A model-agnostic approach for understanding heart failure risk factors.
Ontology highlight
ABSTRACT: Objective
Understanding the risk factors for developing heart failure among patients with type 2 diabetes can contribute to preventing deterioration of quality of life for those persons. Electronic health records (EHR) provide an opportunity to use sophisticated machine learning models to understand and compare the effect of different risk factors for developing HF. As the complexity of the model increases, however, the transparency of the model often decreases. To interpret the results, we aimed to develop a model-agnostic approach to shed light on complex models and interpret the effect of features on developing heart failure. Using the HealthFacts EHR database of the Cerner EHR, we extracted the records of 723 patients with at least 6 yeas of follow up of type 2 diabetes, of whom 134 developed heart failure. Using age and comorbidities as features and heart failure as the outcome, we trained logistic regression, random forest, XGBoost, neural network, and then applied our proposed approach to rank the effect of each factor on developing heart failure.Results
Compared to the "importance score" built-in function of XGBoost, our proposed approach was more accurate in ranking the effect of the different risk factors on developing heart failure.
SUBMITTER: Miran SM
PROVIDER: S-EPMC8130447 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Although care of patients with heart failure (HF) has improved in the past decade, important disparities in HF outcomes persist based on race/ethnicity. Age-adjusted HF-related cardiovascular disease death rates are higher for Black patients, particularly among young Black men and women whose rates of death are 2.6- and 2.97-fold higher, respectively, than White men and women. Similarly, the rate of HF hospitalization for Black men and women is nearly 2.5-fold higher when compared with Whites, with costs that are significantly higher in the first year after HF hospitalization. While the relative rate of HF hospitalization has improved for other race/ethnic minorities, the disparity in HF hospitalization between Black and White patients has not decreased during the last decade. Although access to care and socioeconomic status have been traditional explanations for the observed racial disparities in HF outcomes, contemporary data suggest that novel factors including genetic susceptibility as well as social determinants of health and implicit bias may play a larger role in health outcomes than previously appreciated. The purpose of this review is to describe the complex interplay of factors that influence racial disparities in HF incidence, prevalence, and disease severity, with a highlight on evolving knowledge that will impact the clinical care and address future research needs to improve HF disparities in Blacks.
| S-EPMC7644144 | biostudies-literature
Project description:BACKGROUND:Persons identifying as Black, Chinese, or South Asian make up the largest minority groups in Canada. Individuals with chronic heart failure (CHF) from these groups experience a greater rate of re-hospitalization and poorer quality of life. Although experts agree that culture can shape the experience of CHF, little is known about how patients from these minority populations define a good quality of life with CHF and what barriers they experience when carrying out self-care behaviours. The aim of this qualitative study was to examine cultural and gender-based influences on quality of life in patients with CHF. METHODS:Purposive sampling included 30 patients (67% male), 18 to 75?years of age, who self-identified as Black (n?=?8), Chinese (n?=?9), or South Asian (n?=?6). Caucasians (n?=?7) were included as a comparison group. Semi-structured interviews (see the online appendix), lasting approximately 60?min, were conducted, which focused on personal understanding of CHF and living with the disease, including impact on lifestyle and quality of life. An inductive qualitative approach with thematic content analysis was used to develop key insights into individual experience of CHF, as well as cultural and gender-based influences on self-care and quality of life. Descriptive statistics were generated from questionnaire responses. RESULTS:Five key themes emerged from the narrative analysis of participant interviews: (i) CHF as an emergent reality, (ii) quality of life and disruption of lifecourse milestones, (iii) the challenge to accept CHF and re-evaluation of quality of life; (iv) impact on social activities essential to quality of life, and (v) life with CHF as a commitment to culturally tailored self-care. Participants described the unique impact of CHF on their quality of life, including life trajectory milestones such as dating, parenting, and retirement planning, as well as the importance of accepting their diagnosis, and the reframing goals for living well with heart failure. Positive and negative impacts on social relationships were noted, including sexual intimacy and interactions with spouses, other family members, and co-workers. CONCLUSIONS:Study findings highlight important lifespan, cultural, and gender considerations that can inform the improvement of patient care and quality of life for patients and their families.
| S-EPMC7368735 | biostudies-literature
Project description:AimsInformation on the prevalence, outcome and factors associated with heart failure in patients with adult congenital heart disease (CHD) (ACHD-HF) is lacking. We aimed at assessing the prevalence and outcome of ACHD-HF, the variables associated with ACHD-HF, and the differences between major anatomical/pathophysiological ACHD subgroups.Methods and resultsWe included 3905 patients (age 35.4 ± 13.2 years) under active follow-up in our institution (last visit >2010). Outcome of ACHD-HF cases was compared with sex- and age-matched cases. Univariable and multivariable binary logistic regression with ACHD-HF diagnosis as a dependent variable was performed. Overall prevalence of ACHD-HF was 6.4% (mean age 49.5 ± 16.7 years), but was higher in patients with cyanotic CHD (41%), Fontan circulation (30%), and a systemic right ventricle (25%). All-cause mortality was higher in ACHD-HF cases when compared with controls (mortality rate ratio 4.67 (2.36-9.27); P = 0.0001). In multivariable logistic regression analysis, age at latest follow-up [per 10 years; odds ratio (OR) 1.52; 95% confidence interval (CI) 1.31-1.77], infective endocarditis (OR 4.11; 95%CI 1.80-9.38), history of atrial arrhythmia (OR 3.52; 95%CI 2.17-5.74), pacemaker implantation (OR 2.66; 95% CI 1.50-4.72), end-organ dysfunction (OR 2.41; 95% CI 1.03-5.63), New York Heart Association class (OR 9.28; 95% CI 6.04-14.25), heart rate (per 10 bpm; OR 1.27; 95% CI 1.08-1.50), ventricular dysfunction (OR 3.62; 95% CI 2.54-5.17), and pulmonary hypertension severity (OR 1.66; 95% CI 1.21-2.30) were independently related to the presence of ACHD-HF. Some variables (age, atrial arrhythmia, pacemaker, New York Heart Association, and ventricular dysfunction) were related to ACHD-HF in all anatomical/physiological subgroups, whereas others were not.ConclusionsACHD-HF is prevalent especially in complex CHD and is associated with poor prognosis. Our data provide insight in the factors related to ACHD-HF including differences between specific anatomical and physiological subgroups.
| S-EPMC8318399 | biostudies-literature
Project description:Cancer and cardiovascular disease account for nearly half of all deaths in the US. The majority of cancer therapies are known to cause potential cardiac toxicity in some form. Patients with underlying cardiac disease are at a particularly increased risk for worse outcomes following cancer therapy. Most alarming is the potential for heart failure as a result of cancer treatment, which may lead to early disruption or withdrawal of life-saving cancer therapies and can potentially increase cardiovascular mortality. A multi-disciplinary cardio-oncology approach can improve outcomes through early surveillance, prevention and treatment strategies.
| S-EPMC5494160 | biostudies-other
Project description:OBJECTIVES:This study sought to identify modifiable risk factors and estimate the impact of risk factor modification on heart failure (HF) risk in women with new-onset atrial fibrillation (AF). BACKGROUND:Incident HF is the most common nonfatal event in patients with AF, although strategies for HF prevention are lacking. METHODS:We assessed 34,736 participants in the Women's Health Study who were free of prevalent cardiovascular disease at baseline. Cox models with time-varying assessment of risk factors after AF diagnosis were used to identify significant modifiable risk factors for incident HF. RESULTS:Over a median follow-up of 20.6 years, 1,495 women developed AF without prevalent HF. In multivariable models, new-onset AF was associated with an increased risk of HF (hazard ratio [HR]: 9.03; 95% confidence interval [CI]: 7.52 to 10.85). Once women with AF developed HF, all-cause (HR: 1.83; 95% CI: 1.37 to 2.45) and cardiovascular mortality (HR: 2.87; 95% CI: 1.70 to 4.85) increased. In time-updated, multivariable models accounting for changes in risk factors after AF diagnosis, systolic blood pressure >120 mm Hg, body mass index ?30 kg/m2, current tobacco use, and diabetes mellitus were each associated with incident HF. The combination of these 4 modifiable risk factors accounted for an estimated 62% (95% CI: 23% to 83%) of the population-attributable risk of HF. Compared with women with 3 or 4 risk factors, those who maintained or achieved optimal risk factor control had a progressive decreased risk of HF (HR for 2 risk factors: 0.60; 95% CI: 0.37 to 0.95; 1 risk factor: 0.40; 95% CI: 0.25 to 0.63; and 0 risk factors: 0.14; 95% CI: 0.07 to 0.29). CONCLUSIONS:In women with new-onset AF, modifiable risk factors including obesity, hypertension, smoking, and diabetes accounted for the majority of the population risk of HF. Optimal levels of modifiable risk factors were associated with decreased HF risk. Prospective assessment of risk factor modification at the time of AF diagnosis may warrant future investigation.
| S-EPMC5873947 | biostudies-literature
Project description:Adverse reactions in normal tissue after radiotherapy (RT) limit the dose that can be given to tumour cells. Since 80% of individual variation in clinical response is estimated to be caused by patient-related factors, identifying these factors might allow prediction of patients with increased risk of developing severe reactions. While inactivation of cell renewal is considered a major cause of toxicity in early-reacting normal tissues, complex interactions involving multiple cell types, cytokines, and hypoxia seem important for late reactions. Here, we review 'omics' approaches such as screening of genetic polymorphisms or gene expression analysis, and assess the potential of epigenetic factors, posttranslational modification, signal transduction, and metabolism. Furthermore, functional assays have suggested possible associations with clinical risk of adverse reaction. Pathway analysis incorporating different 'omics' approaches may be more efficient in identifying critical pathways than pathway analysis based on single 'omics' data sets. Integrating these pathways with functional assays may be powerful in identifying multiple subgroups of RT patients characterised by different mechanisms. Thus 'omics' and functional approaches may synergise if they are integrated into radiogenomics 'systems biology' to facilitate the goal of individualised radiotherapy.
| S-EPMC5016239 | biostudies-other
Project description:The lifetime risk of heart failure at age 40 years is approximately 1 in 5 in the general population; however, little is known about the association between modifiable lifestyle factors and the remaining lifetime risk of heart failure.To examine the association between modifiable lifestyle factors and the lifetime risk of heart failure in a large cohort of men.Prospective cohort study using data from 20,900 men (mean age at baseline, 53.6 years) from the Physicians' Health Study I (1982-2008) who were apparently healthy at baseline. Six modifiable lifestyle factors were assessed: body weight, smoking, exercise, alcohol intake, consumption of breakfast cereals, and consumption of fruits and vegetables.Lifetime risk of heart failure.During a mean follow-up of 22.4 years, 1200 men developed heart failure. Overall, the lifetime risk of heart failure was 13.8% (95% confidence interval [CI], 12.9%-14.7%) at age 40 years. Lifetime risk remained constant in men who survived free of heart failure through age 70 years and reached 10.6% (95% CI, 9.4%-11.7%) at age 80 years. Lifetime risk of heart failure was higher in men with hypertension than in those without hypertension. Healthy lifestyle habits (normal body weight, not smoking, regular exercise, moderate alcohol intake, consumption of breakfast cereals, and consumption of fruits and vegetables) were individually and jointly associated with a lower lifetime risk of heart failure, with the highest risk in men adhering to none of the 6 lifestyle factors (21.2%; 95% CI, 16.8%-25.6%) and the lowest risk in men adhering to 4 or more desirable factors (10.1%; 95% CI, 7.9%-12.3%).In this cohort of apparently healthy men, adherence to healthy lifestyle factors is associated with a lower lifetime risk of heart failure.
| S-EPMC2742484 | biostudies-literature
Project description:Patients with atrial fibrillation (AF) have an increased risk for the development of heart failure (HF). In this study, we aimed to detect predictors of HF hospitalizations in an unselected AF population.The Basel Atrial Fibrillation Cohort Study is an ongoing observational multicenter cohort study in Switzerland. For this analysis, 1193 patients with documented AF underwent clinical examination, venous blood sampling and resting 12-lead ECG at baseline. Questionnaires about lifestyle and medical history were obtained in person at baseline and during yearly follow-up phone calls. HF hospitalizations were validated by two independent physicians. Cox regression analyses were performed using a forward selection strategy.Overall, 29.8% of all patients were female and mean age was 69 ±12 years. Mean follow-up time was 3.7 ±1.5 years. Hospitalization for HF occurred in 110 patients, corresponding to an incidence of 2.5 events per 100 person years of follow-up. Independent predictors for HF were body mass index (HR 1.40 [95%CI 1.17; 1.66], p = 0.0002), chronic kidney disease (2.27 [1.49; 3.45], p = 0.0001), diabetes mellitus (2.13 [1.41; 3.24], p = 0.0004), QTc interval (1.25 [1.04; 1.49], p = 0.02), brain natriuretic peptide (2.19 [1.73; 2.77], p<0.0001), diastolic blood pressure (0.79 [0.65; 0.96], p = 0.02), history of pulmonary vein isolation or electrical cardioversion (0.54 [0.36; 0.80], p = 0.003) and serum chloride (0.82 [0.70; 0.96], p = 0.02).In this unselected AF population, several traditional cardiovascular risk factors and arrhythmia interventions predicted HF hospitalizations, providing potential opportunities for the implementation of strategies to reduce HF among AF patients.
| S-EPMC5823079 | biostudies-literature
Project description:AimsRisk factors for asymptomatic echocardiographic abnormalities that predict symptomatic heart failure (HF) may provide insight into early mechanisms of HF pathogenesis. We examined risk factors associated with asymptomatic echocardiographic structural, systolic, and diastolic abnormalities, separately and in combination, and interactions between risk factors, in the prospective community-based SCReening Evaluation of the Evolution of New HF (SCREEN-HF) Study cohort of 3190 participants at increased risk of cardiovascular disease.Methods and resultsInclusion criteria were age ≥ 60 years with one or more of hypertension, diabetes, ischaemic heart disease, valvular heart disease, abnormal heart rhythm, cerebrovascular disease, or renal impairment. Exclusion criteria were known HF, ejection fraction < 50%, or >mild valve abnormality. Structural, systolic, and diastolic echocardiographic abnormalities were defined according to the Atherosclerosis Risk in Communities study criteria, and risk factors for asymptomatic structural, systolic, and diastolic abnormalities were identified using logistic regression analysis. In multivariable analysis, increased body mass index (BMI), non-steroidal anti-inflammatory drug therapy, and alcohol intake were risk factors for isolated structural abnormality, whereas male gender, increased heart rate, atrial fibrillation (AF), angiotensin-converting enzyme inhibitor therapy, and obstructive sleep apnoea were associated with a lower risk. Moreover, male gender, smoking, increased systolic blood pressure, and physical inactivity were risk factors for isolated systolic abnormality, whereas increased pulse pressure and antihypertensive therapy were associated with a lower risk. Furthermore, increased age, blood pressure, amino-terminal pro-B-type natriuretic peptide level, and warfarin therapy (associated with AF) were risk factors for isolated diastolic abnormality, whereas increased heart rate and triglyceride level (associated with BMI) were associated with a lower risk. The association of increased heart rate with lower risk of structural and diastolic abnormalities was independent of β-blocker therapy. Interactions between risk factors differed for structural, systolic, and diastolic abnormalities.ConclusionsThe different risk factors for asymptomatic structural, systolic, and diastolic abnormalities that predict symptomatic HF, and the interactions between risk factors, illustrate how these structural, systolic, and diastolic abnormalities represent unique trajectories that lead to symptomatic HF. Improved understanding of these trajectories may assist in the design of HF prevention strategies.
| S-EPMC8788044 | biostudies-literature
Project description:AimsPeople with obesity are at risk for developing heart failure (HF), but little is known about the mechanistic pathways that link obesity with cardiac dysfunction.Methods and resultsWe included 2030 participants from the Swedish Obese Subjects study who received conventional obesity treatment. First-time detection of HF was obtained by cross-checking the study population with the Swedish National Patient Register and the Swedish Cause of Death Register. We also examined if atrial fibrillation and myocardial infarction as time-dependent variables could predict incident HF The mean age of the study cohort was 48.7 years, and 28% were men. The mean body mass index at baseline was 40.1 kg/m2 and remained stable during a median follow-up of 20.1 years. First-time diagnosis of HF occurred in 266 of patients and was related to male sex, increasing age, greater waist-hip ratio, hypertension, higher cholesterol, diabetes mellitus, and elevated free thyroxine in univariable analysis. Estimated glomerular filtration rate was negatively related to HF risk. In multivariable analysis, atrial fibrillation, which is related to HF with preserved ejection fraction (HFpEF), and myocardial infarction, which is linked to HF with reduced ejection fraction (HFrEF), were strongly associated with incident HF with sub-hazard ratios 3.75 (95% confidence interval: 2.72-5.18, P < 0.001) and 3.68 (95% confidence interval: 2.55-5.30, P < 0.001), respectively.ConclusionsBoth atrial fibrillation and myocardial infarction as time-dependent variables were independently and strongly related to incident HF in people with excess body fat, suggesting two main obesity-related mechanistic pathways leading to either HFpEF or HFrEF.
| S-EPMC7835624 | biostudies-literature