Dataset Information

Machine learning models in heart failure with mildly reduced ejection fraction patients.

ABSTRACT:

Objective

Heart failure with mildly reduced ejection fraction (HFmrEF) has been recently recognized as a unique phenotype of heart failure (HF) in current practical guideline. However, risk stratification models for mortality and HF re-hospitalization are still lacking. This study aimed to develop and validate a novel machine learning (ML)-derived model to predict the risk of mortality and re-hospitalization for HFmrEF patients.

Methods

We assessed the risks of mortality and HF re-hospitalization in HFmrEF (45-49%) patients enrolled in the TOPCAT trial. Eight ML-based models were constructed, including 72 candidate variables. The Harrell concordance index (C-index) and DeLong test were used to assess discrimination and the improvement in discrimination between models, respectively. Calibration of the HF risk prediction model was plotted to obtain bias-corrected estimates of predicted versus observed values.

Results

Least absolute shrinkage and selection operator (LASSO) Cox regression was the best-performing model for 1- and 6-year mortality, with a highest C-indices at 0.83 (95% CI: 0.68-0.94) over a maximum of 6 years of follow-up and 0.77 (95% CI: 0.64-0.89) for the 1-year follow-up. The random forest (RF) showed the best discrimination for HF re-hospitalization, scoring 0.80 (95% CI: 0.66-0.94) and 0.85 (95% CI: 0.71-0.99) at the 6- and 1-year follow-ups, respectively. For risk assessment analysis, Kansas City Cardiomyopathy Questionnaire (KCCQ) subscale scores were the most important predictor of readmission outcome in the HFmrEF patients.

Conclusion

ML-based models outperformed traditional models at predicting mortality and re-hospitalization in patients with HFmrEF. The results of the risk assessment showed that KCCQ score should be paid increasing attention to in the management of HFmrEF patients.

SUBMITTER: Zhao H

PROVIDER: S-EPMC9748556 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning models in heart failure with mildly reduced ejection fraction patients.

Zhao Hengli H Li Peixin P Zhong Guoheng G Xie Kaiji K Zhou Haobin H Ning Yunshan Y Xu Dingli D Zeng Qingchun Q

Frontiers in cardiovascular medicine 20221130

<h4>Objective</h4>Heart failure with mildly reduced ejection fraction (HFmrEF) has been recently recognized as a unique phenotype of heart failure (HF) in current practical guideline. However, risk stratification models for mortality and HF re-hospitalization are still lacking. This study aimed to develop and validate a novel machine learning (ML)-derived model to predict the risk of mortality and re-hospitalization for HFmrEF patients.<h4>Methods</h4>We assessed the risks of mortality and HF re ...[more]

PMID: 36531735

Similar Datasets

Project description:AimsHeart failure with mildly reduced ejection fraction (HFmrEF) is associated with a favourable prognosis compared with heart failure (HF) with reduced ejection fraction (EF). We assessed whether left ventricular ejection fraction (LVEF) trajectory can be used to identify groups of patients with HFmrEF who have different clinical outcomes in a large retrospective study of patients with serial imaging.Methods and resultsPatients with HF and ≥2 echocardiograms performed ≥6 months apart were included if the LVEF measured 40-49% on the second study. Patients were classified as HFmrEF-Increasing if LVEF had increased ≥10% (n = 450), HFmrEF-Decreasing if LVEF had decreased ≥10% (n = 512), or HFmrEF-Stable if they did not meet other criteria (n = 389). The primary outcome was all-cause mortality or cardiovascular hospitalization after the second echocardiogram. Associations with time to first event were assessed with multivariable Cox analyses adjusted for age, co-morbidities, and medications. In total, 1351 patients with HFmrEF (median age 74, 64.2% male) were included with 28.8% exhibiting stable LVEF. During median follow-up of 15.3 months, the composite outcome occurred in 811 patients. During follow-up, patients with HFmrEF-Increasing were less likely to experience the primary outcome [adjusted hazard ratio (HR) 0.72, 95% confidence interval (CI) 0.60-0.88, P < 0.001] compared with HFmrEF-Stable. Patients with HFmrEF-Decreasing were more likely to experience the composite outcome in unadjusted analyses (unadjusted HR 1.19, 95% CI 1.01-1.40, P = 0.040) but not adjusted analyses (adjusted HR 1.16, 95% CI 0.98-1.37, P = 0.092). Associations with death or HF hospitalizations were similar (HFmrEF-Increasing: adjusted HR 0.72, 95% CI 0.59-0.88, P = 0.005; HFmrEF-Decreasing: adjusted HR 1.20, 95% CI 1.01-1.44, P = 0.044). Patients with HFmrEF-Decreasing had a similar risk of the composite outcome as patients with HF with reduced EF (adjusted HR 1.03, 95% CI 0.89-1.20, P = 0.670). Patients with HFmrEF-Increasing were less likely to experience the composite outcome compared with patients with HF with preserved EF (adjusted HR 0.73, 95% CI 0.62-0.87, P < 0.001).ConclusionsAmongst patients with HFmrEF, those exhibiting positive LVEF trajectory were less likely to experience adverse outcomes after correcting for important confounders including medical therapy. Categorizing HFmrEF patients based on LVEF trajectory provides meaningful clinical information and may assist clinicians with management decisions.

Project description:BackgroundGuideline recommendations for the treatment of heart failure with mildly reduced ejection fraction (HFmrEF) derive from small subgroups in post-hoc analyses of randomized trials.ObjectivesWe investigated predictors of renin-angiotensin system inhibitors/angiotensin receptor neprilysin inhibitors (RASI/ARNI) and beta-blockers use, and the associations between these medications and mortality/morbidity in a large real-world cohort with HFmrEF.Methods and resultsPatients with HFmrEF (EF 40-49%) from the Swedish HF Registry were included. The associations between medications and cardiovascular (CV) mortality/HF hospitalization (HFH), and all-cause mortality were assessed through Cox regressions in a 1:1 propensity score-matched cohort. A positive control analysis was performed in patients with EF < 40%, while a negative control outcome analysis had cancer-related hospitalization as endpoint. Of 12 421 patients with HFmrEF, 84% received RASI/ARNI and 88% beta-blockers. Shared-independent predictors of RASI/ARNI and beta-blockers use were younger age, being an outpatient, follow-up in specialty care, and hypertension. In the matched cohorts, use of both RASI/ARNI and beta-blocker use was separately associated with lower risk of CV mortality/HFH [hazard ratio (HR) = 0.90, 95% confidence interval (CI): 0.83-0.98 and HR = 0.82, 95% CI: 0.74-0.90, respectively] and of all-cause mortality (HR = 0.75, 95% CI: 0.69-0.81 and HR = 0.79, 95% CI: 0.72-0.87, respectively). Results were consistent at the positive control analysis, and there were no associations between treatment use and the negative control outcome.ConclusionsRASI/ARNI and beta-blockers were extensively used in this large real-world cohort with HFmrEF. Their use was safe since associated with lower mortality and morbidity. Our findings confirm the real-world evidence from previous post-hoc analyses of trials, and represent a further call for implementing guideline recommendations.

Project description:AimsWhereas up to about half of patients with heart failure with reduced ejection fraction (HFrEF) report no or only mild symptoms and are considered as clinically stable, the progressive nature of HFrEF, often silent, renders clinical stability a misleading situation, especially if disease progression is unrecognized. We highlight the challenges in the definition of clinical stability and mild symptomatic status in HFrEF, outline clinical characteristics and available diagnostic tools, and discuss evidence and gaps in the current guidelines for the management of these patients.Methods and resultsThis is a state-of-the-art review that focuses on clinical, diagnostic, and therapeutic aspects in mildly symptomatic HFrEF patients; summarizes the challenges; and proposes directions for future research in this group of patients. The New York Heart Association classification has been widely used as a measure of prognosis in HFrEF, but it lacks objectivity and reproducibility in terms of symptoms assessment. The definition of clinical stability as described in current guidelines is vague and may often lead to underdiagnosis of disease progression in patients who appear to be 'stable' but in fact are at an increased risk of clinical worsening, hospitalization, or death. Although an increasing number of clinical trials proved that the efficacy of HFrEF therapies was unrelated to the symptomatic status of patients and led to their implementation early in the course of the disease, clinical inertia in terms of under-prescription or underdosing of guideline-recommended medications in mildly symptomatic HFrEF patients is still a challenging issue to deal with.ConclusionsMildly symptomatic status in a patient with HFrEF is very frequent; it should not be ignored and should not be regarded as an index of disease stability. The application of risk scores designed to predict mortality and mode of death should be engaged among mildly symptomatic patients, not only to identify the most suitable HF candidates for cardioverter defibrillator implantation, but also to identify patients who might benefit from early intensification of medical treatment before the implementation of more interventional approaches.

Project description:IntroductionData on heart failure (HF) with mildly reduced ejection fraction (HFmrEF) is still emerging, especially in Asian populations. This study aims to compare the clinical characteristics and outcomes of Asian HFmrEF patients with those of HF patients with reduced ejection fraction (HFrEF) and preserved ejection fraction (HFpEF).MethodsPatients admitted nationally for HF between 2008 and 2014 were included in the study. They were categorised according to ejection fraction (EF). Patients with EF <40%, EF 40%-49% and EF ≥50% were categorised into the following groups: HFrEF, HFmrEF and HFpEF, respectively. All patients were followed up till December 2016. Primary outcome was all-cause mortality. Secondary outcomes included cardiovascular death and/or HF rehospitalisations.ResultsA total of 16,493 patients were included in the study - HFrEF, n = 7,341 (44.5%); HFmrEF, n = 2,272 (13.8%); and HFpEF n = 6,880 (41.7%). HFmrEF patients were more likely to be gender neutral, of mid-range age and have concomitant diabetes mellitus, hyperlipidaemia, peripheral vascular disease and coronary artery disease ( P < 0.001). The two-year overall mortality rates for HFrEF, HFmrEF and HFpEF were 32.9%, 31.8% and 29.1%, respectively. HFmrEF patients had a significantly lower overall mortality rate compared to HFrEF patients (adjusted hazard ratio [HR] 0.89, 95% confidence interval [CI] 0.83-0.95; P < 0.001) and a significantly higher overall mortality rate (adjusted HR 1.25, 95% CI 1.17-1.33; P < 0.001) compared to HFpEF patients. This was similarly seen with cardiovascular mortality and HF hospitalisations, with the exception of similar HF hospitalisations between HFmrEF and HFpEF patients.ConclusionHFmrEF patients account for a significant burden of patients with HF. HFmrEF represents a distinct HF phenotype with high atherosclerotic burden and clinical outcomes saddled in between those of HFrEF and HFpEF. Further therapeutic studies to guide management of this challenging group of patients are warranted.

Dataset Information

Machine learning models in heart failure with mildly reduced ejection fraction patients.

Objective

Methods

Results

Conclusion

Publications

Machine learning models in heart failure with mildly reduced ejection fraction patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets