Literature DB >> 29661795

Machine Learning Analysis of Left Ventricular Function to Characterize Heart Failure With Preserved Ejection Fraction.

Sergio Sanchez-Martinez1, Nicolas Duchateau2, Tamas Erdei2, Gabor Kunszt2, Svend Aakhus2, Anna Degiovanni2, Paolo Marino2, Erberto Carluccio2, Gemma Piella2, Alan G Fraser2, Bart H Bijnens2.   

Abstract

BACKGROUND: Current diagnosis of heart failure with preserved ejection fraction (HFpEF) is suboptimal. We tested the hypothesis that comprehensive machine learning (ML) of left ventricular function at rest and exercise objectively captures differences between HFpEF and healthy subjects. METHODS AND
RESULTS: One hundred fifty-six subjects aged >60 years (72 HFpEF+33 healthy for the initial analyses; 24 hypertensive+27 breathless for independent evaluation) underwent stress echocardiography, in the MEDIA study (Metabolic Road to Diastolic Heart Failure). Left ventricular long-axis myocardial velocity patterns were analyzed using an unsupervised ML algorithm that orders subjects according to their similarity, allowing exploration of the main trends in velocity patterns. ML identified a continuum from health to disease, including a transition zone associated to an uncertain diagnosis. Clinical validation was performed (1) to characterize the main trends in the patterns for each zone, which corresponded to known characteristics and new features of HFpEF; the ML-diagnostic zones differed for age, body mass index, 6-minute walk distance, B-type natriuretic peptide, and left ventricular mass index (P<0.05) and (2) to evaluate the consistency of the proposed groupings against diagnosis by current clinical criteria; correlation with diagnosis was good (κ, 72.6%; 95% confidence interval, 58.1-87.0); ML identified 6% of healthy controls as HFpEF. Blinded reinterpretation of imaging from subjects with discordant clinical and ML diagnoses revealed abnormalities not included in diagnostic criteria. The algorithm was applied independently to another 51 subjects, classifying 33% of hypertensive and 67% of breathless controls as mild-HFpEF.
CONCLUSIONS: The analysis of left ventricular long-axis function on exercise by interpretable ML may improve the diagnosis and understanding of HFpEF.
© 2018 American Heart Association, Inc.

Entities:  

Keywords:  early diagnosis; echocardiography, stress; heart failure, diastolic; machine learning; ultrasonography, doppler

Mesh:

Year:  2018        PMID: 29661795     DOI: 10.1161/CIRCIMAGING.117.007138

Source DB:  PubMed          Journal:  Circ Cardiovasc Imaging        ISSN: 1941-9651            Impact factor:   7.792


  28 in total

Review 1.  Artificial Intelligence in Cardiovascular Imaging: JACC State-of-the-Art Review.

Authors:  Damini Dey; Piotr J Slomka; Paul Leeson; Dorin Comaniciu; Sirish Shrestha; Partho P Sengupta; Thomas H Marwick
Journal:  J Am Coll Cardiol       Date:  2019-03-26       Impact factor: 24.094

Review 2.  Artificial Intelligence in Cardiovascular Medicine.

Authors:  Karthik Seetharam; Sirish Shrestha; Partho P Sengupta
Journal:  Curr Treat Options Cardiovasc Med       Date:  2019-05-14

3.  Automated algorithms in diastology: how to move forward?

Authors:  Mihai Strachinaru; Johan G Bosch
Journal:  Int J Cardiovasc Imaging       Date:  2022-02-08       Impact factor: 2.357

Review 4.  The future of heart failure with preserved ejection fraction : Deep phenotyping for targeted therapeutics.

Authors:  Frank R Heinzel; Sanjiv J Shah
Journal:  Herz       Date:  2022-06-29       Impact factor: 1.740

Review 5.  Artificial Intelligence in Cardiovascular Medicine: Current Insights and Future Prospects.

Authors:  Ikram U Haq; Karanjot Chhatwal; Krishna Sanaka; Bo Xu
Journal:  Vasc Health Risk Manag       Date:  2022-07-12

6.  Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery.

Authors:  Patricia Garcia-Canadilla; Alba Isabel-Roquero; Esther Aurensanz-Clemente; Arnau Valls-Esteve; Francesca Aina Miguel; Daniel Ormazabal; Floren Llanos; Joan Sanchez-de-Toledo
Journal:  Front Pediatr       Date:  2022-06-27       Impact factor: 3.569

7.  Association of Machine Learning-Derived Phenogroupings of Echocardiographic Variables with Heart Failure in Stable Coronary Artery Disease: The Heart and Soul Study.

Authors:  Rakesh K Mishra; Geoffrey H Tison; Qizhi Fang; Rebecca Scherzer; Mary A Whooley; Nelson B Schiller
Journal:  J Am Soc Echocardiogr       Date:  2020-01-14       Impact factor: 5.251

8.  Risk stratification of ST-segment elevation myocardial infarction (STEMI) patients using machine learning based on lipid profiles.

Authors:  Yuzhou Xue; Jian Shen; Weifeng Hong; Wei Zhou; Zhenxian Xiang; Yuansong Zhu; Chuiguo Huang; Suxin Luo
Journal:  Lipids Health Dis       Date:  2021-05-06       Impact factor: 3.876

9.  Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use.

Authors:  Akhil Narang; Richard Bae; Ha Hong; Yngvil Thomas; Samuel Surette; Charles Cadieu; Ali Chaudhry; Randolph P Martin; Patrick M McCarthy; David S Rubenson; Steven Goldstein; Stephen H Little; Roberto M Lang; Neil J Weissman; James D Thomas
Journal:  JAMA Cardiol       Date:  2021-06-01       Impact factor: 14.676

10.  Identifying knowledge gaps in heart failure research among women using unsupervised machine-learning methods.

Authors:  Khalid Alhussain; Kazuhiko Kido; Nilanjana Dwibedi; Traci LeMasters; Danielle E Rose; Ranjita Misra; Usha Sambamoorthi
Journal:  Future Cardiol       Date:  2021-01-11
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.