Artificial Intelligence–Assisted Left Ventricular Diastolic Function Assessment and Grading: Multiview Versus Single View

Xu, Chenyu; Yang, Fang; Zhang, Peifang; Lin, Xixiang; Wang, Wenjun; Pu, Haitao; Chen, Xiaotian; Chen, Yixin; Yu, Liheng; Deng, Yao; Liu, Bohan; Yang, Bai; Burkhoff, Daniel; He, Kunlun

doi:10.1016/j.echo.2023.07.001

“…36 Despite a recent study provided a simple method to diagnose DD based on a single echocardiographic view, which saved lots of time and labors at the expense of accuracy. 37 The introduction of the PV loop may efficiently address Besides EF and VA coupling, ventricular efficiency, SBP and are essential parameters to the classification. Ventricular efficiency and PE are defined by both pressure and volume which supply additional information on global cardiac function.…”

Section: Discussionmentioning

confidence: 99%

Heart failure classifications via non‐invasive pressure volume loops from echocardiography

Liu,

Chen,

Xia

et al. 2023

Echocardiography

Self Cite

0

View full text Add to dashboard Cite

BackgroundLeft ventricular pressure‐volume (LV‐PV) loops provide comprehensive characterization of cardiovascular system in both health and disease, which are the essential element of the hemodynamic evaluation of heart failure (HF). This study attempts to achieve more detailed HF classifications by non‐invasive LV‐PV loops from echocardiography and analyzes contribution of parameters to HF classifications.MethodsFirstly, non‐invasive PV loops are established by time‐varying elastance model where LV volume curves were extracted from apical‐four‐chambers view of echocardiographic videos. Then, 16 parameters related to cardiac structure and functions are automatically acquired from PV loops. Next, we applied six machine learning (ML) methods to divide four categories. On this premise, we choose the best performing classifier among machine learning approaches for feature ranking. Finally, we compare the contributions of different parameters to HF classifications.ResultsBy the experimental, the PV loops were successfully acquired in 1076 cases. When single left ventricular ejection fraction (LVEF) is used for HF classifications, the accuracy of the model is 91.67%. When added parameters extracted from ML‐derived LV‐PV loops, the classification accuracy is 96.57%, which improved by 5.1%. Especially, our parameters have a great improvement in the classification of non‐HF controls and heart failure with preserved ejection fraction (HFpEF).ConclusionsWe successfully presented the classification of HF by machine derived non‐invasive LV‐PV loops, which has the potential to improve the diagnosis and management of heart failure in clinic. Moreover, ventriculo‐arterial (VA) coupling and ventricular efficiency were demonstrated important factors for ML‐based HF classification model besides LVEF.

show abstract

“…In the latest investigation, Chen et al [80] introduced three AI-assisted methods for diastolic function assessment, achieving better diagnostic accuracy than human experts following guidelines. The models showed favorable results in evaluating and grading LV diastolic function.…”

Section: Integrating Artificial Intelligence (Ai)mentioning

confidence: 99%

Interpreting Diastolic Dynamics and Evaluation Through Echocardiography

Zhang,

Li,

Cardoso

et al. 2024

Preprint

0

View full text Add to dashboard Cite

In patients with heart failure, the evaluation of left ventricular (LV) diastolic function is vital, offering crucial insights into hemodynamic impact and prognostic accuracy. Echocardiography stands as the primary imaging modality for diastolic function assessment, and using it effectively requires a profound understanding of the underlying pathology. This review covers four main topics: first, the fundamental driving forces behind each phase of normal diastolic dynamics, along with the physiological basis of two widely used echocardiographic assessment parameters, E/e' and mitral annulus early diastolic velocity (e'); second, the intricate functional relationship between the left atrium and LV in patients with varying degrees of LV diastolic dysfunction (LVDD); third, the role of stress echocardiography in diagnosing LVDD and the significance of parameter changes in this context; and fourth, the clinical utility of evaluating diastolic function from echocardiography images across diverse cardiovascular care areas.

show abstract

“…In the latest investigation, Chen et al [83] introduced three AI-assisted methods for diastolic function assessment, achieving better diagnostic accuracy than human experts following guidelines. The models showed favorable results in evaluating and grading LV diastolic function.…”

Section: Integrating Artificial Intelligence (Ai)mentioning

confidence: 99%

Interpreting Diastolic Dynamics and Evaluation Through Echocardiography

Zhang,

Li,

Cardoso

et al. 2024

Preprint

0

View full text Add to dashboard Cite

In patients with heart failure, the evaluation of left ventricular (LV) diastolic function is vital, offering crucial insights into hemodynamic impact and prognostic accuracy. Echocardiography stands as the primary imaging modality for diastolic function assessment, and using it effectively requires a profound understanding of the underlying pathology. This review covers four main topics: first, the fundamental driving forces behind each phase of normal diastolic dynamics, along with the physiological basis of two widely used echocardiographic assessment parameters, E/e' and mitral annulus early diastolic velocity (e'); second, the intricate functional relationship between the left atrium and LV in patients with varying degrees of LV diastolic dysfunction (LVDD); third, the role of stress echocardiography in diagnosing LVDD and the significance of parameter changes in this context; and fourth, the clinical utility of evaluating diastolic function from echocardiography images across diverse cardiovascular care areas.

show abstract

Artificial Intelligence–Assisted Left Ventricular Diastolic Function Assessment and Grading: Multiview Versus Single View

Cited by 9 publications

References 30 publications

Heart failure classifications via non‐invasive pressure volume loops from echocardiography

Heart failure classifications via non‐invasive pressure volume loops from echocardiography

Interpreting Diastolic Dynamics and Evaluation Through Echocardiography

Interpreting Diastolic Dynamics and Evaluation Through Echocardiography

Contact Info

Product

Resources

About