Dataset Information

Deep learning of ECG waveforms for diagnosis of heart failure with a reduced left ventricular ejection fraction

ABSTRACT: The performance and clinical implications of the deep learning aided algorithm using electrocardiogram of heart failure (HF) with reduced ejection fraction (DeepECG-HFrEF) were evaluated in patients with acute HF. The DeepECG-HFrEF algorithm was trained to identify left ventricular systolic dysfunction (LVSD), defined by an ejection fraction (EF) < 40%. Symptomatic HF patients admitted at Seoul National University Hospital between 2011 and 2014 were included. The performance of DeepECG-HFrEF was determined using the area under the receiver operating characteristic curve (AUC) values. The 5-year mortality according to DeepECG-HFrEF results was analyzed using the Kaplan–Meier method. A total of 690 patients contributing 18,449 ECGs were included with final 1291 ECGs eligible for the study (mean age 67.8 ± 14.4 years; men, 56%). HFrEF (+) identified an EF < 40% and HFrEF (−) identified EF ≥ 40%. The AUC value was 0.844 for identifying HFrEF among patients with acute symptomatic HF. Those classified as HFrEF (+) showed lower survival rates than HFrEF (−) (log-rank p < 0.001). The DeepECG-HFrEF algorithm can discriminate HFrEF in a real-world HF cohort with acceptable performance. HFrEF (+) was associated with higher mortality rates. The DeepECG-HFrEF algorithm may help in identification of LVSD and of patients at risk of worse survival in resource-limited settings.

SUBMITTER: Choi J

PROVIDER: S-EPMC9392508 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Aims: Evidence-based guidelines for heart failure management depend mainly on current left ventricular ejection fraction (LVEF). However, fewer studies have examined the impact of prior LVEF. Patients may enter the heart failure with midrange ejection fraction (HFmrEF) category when heart failure with preserved ejection fraction (HFpEF) deteriorates or heart failure with reduced ejection fraction (HFrEF) improves. In this study, we examined the association between change in LVEF and adverse outcomes. Methods: HFmrEF patients with at least two or more echocardiograms 3 months apart at the First Affiliated Hospital of Dalian Medical University between September 1, 2015 and November 30, 2019 were identified. According to the prior LVEF, the subjects were divided into improved group (prior LVEF < 40%), stable group (prior LVEF between 40 and 50%), and deteriorated group (prior LVEF ≥ 50%). The primary outcomes were cardiovascular death, all-cause mortality, hospitalization for worsening heart failure, and composite event of all-cause mortality or all-cause hospitalization. Results: A total of 1,168 HFmrEF patients (67.04% male, mean age 63.60 ± 12.18 years) were included. The percentages of improved, stable, and deteriorated group were 310 (26.54%), 334 (28.60%), and 524 (44.86%), respectively. After a period of follow-up, 208 patients (17.81%) died and 500 patients met the composite endpoint. The rates of all-cause mortality were 35 (11.29%), 55 (16.47%), and 118 (22.52%), and the composite outcome was 102 (32.90%), 145 (43.41%), and 253 (48.28%) for the improved, stable, and deteriorated groups, respectively. Cox regression analysis showed that the deterioration group had higher risk of cardiovascular death (HR: 1.707, 95% CI: 1.064-2.739, P = 0.027), all-cause death (HR 1.948, 95% CI 1.335-2.840, P = 0.001), and composite outcome (HR 1.379, 95% CI 1.096-1.736, P = 0.006) compared to the improvement group. The association still remained significant after fully adjusted for both all-cause mortality (HR = 1.899, 95% CI 1.247-2.893, P = 0.003) and composite outcome (HR: 1.324, 95% CI: 1.020-1.718, P = 0.035). Conclusion: HFmrEF patients are heterogeneous with three different subsets identified, each with different outcomes. Strategies for managing HFmrEF should include previously measured LVEF to allow stratification based on direction changes in LVEF to better optimize treatment.

Project description:AimsNeuregulin1-β (NRG1-β) is released from microvascular endothelial cells in response to inflammation with compensatory cardioprotective effects. Circulating NRG1-β is elevated in heart failure (HF) with reduced ejection fraction (HFrEF) but not studied in HF with preserved EF (HFpEF).Methods and resultsCirculating NRG1-β was quantified in 86 stable patients with HFpEF (EF ≥45% and N-terminal pro-brain natriuretic peptide >300 ng/L), in 86 patients with HFrEF prior to and after left ventricular assist device (LVAD) and/or heart transplantation (HTx) and in 21 healthy controls. Association between NRG1-β and the composite outcome of all-cause mortality/HF hospitalization in HFpEF and all-cause mortality/HTx/LVAD implantation in HFrEF with and without ischaemia assessed as macrovascular coronary artery disease was assessed. In HFpEF, median (25th-75th percentile) NRG1-β was 6.5 (2.1-11.3) ng/mL; in HFrEF, 3.6 (2.1-7.6) ng/mL (P = 0.035); after LVAD, 1.7 (0.9-3.6) ng/mL; after HTx 2.1 (1.4-3.6) ng/mL (overall P < 0.001); and in controls, 29.0 (23.1-34.3) ng/mL (P = 0.001). In HFrEF, higher NRG1-β was associated with worse outcomes (hazard ratio per log increase 1.45, 95% confidence interval 1.04-2.03, P = 0.029), regardless of ischaemia. In HFpEF, the association of NRG1-β with outcomes was modified by ischaemia (log-rank P = 0.020; Pinteraction = 0.553) such that only in ischaemic patients, higher NRG1-β was related to worse outcomes. In contrast, in patients without ischaemia, higher NRG1-β trended towards better outcomes (hazard ratio 0.71, 95% confidence interval 0.48-1.05, P = 0.085).ConclusionsNeuregulin1-β was reduced in HFpEF and further reduced in HFrEF. The opposing relationships of NRG1-β with outcomes in non-ischaemic HFpEF compared with HFrEF and ischaemic HFpEF may indicate compensatory increases of cardioprotective NRG1-β from microvascular endothelial dysfunction in the former (non-ischaemic HFpEF), but this compensatory mechanism is overwhelmed by the presence of ischaemia in the latter (HFrEF and ischaemic HFpEF).

Project description:AimsTwo key echocardiographic parameters that are currently used to diagnose heart failure (HF) with preserved ejection fraction (HFpEF) are left atrial volume index (LAVi) and left ventricular mass index (LVMi). We investigated whether patients' characteristics, biomarkers, and co-morbidities are associated with these parameters and whether the relationships differ between patients with HFpEF or HF with reduced ejection fraction (HFrEF).MethodsWe consecutively enrolled 831 outpatients with typical signs and symptoms of HF and elevated N-terminal prohormone of brain natriuretic peptide (NT-proBNP) levels and categorized patients based upon left ventricular ejection fraction (LVEF): LVEF < 40% (HFrEF), LVEF between 40% and 50% (HF with mid-range ejection fraction), and LVEF ≥ 50% (HFpEF). The study includes consecutively enrolled HF patients from an HF outpatient clinic at a tertiary medical centre in the Netherlands. All patients underwent baseline characterization, laboratory measurements, and echocardiography.ResultsFour hundred sixty-nine patients had HFrEF, 189 HF with mid-range ejection fraction, and 173 HFpEF. The patients with HFrEF were rather male [HFrEF: 323 (69%); HFpEF: 80 (46%); P < 0.001], and the age was comparable (HFrEF 67 ± 13; HFpEF 70 ± 14; P = 0.069). In HFpEF, more patients had hypertension [190 (40.5%); 114 (65.9%); P < 0.001], higher body mass indices (27 ± 8; 30 ± 7; P < 0.001), and atrial fibrillation [194 (41.4); 86 (49.7); P = 0.029]. The correlation analyses showed that in HFrEF patients, LAVi was significantly associated with age (β 0.293; P < 0.001), male gender (β 0.104; P = 0.042), body mass index (β -0160; P = 0.002), diastolic blood pressure (β -0.136; P < 0.001), New York Heart Association (β 0.174; P = 0.001), atrial fibrillation (β 0.381; P < 0.001), galectin 3 (β 0.230; P < 0.001), NT-proBNP (β 0.183; P < 0.001), estimated glomerular filtration rate (β -0.205; P < 0.001), LVEF (β -0.173; P = 0.001), and LVMi (β 0.337; P < 0.001). In HFpEF patients, only age (β 0.326; P < 0.001), atrial fibrillation (β 0.386; P < 0.001), NT-proBNP (β 0.176; P = 0.036), and LVMi (β 0.213; P = 0.013) were associated with LAVi.ConclusionsAlthough LVMi and LAVi are hallmark parameters to diagnose HFpEF, they only correlate with a few characteristics of HF and mainly with atrial fibrillation. In contrast, in HFrEF patients, LAVi relates strongly to several other HF parameters. These findings underscore the complexity in visualizing the pathophysiology of HFpEF and question the relation between cardiac structural remodeling and the impact of co-morbidities.

Dataset Information

Deep learning of ECG waveforms for diagnosis of heart failure with a reduced left ventricular ejection fraction

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets