Deep Learning to Estimate Left Ventricular Ejection Fraction From Routine Coronary Angiographic Images
Ontology highlight
ABSTRACT:
SUBMITTER:
PROVIDER: S-EPMC11198437 | biostudies-literature | 2023 Oct
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: Not available
| S-EPMC10869567 | biostudies-literature
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.
| S-EPMC8364975 | biostudies-literature
Project description:Background Intracoronary physiologic indexes such as coronary flow reserve (CFR) and left ventricular ejection fraction (LVEF) have been regarded as prognostic indicators in patients with coronary artery disease. The current study evaluated the association between intracoronary physiologic indexes and LVEF and their differential prognostic implications in patients with coronary artery disease. Methods and Results A total of 1889 patients with 2492 vessels with available CFR and LVEF were selected from an international multicenter prospective registry. Baseline physiologic indexes were measured by thermodilution or Doppler methods and LVEF was recorded at the index procedure. The primary outcome was target vessel failure, which was a composite of cardiac death, target vessel myocardial infarction, or clinically driven target vessel revascularization over 5 years of follow-up. Patients with reduced LVEF <50% (162 patients [8.6%], 202 vessels [8.1%]) showed a similar degree of epicardial coronary artery disease but lower CFR values than those with preserved LVEF (2.4±1.2 versus 2.7±1.2, P<0.001), mainly driven by the increased resting coronary flow. Conversely, hyperemic coronary flow, fractional flow reserve, and the degree of microvascular dysfunction were similar between the 2 groups. Reduced CFR (≤2.0) was seen in 613 patients (32.5%) with 771 vessels (30.9%). Reduced CFR was an independent predictor for target vessel failure (hazard ratio, 2.081 [95% CI, 1.385-3.126], P<0.001), regardless of LVEF. Conclusions CFR was lower in patients with reduced LVEF because of increased resting coronary flow. Patients with reduced CFR showed a significantly higher risk of target vessel failure than did those with preserved CFR, regardless of LVEF. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT04485234.
| S-EPMC9375477 | biostudies-literature
Project description:The ejection fraction (EF) is a vital metric for assessing cardiovascular function through cardiac ultrasound. Manual evaluation is time-consuming and exhibits high variability among observers. Deep-learning techniques offer precise and autonomous EF predictions, yet these methods often lack explainability. Accurate heart failure prediction using cardiac ultrasound is challenging due to operator dependency and inconsistent video quality, resulting in significant interobserver variability. To address this, we developed a method integrating convolutional neural networks (CNN) and transformer models for direct EF estimation from ultrasound video scans. This article introduces a Residual Transformer Module (RTM) that extends a 3D ResNet-based network to analyze (2D + t) spatiotemporal cardiac ultrasound video scans. The proposed method, EFNet, utilizes cardiac ultrasound video images for end-to-end EF value prediction. Performance evaluation on the EchoNet-Dynamic dataset yielded a mean absolute error (MAE) of 3.7 and an R2 score of 0.82. Experimental results demonstrate that EFNet outperforms state-of-the-art techniques, providing accurate EF predictions.
| S-EPMC11784862 | biostudies-literature
Project description: Not available
| S-EPMC11536577 | biostudies-literature
Project description:Left ventricular (LV) systolic function is often measured with echocardiography using LV ejection fraction (LVEF) or global longitudinal peak systolic strain (GLPSS). Global wasted work (GWW), global work efficiency (GWE), and first-phase ejection fraction (LVEF-1) are newer LV systolic function indices. We examined these parameters in 45 healthy individuals and 50 patients with stable coronary artery disease (CAD), normal LV contractility, and LVEF > 50%. Compared to healthy individuals, CAD patients had similar LVEF but increased GLPSS and GWW and reduced GWE and LVEF-1. The highest area under the receiver operating characteristic for detecting CAD was found for LVEF-1 (0.84; 95% CI 0.75-0.91; p < 0.0001), and it was significantly larger than for GLPSS (+0.166, p = 0.0082) and LVEF (+0.283, p = 00001). For LVEF-1 < 30%, the odds ratio for the presence of CAD was 22.67 (95% CI 6.47-79.44, p < 0.0001) in the logistic regression adjusted for age, sex, and body mass index. Finding LVEF-1 < 30% in an individual with normal LV myocardial contraction and preserved LVEF strongly suggests the presence of CAD.
| S-EPMC9918081 | biostudies-literature
Project description:BackgroundLimited data exist on the long-term impact of beta-blocker therapy after percutaneous coronary intervention (PCI) in patients with stable coronary artery disease (CAD) and preserved left ventricular ejection fraction (LVEF).ObjectivesThe aim of the study was to evaluate the effects of early beta-blocker initiation vs no initiation following PCI in patients with stable CAD and preserved LVEF.MethodsThis retrospective cohort study employed target trial emulation and incident user design, utilizing the TriNetx database (2009-2024). Early beta-blocker initiation (within days 1 and 7) was compared with no initiation using 1:1 greedy propensity score matching. The outcomes included all-cause mortality, hospitalization for myocardial infarction, heart failure, atrial fibrillation/flutter, stroke, and safety endpoints. Hospitalization for bone fracture and acute appendicitis served as falsification endpoints. In the intention-to-treat analysis, outcomes were analyzed over 5 years using Cox-proportional hazards.ResultsOut of 11,681 matched patients per group, beta-blocker therapy was associated with increased all-cause mortality (HR: 1.11 [95% CI: 1.09-1.18]). No significant differences were found in hospitalization for myocardial infarction (HR: 1.03 [95% CI: 0.97-1.09]), stroke (HR: 0.98 [95% CI: 0.91-1.05]), heart failure (HR: 0.99 [95% CI: 0.95-1.03]), and atrial fibrillation/flutter (HR: 0.97 [95% CI: 0.93-1.01]). Hospitalization for hypotension was higher with beta-blockers (HR: 1.10 [95% CI: 1.06-1.14]). Hospitalization for bone fracture (HR: 1.02 [95% CI: 0.85-1.22]) and acute appendicitis (HR: 1.17 [95% CI: 0.95-1.45]) showed no significant associations. Several sensitivity analyses showed consistent results.ConclusionsEarly beta-blocker initiation after PCI for stable CAD with preserved LVEF was associated with higher mortality, with no impact on cardiovascular events.
| S-EPMC11787421 | biostudies-literature
Project description:PurposeRecently, a "U" hazard ratio curve between resting left ventricular ejection fraction (LVEF) and prognosis has been observed in patients referred for routine clinical echocardiograms. The present study sought to explore whether a similar "U" curve existed between resting LVEF and coronary flow reserve (CFR) in patients without severe cardiovascular disease (CVD) and whether impaired CFR played a role in the adverse outcome of patients with supra-normal LVEF (snLVEF, LVEF ≥ 65%).MethodsTwo hundred ten consecutive patients (mean age 52.3 ± 9.3 years, 104 women) without severe CVD underwent clinically indicated rest/dipyridamole stress electrocardiography (ECG)-gated 13 N-ammonia positron emission tomography/computed tomography (PET/CT). Major adverse cardiac events (MACE) were followed up for 27.3 ± 9.5 months, including heart failure, late revascularization, re-hospitalization, and re-coronary angiography for any cardiac reason. Clinical characteristics, corrected CFR (cCFR), and MACE were compared among the three groups categorized by resting LVEF detected by PET/CT. Dose-response analyses using restricted cubic spline (RCS) functions, multivariate logistic regression, and Kaplan-Meier survival analysis were conducted to evaluate the relationship between resting LVEF and CFR/outcome.ResultsAn inverted "U" curve existed between resting LVEF and cCFR (p = 0.06). Both patients with snLVEF (n = 38) and with reduced LVEF (rLVEF, LVEF < 55%) (n = 66) displayed a higher incidence of reduced cCFR than those with normal LVEF (nLVEF, 55% ≤ LVEF < 65%) (n = 106) (57.9% vs 54.5% vs 34.3%, p < 0.01, respectively). Both snLVEF (p < 0.01) and rLVEF (p < 0.05) remained independent predictors for reduced cCFR after multivariable adjustment. Patients with snLVEF encountered more MACE than those with nLVEF (10.5% vs 0.9%, log-rank p = 0.01).ConclusionsPatients with snLVEF are prone to impaired cCFR, which may be related to the adverse prognosis. Further investigations are warranted to explore its underlying pathological mechanism and clinical significance.
| S-EPMC9165269 | biostudies-literature
Project description:BackgroundStatins taken for cardiovascular indications by patients with breast cancer and lymphoma during doxorubicin treatment may attenuate left ventricular ejection fraction (LVEF) decline, but the effect of statins on LVEF among patients with no cardiovascular indications is unknown.MethodsA double-blind, placebo-controlled, 24-month randomized trial of 40 mg of atorvastatin per day administered to patients with breast cancer and lymphoma receiving doxorubicin was conducted within the National Cancer Institute Community Oncology Research Program across 31 sites in the United States. At pretreatment and then 6 and 24 months after initiating doxorubicin, we assessed left ventricular (LV) volumes, strain, mass, and LVEF through cardiac magnetic resonance imaging, along with cognitive function and serum markers of inflammation. The primary outcome was the difference in 24-month LVEF between placebo and treatment groups, adjusted for pretreatment LVEF.ResultsA total of 279 participants were enrolled in the trial. Participants had a mean (±SD) age of 49±12 years; 92% were women; and 83% were White. The mean (±SD) LVEF values were 61.7±5.5% before treatment and 57.4±6.8% at 24 months in the placebo group and 62.6±6.4% before treatment and 57.7±5.6% at 24 months in the atorvastatin group. On the basis of a multiple imputed data set for missing data and adjusted for each individual's pretreatment LVEF, 24-month declines in LVEF averaged 3.3±0.6 percentage points and 3.2±0.7 percentage points, for those randomly assigned to placebo versus statins, respectively (P=0.93). Across both treatment arms, similar percentages of individuals experienced changes of more than 10 percentage points in LVEF, LV strain, LV mass, cognition, and inflammation biomarkers, including among those with greater than 90% drug compliance.ConclusionsIn patients with breast cancer and lymphoma with no existing indication for statin therapy, prospective statin administration did not affect LVEF declines 2 years after doxorubicin. (Funded by the National Institutes of Health; ClinicalTrials.gov number, NCT01988571.).
| S-EPMC9997095 | biostudies-literature
Project description:ObjectivesThis study sought to examine the association of a borderline left ventricular ejection fraction (LVEF) of 50% to 55% with cardiovascular morbidity and mortality in a community-based cohort.BackgroundGuidelines stipulate a LVEF >55% as normal, but the optimal threshold, if any, remains uncertain. The prognosis of a "borderline" LVEF, 50% to 55%, is unknown.MethodsThis study evaluated Framingham Heart Study participants who underwent echocardiography between 1979 and 2008 (n = 10,270 person-observations, mean age 60 years, 57% women). Using pooled data with up to 12 years of follow-up and multivariable Cox regression, we evaluated the associations of borderline LVEF and continuous LVEF with the risk of developing a composite outcome (heart failure [HF] or death; primary outcome) and incident HF (secondary outcome).ResultsDuring follow-up (median 7.9 years), HF developed in 355 participants, and 1,070 died. Among participants with an LVEF of 50% to 55% (prevalence 3.5%), rates of the composite outcome and HF were 0.24 and 0.13 per 10 years of follow-up, respectively, versus 0.16 and 0.05 in participants having a normal LVEF. In multivariable-adjusted analyses, LVEF of 50% to 55% was associated with increased risk of the composite outcome (hazard ratio [HR]: 1.37; 95% confidence interval [CI]: 1.05 to 1.80) and HF (HR: 2.15; 95% CI: 1.41 to 3.28). There was a linear inverse relationship of continuous LVEF with the composite outcome (HR per 5 LVEF% decrement: 1.12; 95% CI: 1.07 to 1.16) and HF (HR per 5 LVEF% decrement: 1.23; 95% CI: 1.15 to 1.32).ConclusionsPersons with an LVEF of 50% to 55% in the community have greater risk for morbidity and mortality relative to persons with an LVEF >55%. Additional studies are warranted to elucidate the optimal management of these individuals.
| S-EPMC4932891 | biostudies-literature