Machine Learning Augmented Echocardiography for Diastolic Function Assessment
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 echocardi...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-08-01
|
Series: | Frontiers in Cardiovascular Medicine |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2021.711611/full |
id |
doaj-da8548f8bb8849cca4408a920b799982 |
---|---|
record_format |
Article |
spelling |
doaj-da8548f8bb8849cca4408a920b7999822021-08-04T08:38:35ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2021-08-01810.3389/fcvm.2021.711611711611Machine Learning Augmented Echocardiography for Diastolic Function AssessmentAndrew J. Fletcher0Andrew J. Fletcher1Winok Lapidaire2Paul Leeson3Oxford Cardiovascular Clinical Research Facility, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, United KingdomDepartment of Cardiac Physiology, Royal Papworth Hospital National Health Service Foundation Trust, Cambridge, United KingdomOxford Cardiovascular Clinical Research Facility, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, United KingdomOxford Cardiovascular Clinical Research Facility, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, United KingdomCardiac 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.https://www.frontiersin.org/articles/10.3389/fcvm.2021.711611/fullartificial inteligenceechocardiogaphydiastolic dysfunctionmachine learningheart failure preserved ejection fraction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Andrew J. Fletcher Andrew J. Fletcher Winok Lapidaire Paul Leeson |
spellingShingle |
Andrew J. Fletcher Andrew J. Fletcher Winok Lapidaire Paul Leeson Machine Learning Augmented Echocardiography for Diastolic Function Assessment Frontiers in Cardiovascular Medicine artificial inteligence echocardiogaphy diastolic dysfunction machine learning heart failure preserved ejection fraction |
author_facet |
Andrew J. Fletcher Andrew J. Fletcher Winok Lapidaire Paul Leeson |
author_sort |
Andrew J. Fletcher |
title |
Machine Learning Augmented Echocardiography for Diastolic Function Assessment |
title_short |
Machine Learning Augmented Echocardiography for Diastolic Function Assessment |
title_full |
Machine Learning Augmented Echocardiography for Diastolic Function Assessment |
title_fullStr |
Machine Learning Augmented Echocardiography for Diastolic Function Assessment |
title_full_unstemmed |
Machine Learning Augmented Echocardiography for Diastolic Function Assessment |
title_sort |
machine learning augmented echocardiography for diastolic function assessment |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Cardiovascular Medicine |
issn |
2297-055X |
publishDate |
2021-08-01 |
description |
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. |
topic |
artificial inteligence echocardiogaphy diastolic dysfunction machine learning heart failure preserved ejection fraction |
url |
https://www.frontiersin.org/articles/10.3389/fcvm.2021.711611/full |
work_keys_str_mv |
AT andrewjfletcher machinelearningaugmentedechocardiographyfordiastolicfunctionassessment AT andrewjfletcher machinelearningaugmentedechocardiographyfordiastolicfunctionassessment AT winoklapidaire machinelearningaugmentedechocardiographyfordiastolicfunctionassessment AT paulleeson machinelearningaugmentedechocardiographyfordiastolicfunctionassessment |
_version_ |
1721222482722029568 |