Variability in echocardiographic measurements of left ventricular function in septic shock patients

Geer, Lina De; Oscarsson, Anna; Engvall, Jan

doi:10.1186/s12947-015-0015-6

Cited by 39 publications

(31 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, it has significant variation in human interpretation. 18,19 The ejection fraction, a measure of the volume change in the left ventricle with each heart beat, is a key metric of cardiac function, but its measurement relies on the time-consuming manual tracing of left ventricular areas and volumes at different times during the cardiac cycle. We trained EchoNet to predict left ventricular end systolic volume (ESV), end diastolic volume (EDV), and ejection fraction from sampled apical-four-chamber view images ( Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Despite its importance in clinical phenotyping, there is variance in the human interpretation of echocardiogram images that could impact clinical care. [18][19][20] Formalized training guidelines for cardiologists recognize the value of experience in interpreting echocardiogram images and basic cardiology training might be insufficient to interpret echocardiograms at the highest level. 21 Given the importance of imaging to cardiovascular care, an automated pipeline for interpreting cardiovascular imaging can improve peri-operative risk stratification, manage the cardiovascular risk of patients with oncologic disease undergoing chemotherapy, and aid in the diagnosis of cardiovascular disease.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning interpretation of echocardiograms

et al. 2020

View full text Add to dashboard Cite

Echocardiography uses ultrasound technology to capture high temporal and spatial resolution images of the heart and surrounding structures, and is the most common imaging modality in cardiovascular medicine. Using convolutional neural networks on a large new dataset, we show that deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation. Our deep learning model, EchoNet, accurately identified the presence of pacemaker leads (AUC = 0.89), enlarged left atrium (AUC = 0.86), left ventricular hypertrophy (AUC = 0.75), left ventricular end systolic and diastolic volumes (R 2 = 0.74 and R 2 = 0.70), and ejection fraction (R 2 = 0.50), as well as predicted systemic phenotypes of age (R 2 = 0.46), sex (AUC = 0.88), weight (R 2 = 0.56), and height (R 2 = 0.33). Interpretation analysis validates that EchoNet shows appropriate attention to key cardiac structures when performing human-explainable tasks and highlights hypothesis-generating regions of interest when predicting systemic phenotypes difficult for human interpretation. Machine learning on echocardiography images can streamline repetitive tasks in the clinical workflow, provide preliminary interpretation in areas with insufficient qualified cardiologists, and predict phenotypes challenging for human evaluation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning interpretation of echocardiograms

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Predicting cardiac function Quantification of cardiac function is a crucial assessment addressed by echocardiography. However it has significant variation in human interpretation 18,19 . The ejection fraction, a measure of the volume change in the left ventricle with each heart beat, is a key metric of cardiac function, but its measurement relies on the time-consuming manual tracing of left ventricular areas and volumes at different times during the cardiac cycle.…”

Section: View Classification Echocardiogram Studymentioning

confidence: 99%

“…Despite its importance in clinical phenotyping, there is variance in the human interpretation of echocardiogram images that could impact clinical care. [18][19][20] Formalized training guidelines for cardiologists recognize the value of experience in interpreting echocardiogram images and basic cardiology training might be insufficient to interpret echocardiograms at the highest level. 21 Given the importance of imaging to cardiovascular care, an automated pipeline for standardizing and interpreting cardiovascular imaging can improve peri-operative risk stratification, manage the cardiovascular risk of patients with oncologic disease undergoing chemotherapy, and aid in the diagnosis of cardiovascular disease.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Interpretation of Echocardiograms

Ghorbani

Ouyang

Abid

et al. 2019

Preprint

View full text Add to dashboard Cite

Echocardiography uses ultrasound technology to capture high temporal and spatial resolution images of the heart and surrounding structures and is the most common imaging modality in cardiovascular medicine. Using convolutional neural networks on a large new dataset, we show that deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation. Our deep learning model, EchoNet, accurately identified the presence of pacemaker leads (AUC = 0.89), enlarged left atrium (AUC = 0.85), normal left ventricular wall thickness (AUC = 0.75), left ventricular end systolic and diastolic volumes(R 2 = 0.73 and R 2 = 0.68), and ejection fraction (R 2 = 0.48) as well as predicted systemic phenotypes of age (R 2 = 0.46), sex (AUC = 0.88), weight (R 2 = 0.56), and height (R 2 = 0.33). Interpretation analysis validates that EchoNet shows appropriate attention to key cardiac structures when performing human-explainable tasks and highlight hypothesis-generating regions of interest when predicting systemic phenotypes difficult for human interpretation. Machine learning on echocardiography images can streamline repetitive tasks in the clinical workflow, standardize interpretation in areas with insufficient qualified cardiologists, and more consistently produce echocardiographic measurements.Related works Current literature have already shown that it is possible to identify standard echocardiogram views from unlabeled datasets. 5,6,24 Previous works have used convolutional neural networks (CNNs) trained on images and videos from echocardiography to perform segmentation to identify cardiac structures and derive cardiac function. In this study, we extend previous analyses to show that EchoNet, our deep learning model using echocardiography images, local cardiac structures and anatomy, estimate volumetric measurements and metrics of cardiac function, and predict systemic human phenotypes that modify cardiovascular risk. Additionally, we show the first application of interpretation frameworks to understand deep learning models from echocardiogram images. Human identifiable features, such as the presence of pacemaker and defibrillator leads, left ventricular hypertrophy, and abnormal left atrial chamber size identified by our convolutional neural network were validated using interpretation frameworks to highlight the most relevant regions of interest. To the best of our knowledge, we develop the first deep learning model that can directly predict age, sex, weight and height from echocardiogram images and use interpretation methods to understand how the model predicts these systemic phenotypes difficult for human interpreters. 2/14Lessons from model training and experiments EchoNet performance greatly improved with efforts to augment data size, homogenize input data, and with optimize model training with hyperparameter search. Our experience shows that increasing number of unique patien...

show abstract

“…Landesberg (E/é), decreased LV ejection fraction (EF) in septic shock patients. 19 Sam R Orde et al (2014) stated that, Cardiac dysfunction was associated with high mortality in patients with severe sepsis or septic shock. 20 LV dysfunction was not associated with survival outcomes, similarly in present study mean LVEF in both genders in death and survived group in cohort of septic shock were statistically insignificant.…”

Section: Present Studymentioning

confidence: 99%

Relation of Echocardiographic Parameters to Outcome of Patients with Severe Sepsis and Septic Shock

Patil¹,

Patil²,

Rajput³

et al. 2017

JCDR

View full text Add to dashboard Cite

Background: Myocardial dysfunction is one of the most important features of sepsis. The presence of cardiac dysfunction in sepsis has been associated with high mortality rate in septic patients. Material & Methods: This was prospective, observational cohort (patient with severe sepsis and septic shock) study conducted over period of one year in medical intensive care unit. Patients with an initial diagnosis of severe sepsis or septic shock were enrolled. Aims & Objectives:To study demographic profile, APACHE-II score and echocardiographic parameters in patients with severe sepsis and septic shock and to find out relation of echocardiographic parameters to variables of sepsis and outcome. Study Population: All patients underwent laboratory investigations, APACHE-II score and Transthoracic 2-Dimensional echocardiogram. Statistical analysis: Data was analysed by trial version SPSS-16 for mean, SD, chi-square test with'p' <0.05 was considered as statistically significant. Results: Of total 51 patients with sepsis and septic shock 32 were males and 19 were females with mean age of 51.48 (±13.11) years and 59.66 (±16.93) respectively. The mean LVEF was 35.70% (±7.47608). APACHE-II score had negative correlation with LVEF and positive with DD. Total 17.64% had normal LV diastolic function, 47.05% had grade-I diastolic dysfunction and 35.29% had grade-II diastolic dysfunction ['p'=0.082]. Overall mortality was 29.41% in patient with sepsis. Overall diastolic dysfunction was significantly more in patients with death compared to survived population ['p'= 0.0218 and 0.0329]. Conclusion: Diastolic dysfunction was common and a major predictor of mortality and outcome in severe sepsis and septic shock and was well correlated with APACHE-II score. Present study favors to use echocardiography as an ideal monitoring, tool in the septic patient for goal-oriented therapy for better outcome.

show abstract

Variability in echocardiographic measurements of left ventricular function in septic shock patients

Cited by 39 publications

References 31 publications

Deep learning interpretation of echocardiograms

Deep learning interpretation of echocardiograms

Deep Learning Interpretation of Echocardiograms

Relation of Echocardiographic Parameters to Outcome of Patients with Severe Sepsis and Septic Shock

Contact Info

Product

Resources

About