A machine learning framework for the evaluation of myocardial rotation in patients with noncompaction cardiomyopathy

Imagem de Miniatura
Arquivos
art_MELO_A_machine_learning_framework_for_the_evaluation_of_2021.PDF (1.39 MB)
Citações na Scopus
1
Tipo de produção
article
Data de publicação
2021
DOI
Scopus
Web of Science
PubMed
Título da Revista
ISSN da Revista
Título do Volume
Editora
PUBLIC LIBRARY SCIENCE
Autores
ARAUJO-FILHO, Jose de Arimateia Batista
BARBOSA, Jose Raimundo
ROCON, Camila
REGIS, Carlos Danilo Miranda
FELIX, Alex dos Santos
TABASSIAN, Mahdi
Citação
PLOS ONE, v.16, n.11, article ID e0260195, 13p, 2021
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Aims Noncompaction cardiomyopathy (NCC) is considered a genetic cardiomyopathy with unknown pathophysiological mechanisms. We propose to evaluate echocardiographic predictors for rigid body rotation (RBR) in NCC using a machine learning (ML) based model. Methods and results Forty-nine outpatients with NCC diagnosis by echocardiography and magnetic resonance imaging (21 men, 42.8 +/- 14.8 years) were included. A comprehensive echocardiogram was performed. The layer-specific strain was analyzed from the apical two-, three, four-chamber views, short axis, and focused right ventricle views using 2D echocardiography (2DE) software. RBR was present in 44.9% of patients, and this group presented increased LV mass indexed (118 +/- 43.4 vs. 94.1 +/- 27.1g/m(2), P = 0.034), LV end-diastolic and end-systolic volumes (P < 0.001), E/e' (12.2 +/- 8.68 vs. 7.69 +/- 3.13, P = 0.034), and decreased LV ejection fraction (40.7 +/- 8.71 vs. 58.9 +/- 8.76%, P < 0.001) when compared to patients without RBR. Also, patients with RBR presented a significant decrease of global longitudinal, radial, and circumferential strain. When ML model based on a random forest algorithm and a neural network model was applied, it found that twist, NC/C, torsion, LV ejection fraction, and diastolic dysfunction are the strongest predictors to RBR with accuracy, sensitivity, specificity, area under the curve of 0.93, 0.99, 0.80, and 0.88, respectively. Conclusion In this study, a random forest algorithm was capable of selecting the best echocardiographic predictors to RBR pattern in NCC patients, which was consistent with worse systolic, diastolic, and myocardium deformation indices. Prospective studies are warranted to evaluate the role of this tool for NCC risk stratification.
Palavras-chave
URI
https://observatorio.fm.usp.br/handle/OPI/45879
Referências
  1. Araujo JAB, 2018, EUR HEART J-CARD IMG, V19, P888, DOI 10.1093/ehjci/jey022
  2. Bricq S, 2016, J MAGN RESON IMAGING, V43, P1398, DOI 10.1002/jmri.25113
  3. CHIN TK, 1990, CIRCULATION, V82, P507, DOI 10.1161/01.CIR.82.2.507
  4. ENGBERDING R, 1984, Z KARDIOL, V73, P786
  5. Farsalinos KE, 2015, J AM SOC ECHOCARDIOG, V28, P1171, DOI 10.1016/j.echo.2015.06.011
  6. Gastl M, 2019, SCI REP-UK, V9, DOI 10.1038/s41598-019-52161-1
  7. Jenni R, 2001, HEART, V86, P666, DOI 10.1136/heart.86.6.666
  8. Kawel-Boehm N, 2017, RADIOLOGY, V284, P667, DOI 10.1148/radiol.2017161995
  9. Kohli SK, 2008, EUR HEART J, V29, P89, DOI 10.1093/eurheartj/ehm481
  10. Lang RM, 2015, EUR HEART J-CARD IMG, V16, P233, DOI 10.1093/ehjci/jev014
  11. Maharaj N, 2013, EUR HEART J-CARD IMG, V14, P358, DOI 10.1093/ehjci/jes175
  12. Menze BH, 2009, BMC BIOINFORMATICS, V10, DOI 10.1186/1471-2105-10-213
  13. Notomi Y, 2006, CIRCULATION, V113, P2524, DOI 10.1161/CIRCULATIONAHA.105.596502
  14. Peters F, 2014, EUR HEART J-CARD IMG, V15, P48, DOI 10.1093/ehjci/jet076
  15. Petersen SE, 2005, J AM COLL CARDIOL, V46, P101, DOI 10.1016/j.jacc.2005.03.045
  16. Petersen SE, 2017, CIRC-CARDIOVASC IMAG, V10, DOI 10.1161/CIRCIMAGING.117.006908
  17. Popescu BA, 2009, EUR J HEART FAIL, V11, P945, DOI 10.1093/eurjhf/hfp124
  18. Rocon C, 2020, ESC HEART FAIL, V7, P2431, DOI 10.1002/ehf2.12795
  19. Sabatino J, 2019, CIRC-CARDIOVASC IMAG, V12, DOI 10.1161/CIRCIMAGING.118.007805
  20. Sengupta PP, 2008, JACC-CARDIOVASC IMAG, V1, P366, DOI 10.1016/j.jcmg.2008.02.006
  21. Smistad E, 2020, IEEE T ULTRASON FERR, V67, P2595, DOI 10.1109/TUFFC.2020.2981037
  22. Stollberger C, 2002, AM J CARDIOL, V90, P899, DOI 10.1016/S0002-9149(02)02723-6
  23. van Dalen BM, 2011, J AM SOC ECHOCARDIOG, V24, P548, DOI 10.1016/j.echo.2011.01.002
  24. Xu CC, 2020, MED IMAGE ANAL, V59, DOI 10.1016/j.media.2019.101568
  25. Zhang Y, 2018, NPJ COMPUT MATER, V4, DOI [10.1038/s41524-018-0081-z, 10.1186/s41016-018-0133-8]

Coleções
Artigos e Materiais de Revistas Científicas - FM/MCP
Artigos e Materiais de Revistas Científicas - HC/ICESP
Artigos e Materiais de Revistas Científicas - HC/InCor
Artigos e Materiais de Revistas Científicas - LIM/08
Artigos e Materiais de Revistas Científicas - LIM/11
Artigos e Materiais de Revistas Científicas - ODS/03