Deep learning-based automated left ventricular ejection fraction assessment using 2D echocardiography

2021 ◽  
Author(s):  
Xin Liu ◽  
Yiting Fan ◽  
Shuang Li ◽  
Meixiang Chen ◽  
Ming Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ejection Fraction ◽  
High Performance ◽  
Diagnostic Performance ◽  
Heart Diseases ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
2D Echocardiography ◽  
The Impact

Background. Deep-learning (DL) has been applied for automatic left ventricle (LV) ejection fraction (EF) measurement, but the diagnostic performance was rarely evaluated for various phenotypes of heart disease. This study aims to evaluate a new DL algorithm for automated LVEF measurement using two-dimensional echocardiography (2DE) images collected from 3 centers. The impact of 3 ultrasound machines and 3 phenotypes of heart diseases on the automatic LVEF measurement was evaluated. Methods and Results. Using 36890 frames of 2DE from 340 patients, we developed a DL algorithm based on U-Net (DPS-Net) and the biplane Simpson's method was applied for LVEF calculation. Results showed a high performance in LV segmentation and LVEF measurement across phenotypes and echo systems by using DPS-Net. Good performance was obtained for LV segmentation when DPS-Net was tested on the CAMUS dataset (Dice coefficient of 0.932 and 0.928 for ED and ES). Better performance of LV segmentation in study-wise evaluation was observed by comparing the DPS-Net v2 to the EchoNet-dynamic algorithm (p = 0.008). DPS-Net was associated with high correlations and good agreements for the LVEF measurement. High diagnostic performance was obtained that the area under receiver operator characteristic curve was 0.974, 0.948, 0.968 and 0.972 for normal hearts and disease phenotypes including atrial fibrillation, hypertrophic cardiomyopathy, dilated cardiomyopathy, respectively. Conclusion. High performance was obtained by using DPS-Net in LV detection and LVEF measurement for heart failure with several phenotypes. High performance was observed in a large-scale dataset, suggesting that the DPS-Net was highly adaptive across different echocardiographic systems.

scholarly journals Clinical Outcomes in Patients with Ischemic versus Non-Ischemic Cardiomyopathy after Angiotensin-Neprilysin Inhibition Therapy

2021 ◽  
Vol 10 (21) ◽  
pp. 4989
Author(s):  
Mohammad Abumayyaleh ◽  
Christina Pilsinger ◽  
Ibrahim El-Battrawy ◽  
Marvin Kummer ◽  
Jürgen Kuschyk ◽  
...  
Keyword(s):  
Heart Failure ◽  
Ejection Fraction ◽  
Ischemic Cardiomyopathy ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Ventricular Tachyarrhythmias ◽  
Ventricular Ejection Fraction ◽  
One Year ◽  
The Impact

Background: The angiotensin receptor-neprilysin inhibitor (ARNI) decreases cardiovascular mortality in patients with chronic heart failure with a reduced ejection fraction (HFrEF). Data regarding the impact of ARNI on the outcome in HFrEF patients according to heart failure etiology are limited. Methods and results: One hundred twenty-one consecutive patients with HFrEF from the years 2016 to 2017 were included at the Medical Centre Mannheim Heidelberg University and treated with ARNI according to the current guidelines. Left ventricular ejection fraction (LVEF) was numerically improved during the treatment with ARNI in both patient groups, that with ischemic cardiomyopathy (n = 61) (ICMP), and that with non-ischemic cardiomyopathy (n = 60) (NICMP); p = 0.25. Consistent with this data, the NT-proBNP decreased in both groups, more commonly in the NICMP patient group. In addition, the glomerular filtration rate (GFR) and creatinine changed before and after the treatment with ARNI in both groups. In a one-year follow-up, the rate of ventricular tachyarrhythmias (ventricular tachycardia and ventricular fibrillation) tended to be higher in the ICMP group compared with the NICMP group (ICMP 38.71% vs. NICMP 17.24%; p = 0.07). The rate of one-year all-cause mortality was similar in both groups (ICMP 6.5% vs. NICMP 6.6%; log-rank = 0.9947). Conclusions: This study shows that, although the treatment with ARNI improves the LVEF in ICMP and NICMP patients, the risk of ventricular tachyarrhythmias remains higher in ICMP patients in comparison with NICMP patients. Renal function is improved in the NICMP group after the treatment. Long-term mortality is similar over a one-year follow-up.

scholarly journals Profile of Hospitalized Hypertensives with Preserved and Reduced Left Ventricular Ejection Fraction in Nigeria

2019 ◽  
Vol 14 ◽  
Author(s):  
Akinsanya Daniel Olusegun-Joseph ◽  
Kamilu M Karaye ◽  
Adeseye A Akintunde ◽  
Bolanle O Okunowo ◽  
Oladimeji G Opadijo ◽  
...  
Keyword(s):  
Heart Failure ◽  
Left Ventricular Ejection Fraction ◽  
Ejection Fraction ◽  
Left Ventricular ◽  
Ventricular Ejection ◽  
Teaching Hospitals ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
Hypertensive Patients ◽  
The Impact

Introduction The impact of preserved and reduced left ventricular ejection fraction (LVEF) has been well studied in heart failure, but not in hypertension. We aimed to highlight the prevalence, clinical characteristics, comorbidities and outcomes of hospitalized hypertensives with preserved and reduced LVEF from three teaching hospitals in Nigeria. Methods: This is a retrospective study of hypertensives admitted in 2013 in three teaching hospitals in Lagos, Kano and Ogbomosho, who had echocardiography done while on admission. Medical records and echocardiography parameters of the patients were retrieved and analyzed. Results: 54 admitted hypertensive patients who had echocardiography were recruited, of which 30 (55.6%) had reduced left ventricular ejection fraction (RLVEF), defined as ejection fraction <50%; while 24 (44.4%) had preserved left ventricular ejection fraction (PLVEF). There were 37(61.5%) females and 17 (31.5%) males. Of the male patients 64.7% had RLVEF, while 35.3% had PLVEF. 19(51.4%) of females had RLVEF, while 48.6% had PLVEF. Mean age of patients with PLVEF was 58.83±12.09 vs 54.83± 18.78 of RLVEF; p-0.19. Commonest comorbidity was Heart failure (HF) followed by stroke (found among 59.3% and 27.8% of patients respectively). RLVEF was significantly commoner than PLVEF in HF patients (68.8% vs 31.3%; p- 0.019); no significant difference in stroke patients (46.7% vs 53.3%; p-0.44). Mortality occurred in 1 (1.85%) patient who had RLVEF.         Conclusion: RLVEF was more common than PLVEF among admitted hypertensive patients; they also have more comorbidities. In-hospital mortality is, however, very low in both groups.

scholarly journals Cardiotoxic Effect of Modern Anthracycline Dosing on Left Ventricular Ejection Fraction: A Systematic Review and Meta‐Analysis of Placebo Arms From Randomized Controlled Trials

2021 ◽  
Vol 10 (6) ◽  
Author(s):  
Prajith Jeyaprakash ◽  
Sukhmandeep Sangha ◽  
Katherine Ellenberger ◽  
Shanthosh Sivapathan ◽  
Faraz Pathan ◽  
...  
Keyword(s):  
Left Ventricular Ejection Fraction ◽  
Ejection Fraction ◽  
Left Ventricular ◽  
Ventricular Ejection ◽  
Left Ventricular Ejection ◽  
Cancer Type ◽  
Solid Organ ◽  
Ventricular Ejection Fraction ◽  
The Impact ◽  
Anthracycline Dose

Background Anthracyclines are a key chemotherapeutic agent used against hematological and solid organ malignancies. However, their benefits in cancer survival are limited by cumulative, dose‐related cardiotoxicity. The impact of anthracyclines on left ventricular ejection fraction (LVEF), in the era of modern chemotherapy regimens, remains unclear. Methods and Results Three databases (CENTRAL, MEDLINE, and SCOPUS) were systematically searched for randomized trials evaluating cardioprotective agents against placebo, in preventing cardiotoxicity. Echocardiography or magnetic resonance measured LVEF pre‐ and post‐anthracycline‐based chemotherapy was abstracted from placebo trial arms. The key terms included “anthracycline,” “cardiotoxicity” and “randomized.” A doxorubicin equivalent anthracycline dose metric was calculated to compare different anthracyclines. A random‐effects model was used to pool mean difference in LVEF after anthracycline. Meta‐regressions were calculated to identify variation sources. We included 660 patients from 19 trials. The weighted mean baseline LVEF across studies was 62.6%, and follow‐up LVEF assessment was performed at 6 months. The pooled mean decline in LVEF among placebo arms was 5.4% (95% CI, 3.5%–7.3%) with a doxorubicin equivalent anthracycline dose of 385 mg/m 2 . Meta‐regression analysis showed no significant difference in LVEF against doxorubicin equivalent anthracycline dose as continuous ( P =0.29) or against published cut‐offs for cardiotoxicity (250 mg/m 2 , P =0.21; 360 mg/m 2 , P =0.40; and 400 mg/m 2 , P =0.66). The differences in mean LVEF were not associated with sex, adjunct chemotherapy, or cancer type. Conclusions The magnitude of LVEF impairment post‐anthracycline therapy appears less than previously described with modern dosing regimens. This may improve the accuracy of power calculation for future clinical trials assessing the role of cardioprotective therapy.

Comparison of the prognosis and outcome of heart failure with reduced ejection fraction patients treated with sacubitril/valsartan according to age

2021 ◽  
Author(s):  
Mohammad Abumayyaleh ◽  
Ibrahim El-Battrawy ◽  
Marvin Kummer ◽  
Christina Pilsinger ◽  
Katherine Sattler ◽  
...  
Keyword(s):  
Heart Failure ◽  
Chronic Heart Failure ◽  
Ejection Fraction ◽  
Older Patients ◽  
Left Ventricular ◽  
Adult Patients ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
Reduced Ejection Fraction ◽  
The Impact

The treatment with sacubitril/valsartan in patients suffering from chronic heart failure with reduced ejection fraction increases left ventricular ejection fraction and decreases the risk of sudden cardiac death. We conducted a retrospective analysis regarding the impact of age differences on the treatment outcome of sacubitril/valsartan in patients with chronic heart failure with reduced ejection fraction. Patients were defined as adults if ≤65 years (n = 51) and older if >65 years of age (n = 76). The incidence of ventricular arrhythmias at 1-year follow-up was comparable in both groups (30.8 vs 26.5%; p = 0.71). The mortality rate in adult patients is significantly lower as compared with older patients (2 vs 14.5%; log-rank = 0.04). Older patients may suffer remarkably more side effects than adult patients (21.1 vs 11.8%; p = 0.03).

scholarly journals The Impact of Obesity on the Left Ventricular Ejection Fraction Using Echocardiography

2014 ◽  
Vol 04 (04) ◽  
pp. 172-177 ◽  
Author(s):  
Bahaaedin A. Elkhader ◽  
Alsafi A. Abdulla ◽  
Mohammed A. Ali Omer ◽  
Maram A. Fagiri ◽  
Mustafa Z. Mahmoud
Keyword(s):  
Left Ventricular Ejection Fraction ◽  
Ejection Fraction ◽  
Left Ventricular ◽  
Ventricular Ejection ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
The Impact

scholarly journals Are we aiming for different metabolic targets in heart failure patients?

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
J Brito ◽  
J.R Agostinho ◽  
C Duarte ◽  
B Silva ◽  
S Pereira ◽  
...  
Keyword(s):  
Heart Failure ◽  
High Risk ◽  
Ejection Fraction ◽  
Cardiovascular Events ◽  
Cox Regression ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
The Impact ◽  
Very High

Abstract Introduction Metabolic control plays an important role on major cardiovascular events (MACE) prevention. The 2019 ESC guidelines on dyslipidaemia management recommend tighter LDL-cholesterol (LDL-C) control in order to prevent cardiovascular events. However, it is not yet proven that thigh control of dyslipidaemia, glycaemic levels and body mass index (BMI) in Heart Failure (HF) patients (pts) have an impact on prognosis. Objective To evaluate the impact of LDL-C, HbA1c and BMI values on HF pts mortality and MACE rates. Methods Single centre study that included consecutive pts hospitalized for acute / decompensated chronic HF in a tertiary Hospital between January 2016 to December 2018 and followed for 12 months. The impact of LDL-C, HbA1c and BMI on mortality and MACE was assessed using Cox regression and Kaplan-Meier curve, after adjustment for age, sex, functional class and ejection fraction. A safety cut-off was established when any of these variables was deemed protective using ROC curve analysis. Results Two hundred twenty-four patients (71.68±13.45 years, 63.8% males) were included. Eighty-four (37.5%) pts had type 2 diabetes, 39.7% had ischemic heart disease and the median left ventricular ejection fraction was 34% (IQR 25–49.5; 60.3% HFrEF; 13.8% HFmrEF; 22.3% HFpEF). The median BMI was 25.4 kg/m2 (IQR 23.1–30.5), HbA1c, 6.4% (IQR 5.6–6.8) and LDL-C, 89.5 mg/dL (IQR 64–106); 145 (64.7%) pts were medicated with statins. The overall mortality and MACE rates during follow-up were 16.1% and 21.0%, respectively. According to the CV risk classification 39.7% pts were at very high risk and 19.6% pts at high risk. On multivariate analysis HbA1c (HR 1.5 IQR 1.1–1.9; p=0.007) and female sex (HR 9.453 IQR 2.4–37.2; p=0.001) were independent predictors of mortality, whereas LDL-C (OR 1.05 IQR 1.022–1.075; p&lt;0.001) and BMI (OR 1.23 IQR 1.075–1.404; p=0.002) were independent protective factors. LDL-C and BMI had no effect on MACE rates, although HbA1c was an independent predictor of MACE (HR 1.27 IQR 1.03–1.57; p=0.026). For high and very high-risk pts there was still a protective trend on mortality, although non-significant, for higher levels of LDL-C (OR 1.04 IQR 0.99–1.075; P=NS). Protective LDL-C cut-off were estimated for the whole population (LDL-C 88mg/dL; AUC 0.819; sn 56.6%, sp 100%) and for the high and very-high CV risk pts (LDL-C 84mg/dL; AUC 0.815; sn 59.3%; sp 100%). A BMI safety cut-off for mortality of 25.75 kg/m2 was found (AUC 0.627; sn 61.2%; sp 58.3%). Conclusion This study supports the theory of the obesity and LDL-C paradox in HF. Lower LDL-C and BMI increased mortality and there is no trade-off effect on MACE rates, supporting the idea that LDL-C and BMI should not be aggressively addressed in HF pts. In our cohort a cut-off level of LDL-C below 88mg/dL is associated with higher mortality. On the other hand, diabetes should be actively treated as HbA1c predicts death and MACE in HF pts. Funding Acknowledgement Type of funding source: None

scholarly journals 114 Impact of left ventricular ejection fraction on procedural and long-term outcomes of bifurcation percutaneous coronary intervention

2021 ◽  
Vol 23 (Supplement_G) ◽  
Author(s):  
Guglielmo Gallone ◽  
Francesc Bruno ◽  
Ovidio De Filippo ◽  
Enrico Cerrato ◽  
Saverio Muscoli ◽  
...  
Keyword(s):  
Ejection Fraction ◽  
Systolic Function ◽  
Coronary Intervention ◽  
Left Ventricular ◽  
Doppler Imaging ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction ◽  
All Cause Mortality ◽  
The Impact

Abstract Aims Longitudinal systolic function may integrate information on aortic stenosis (AS) natural history and cardiac comorbidities with potential prognostic implications. We explored the impact of tissue Doppler imaging (TDI)-derived longitudinal systolic function defined by the peak systolic average of lateral and septal mitral annular velocities (average S’) among symptomatic patients with severe AS undergoing transcatheter aortic valve implantation (TAVI). Methods and results 297 unselected patients with severe AS undergoing TAVI from January 2017 to December 2018 at three European centres, with available average S′ at preprocedural echocardiography were retrospectively included. The primary endpoint was the Kaplan Meier estimate of all-cause mortality. After a median 18 months (IQR 12–18) follow-up, 36 (12.1%) patients died. Average S′ was associated with all-cause mortality (per 1 cm/s decrease: HR: 1.29, 95% CI: 1.03–1.60, P = 0.025), with a best cut-off of 6.5 cm/s. Patients with average S′ &lt;6.5 cm/s (55.2% of the study population) presented characteristics of more advanced left ventricular remodelling and functional impairment along with higher burden of cardiac comorbidities, and experienced higher all-cause mortality (17.6% vs. 7.5%, P = 0.007) also when adjusted for in-study outcome predictors (adj-HR: 3.33, 95% CI: 1.25–8.90, P = 0.016). Results were consistent among patients with preserved ejection fraction, normal-flow AS, high-gradient AS and in those without left ventricular hypertrophy. Conclusions Longitudinal systolic function assessed by average S’ is independently associated with long-term all-cause mortality among unselected patients with symptomatic severe AS undergoing TAVI. In this population, an average S′ below 6.5 cm/s best defines clinically meaningful reduced longitudinal systolic function and may aid clinical risk stratification.

Sign in / Sign up

Export Citation Format

Share Document