). We also determined if increases in numbers of predictive combinations of factors increases the probability of developing HF. We recruited people without HF who received health check-ups in 2010, who were followed annually for 4 years. Using 32,547 people, LAMP was performed to identify combinations of factors of fewer than four factors that could predict the onset of HF. The ability of the method to predict the probability of HF onset based on the number of matching predictive combinations of factors was determined in 275,658 people. We identified 549 combinations of factors for the onset of HF. Then we classified 275,658 people into six groups who had 0, 1-50, 51-100, 101-150, 151-200 or 201-250 predictive combinations of factors for the onset of HF. We found that the probability of HF progressively increased as the number of predictive combinations of factors increased. We identified combinations of variables that predict HF onset. An increased number of matching predictive combinations for the onset of HF increased the probability of HF onset.

Blood pressure per the 2017 ACC/AHA and 2018 ESC/ESH guidelines and heart failure risk: the Suita Study

Hypertension is a significant risk factor for heart failure (HF). Since hypertension definition varies across guidelines, identifying blood pressure (BP) categories that should be targeted to prevent HF is required. We, therefore, investigated the association between hypertension per the 2017 American College of Cardiology/American Heart Association (ACC/AHA) and 2018 European Society of Cardiology/European Society of Hypertension (ESC/ESH) guidelines and HF risk. This prospective cohort study included randomly selected 2809 urban Japanese people from the Suita Study. Cox regression was used to assess HF risk, in the form of hazard ratios (HRs) and 95% confidence intervals (95% CIs), for different BP categories in both guidelines, compared to a reference category defined as systolic BP (SBP) <120 mmHg and diastolic BP (DBP) <80 mmHg. Within 8 years of median follow-up, 339 HF cases were detected. Per the 2017 ACC/AHA guidelines, hypertension I and II and isolated systolic hypertension were associated with increased HF risk: HRs (95% CIs) = 1.81 (1.33-2.47), 1.68 (1.24-2.27), and 1.64 (1.13-2.39), respectively. Per the 2018 ESC/ESH guidelines, high-normal BP, hypertension I, II, and III, and isolated systolic hypertension were associated with increased HF risk: HRs (95% CIs) = 1.88 (1.35-2.62), 1.57 (1.13-2.16), 2.10 (1.34-3.29), 2.57 (1.15-5.77), and 1.51 (1.04-2.19), respectively. In conclusion, hypertension and isolated systolic hypertension per the 2017 ACC/AHA and 2018 ESC/ESH guidelines and high-normal BP per the 2018 ESC/ESH guidelines are risk factors for HF.

Atherosclerotic Cardiovascular Disease or Heart Failure: First Cardiovascular Event in Adults With Prediabetes and Diabetes

BACKGROUND

Individuals with prediabetes and diabetes are at increased risk of atherosclerotic cardiovascular disease (ASCVD) and heart failure (HF). Whether ASCVD or HF is more likely to occur first in these populations within different race-sex groups is unknown.

OBJECTIVE

To determine the competing risk for the first cardiovascular event by subtype in Black and white men and women with prediabetes and diabetes.

METHODS

Individual-level data from adults without ASCVD or HF were pooled from 6 population-based cohorts. We estimated the competing cumulative incidences of ASCVD, HF and noncardiovascular death as the first event in middle-aged (40-59 years) and older (60-79 years) adults, stratified by race and sex, with normal fasting plasma glucose (FPG < 100 mg/dL), prediabetes (FPG 100-125 mg/dL) and diabetes (FPG ≥ 126 mg/dL or on antihyperglycemic agents) at baseline. Within each race-sex group, we estimated risk the adjusted hazard ratio of ASCVD, HF and noncardiovascular death in adults with prediabetes and diabetes relative to adults with normoglycemia after adjusting for cardiovascular risk factors.

RESULTS

In 40,117 participants with 638,910 person-years of follow-up, 5781 cases of incident ASCVD and 3179 cases of incident HF occurred. In middle-aged adults with diabetes, competing cumulative incidence of ASCVD as a first event was higher than HF in white men (35.4% vs 11.6%), Black men (31.6% vs 15.1%) and white women (24.3% vs 17.2%) but not in Black women (26.4% vs 28.4%). Within each group, the adjusted hazard ratio of ASCVD and HF was significantly higher in adults with diabetes than in adults with normal FPG levels. Findings were largely similar in middle-aged adults with prediabetes and older adults with prediabetes or diabetes.

CONCLUSIONS

Black women with diabetes are more likely to develop HF as their first CVD event, whereas individuals with diabetes from other race-sex groups are more likely to present first with ASCVD. These results can inform the tailoring of primary prevention therapies for either HF- or ASCVD-specific pathways based on individual-level risk.

Associations of relative fat mass, a new index of adiposity, with type-2 diabetes in the general population

BACKGROUND

Relative fat mass (RFM) is a novel sex-specific anthropometric equation (based on height and waist measurements) to estimate whole-body fat percentage.

OBJECTIVE

To examine associations of RFM with incident type-2 diabetes (T2D), and to benchmark its performance against body-mass index (BMI), waist circumference (WC) and waist-to-hip ratio (WHR).

METHODS

This prospective longitudinal study included data from three Dutch community-based cohorts free of baseline diabetes. First, we examined data from the PREVEND cohort (median age and follow-up duration: 48.0 and 12.5 years, respectively) using Cox regression models. Validation was performed in the Lifelines (median age and follow-up duration: 45.5 and 3.8 years, respectively) and Rotterdam (median age and follow-up duration: 68.0 and 13.9 years, respectively) cohorts.

RESULTS

Among 7961 PREVEND participants, 522 (6.6%) developed T2D. In a multivariable model, all adiposity indices were significantly associated with incident T2D (P_all<0.001). While 1 SD increase in BMI, WC and WHR were associated with 68%, 77% and 61% increased risk of developing T2D [Hazard ratio (HR)_BMI: 1.68 (95%CI: 1.57-1.80), HR_WC: 1.77 (95% CI: 1.63-1.92) and HR_WHR: 1.61 (95%CI: 1.48-1.75)], an equivalent increase in RFM was associated with 119% increased risk [HR: 2.19 (95%CI: 1.96-2.44)]. RFM was associated with incident T2D across all age groups, with the largest effect size in the youngest (<40 years) age category [HR: 2.90 (95%CI: 2.15-3.92)]. Results were broadly similar in Lifelines (n = 93,870) and Rotterdam (n = 5279) cohorts.

CONCLUSIONS

RFM is strongly associated with new-onset T2D and displays the potential to be used in the general practice setting to estimate the risk of future diabetes.

Are Non-Invasive Modalities for the Assessment of Atherosclerosis Useful for Heart Failure Predictions?

Heart failure (HF) is becoming an increasingly common issue worldwide and is associated with significant morbidity and mortality, making its prevention an important clinical goal. The criteria evaluated using non-invasive modalities such as coronary artery calcification, the ankle-brachial index, and carotid intima-media thickness have been proven to be effective in determining the relative risk of atherosclerotic cardiovascular disease. Notably, risk assessments using these modalities have been proven to be superior to the traditional risk predictors of cardiovascular disease. However, the ability to assess HF risk has not yet been well-established. In this review, we describe the clinical significance of such non-invasive modalities of atherosclerosis assessments and examine their ability to assess HF risk. The predictive value could be influenced by the left ventricular ejection fraction. Specifically, when the ejection fraction is reduced, its predictive value increases because this condition is potentially a result of coronary artery disease. In contrast, using these measures to predict HF with a preserved ejection fraction may be difficult because it is a heterogeneous condition. To overcome this issue, further research, especially on HF with a preserved ejection fraction, is required.

Pragmatic screening for heart failure in the general population using an electrocardiogram‐based neural network

AIMS

We aim to develop a pragmatic screening tool for heart failure at the general population level.

METHODS AND RESULTS

This study was conducted within the Hamburg-City-Health-Study, an ongoing, prospective, observational study enrolling randomly selected inhabitants of the city of Hamburg aged 45-75 years. Heart failure was diagnosed per current guidelines. Using only digital electrocardiograms (ECGs), a convolutional neural network (CNN) was built to discriminate participants with and without heart failure. As comparisons, known risk variables for heart failure were fitted into a logistic regression model and a random forest classifier. Of the 5299 individuals included into this study, 318 individuals (6.0%) had heart failure. Using only the digital ECGs instead of several risk variables as an input, the CNN provided a comparable predictive accuracy for heart failure versus the logistic regression model and the random forest classifier [area under the curve (AUC) of 0.75, a sensitivity of 0.67 and a specificity of 0.69 for the CNN; AUC 0.77, a sensitivity of 0.63 and a specificity of 0.76 for the logistic regression; AUC 0.79, a sensitivity of 0.67 and a specificity of 0.72 for the random forest classifier].

CONCLUSIONS

Using a CNN build on digital ECGs only and requiring no additional input, we derived a screening tool for heart failure in the general population. This could be perfectly embedded into clinical routine of general practitioners, as it builds on an already established diagnostic tool and does not require additional, time-consuming input. This could help to alleviate the underdiagnosis of heart failure.

Optimal cardiometabolic health and risk of heart failure in type 2 diabetes: an analysis from the Look AHEAD trial

AIMS

To evaluate the contribution of baseline and longitudinal changes in cardiometabolic health (CMH) towards heart failure (HF) risk among adults with type 2 diabetes (T2D).

METHODS AND RESULTS

Participants of the Look AHEAD trial with T2D and without prevalent HF were included. Adjusted Cox models were used to create a CMH score incorporating target levels of parameters weighted based on relative risk for HF. The associations of baseline and changes in the CMH score with risk of overall HF, HF with preserved (HFpEF) and reduced ejection fraction (HFrEF) were assessed using Cox models. Among the 5080 participants, 257 incident HF events occurred over 12.4 years of follow-up. The CMH score included 2 points each for target levels of waist circumference, glomerular filtration rate, urine albumin-to-creatinine ratio, and 1 point each for blood pressure and glycated haemoglobin at target. High baseline CMH score (6-8) was significantly associated with lower overall HF risk (adjusted hazard ratio [HR], ref = low score (0-3): 0.31, 95% confidence interval [CI] 0.21-0.47) with similar associations observed for HFpEF and HFrEF. Improvement in CMH was significantly associated with lower risk of overall HF (adjusted HR per 1-unit increase in score at 4 years: 0.80, 95% CI 0.70-0.91). In the ACCORD validation cohort, the baseline CMH score performed well for predicting HF risk with adequate discrimination (C-index 0.70), calibration (chi-square 5.53, p = 0.70), and risk stratification (adjusted HR [high (6-8) vs. low score (0-3)]: 0.35, 95% CI 0.26-0.46). In the Look AHEAD subgroup with available biomarker data, incorporating N-terminal pro-B-type natriuretic peptide to the baseline CMH score improved model discrimination (C-index 0.79) and risk stratification (adjusted HR [high (8-10) vs. low score (0-4)]: 0.18, 95% CI 0.09-0.35).

CONCLUSIONS

Achieving target levels of more CMH parameters at baseline and sustained improvements were associated with lower HF risk in T2D.

Improving predictive performance in incident heart failure using machine learning and multi-center data

Objective

To mitigate the burden associated with heart failure (HF), primary prevention is of the utmost importance. To improve early risk stratification, advanced computational methods such as machine learning (ML) capturing complex individual patterns in large data might be necessary. Therefore, we compared the predictive performance of incident HF risk models in terms of (a) flexible ML models and linear models and (b) models trained on a single cohort (single-center) and on multiple heterogeneous cohorts (multi-center).

Design and methods

In our analysis, we used the meta-data consisting of 30,354 individuals from 6 cohorts. During a median follow-up of 5.40 years, 1,068 individuals experienced a non-fatal HF event. We evaluated the predictive performance of survival gradient boosting (SGB), CoxNet, the PCP-HF risk score, and a stacking method. Predictions were obtained iteratively, in each iteration one cohort serving as an external test set and either one or all remaining cohorts as a training set (single- or multi-center, respectively).

Results

Overall, multi-center models systematically outperformed single-center models. Further, c-index in the pooled population was higher in SGB (0.735) than in CoxNet (0.694). In the precision-recall (PR) analysis for predicting 10-year HF risk, the stacking method, combining the SGB, CoxNet, Gaussian mixture and PCP-HF models, outperformed other models with PR/AUC 0.804, while PCP-HF achieved only 0.551.

Conclusion

With a greater number and variety of training cohorts, the model learns a wider range of specific individual health characteristics. Flexible ML algorithms can be used to capture these diverse distributions and produce more precise prediction models.

Machine Learning-Based Models Incorporating Social Determinants of Health vs Traditional Models for Predicting In-Hospital Mortality in Patients With Heart Failure

Importance

Traditional models for predicting in-hospital mortality for patients with heart failure (HF) have used logistic regression and do not account for social determinants of health (SDOH).

Objective

To develop and validate novel machine learning (ML) models for HF mortality that incorporate SDOH.

Design, Setting, and Participants

This retrospective study used the data from the Get With The Guidelines-Heart Failure (GWTG-HF) registry to identify HF hospitalizations between January 1, 2010, and December 31, 2020. The study included patients with acute decompensated HF who were hospitalized at the GWTG-HF participating centers during the study period. Data analysis was performed January 6, 2021, to April 26, 2022. External validation was performed in the hospitalization cohort from the Atherosclerosis Risk in Communities (ARIC) study between 2005 and 2014.

Main Outcomes and Measures

Random forest-based ML approaches were used to develop race-specific and race-agnostic models for predicting in-hospital mortality. Performance was assessed using C index (discrimination), regression slopes for observed vs predicted mortality rates (calibration), and decision curves for prognostic utility.

Results

The training data set included 123 634 hospitalized patients with HF who were enrolled in the GWTG-HF registry (mean [SD] age, 71 [13] years; 58 356 [47.2%] female individuals; 65 278 [52.8%] male individuals. Patients were analyzed in 2 categories: Black (23 453 [19.0%]) and non-Black (2121 [2.1%] Asian; 91 154 [91.0%] White, and 6906 [6.9%] other race and ethnicity). The ML models demonstrated excellent performance in the internal testing subset (n = 82 420) (C statistic, 0.81 for Black patients and 0.82 for non-Black patients) and in the real-world-like cohort with less than 50% missingness on covariates (n = 553 506; C statistic, 0.74 for Black patients and 0.75 for non-Black patients). In the external validation cohort (ARIC registry; n = 1205 Black patients and 2264 non-Black patients), ML models demonstrated high discrimination and adequate calibration (C statistic, 0.79 and 0.80, respectively). Furthermore, the performance of the ML models was superior to the traditional GWTG-HF risk score model (C index, 0.69 for both race groups) and other rederived logistic regression models using race as a covariate. The performance of the ML models was identical using the race-specific and race-agnostic approaches in the GWTG-HF and external validation cohorts. In the GWTG-HF cohort, the addition of zip code-level SDOH parameters to the ML model with clinical covariates only was associated with better discrimination, prognostic utility (assessed using decision curves), and model reclassification metrics in Black patients (net reclassification improvement, 0.22 [95% CI, 0.14-0.30]; P < .001) but not in non-Black patients.

Conclusions and Relevance

ML models for HF mortality demonstrated superior performance to the traditional and rederived logistic regressions models using race as a covariate. The addition of SDOH parameters improved the prognostic utility of prediction models in Black patients but not non-Black patients in the GWTG-HF registry.