Machine Learning Augmented Echocardiography for Diastolic Function Assessment

Abstract

Cardiac diastolic dysfunction is prevalent and is a diagnostic criterion for heart failure with preserved ejection fraction—a burgeoning global health issue. As gold-standard invasive haemodynamic assessment of diastolic function is not routinely performed, clinical guidelines advise using echocardiography measures to determine the grade of diastolic function. However, the current process has suboptimal accuracy, regular indeterminate classifications and is susceptible to confounding from comorbidities. Advances in artificial intelligence in recent years have created revolutionary ways to evaluate and integrate large quantities of cardiology data. Imaging is an area of particular strength for the sub-field of machine-learning, with evidence that trained algorithms can accurately discern cardiac structures, reliably estimate chamber volumes, and output systolic function metrics from echocardiographic images. In this review, we present the emerging field of machine-learning based echocardiographic diastolic function assessment. We summarise how machine-learning has made use of diastolic parameters to accurately differentiate pathology, to identify novel phenotypes within diastolic disease, and to grade diastolic function. Perspectives are given about how these innovations could be used to augment clinical practice, whilst areas for future investigation are identified.

Interrater reproducibility of the 2016 American society of echocardiography left ventricular diastolic function guidelines

“…We believe there is significant promise in using artificial intelligence (AI) augmented echocardiography to improve LV diastolic assessment and application. This includes automating the measurement of diastolic parameters, integrating diastolic parameters to assist with cardiac disease diagnoses, developing novel parameters of diastolic dysfunction, diastolic phenotyping, and prognostication 23 . We believe future research should focus on rethinking the way we categorize and apply diastolic parameter assessment to inform clinical decision making.…”

The Role of Artificial Intelligence in Echocardiography

“…Furthermore, up to a third of patients with a diagnosis of HFpEF may be classified as having normal diastolic function by echocardiography [ 32 ]. Given the advancements in artificial intelligence and the previously described use in the assessment of systolic function, AI may provide a fresh approach to diastology by helping detect diastolic dysfunction in the one-third of patients graded as normal by echocardiographic criteria or more uniformly applying guideline criteria for more consistent interpretation of diastolic parameters [ 33 ].…”

Artificial intelligence and heart failure: A state‐of‐the‐art review

“…28 Studies have also utilized other ML algorithms to predict diastolic function. 41 By obtaining a collection of features directly from heart sounds, feature vectors can be input in a ML algorithm for early HF diagnosis. Using computer-assisted least squares SVM (LS-SVM), the ML algorithm was trained and tested using heart sounds and reverse features of 152 individuals (64 with HF and 88 healthy volunteers).…”

“…During external validation, the AUC of the deep learning model using 12‐lead and 6‐lead ECG were 0.869 and 0.858, respectively 28 . Studies have also utilized other ML algorithms to predict diastolic function 41 . Some of the algorithms based on deep learning have also been approved by the US Food and Drug Administration (FDA) for the implementation in clinical practice to deliver automatic, and repeatable analysis of cardiac images that are just as accurate as segmentations carried out manually by medical professionals 42 .…”