Improving preoperative risk-of-death prediction in surgery congenital heart defects using artificial intelligence model: A pilot study

Imagem de Miniatura
Arquivos
art_CHANG JUNIOR_Improving_preoperative_riskofdeath_prediction_in_surgery_congenital_heart_2020.PDF.pdf (1.04 MB)
Citações na Scopus
22
Tipo de produção
article
Data de publicação
2020
DOI
Scopus
Web of Science
PubMed
Título da Revista
ISSN da Revista
Título do Volume
Editora
PUBLIC LIBRARY SCIENCE
Autores
CHANG JUNIOR, Joao
BINUESA, Fabio
DOSSOU, Paul-Eric
Citação
PLOS ONE, v.15, n.9, article ID e0238199, 21p, 2020
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Background Congenital heart disease accounts for almost a third of all major congenital anomalies. Congenital heart defects have a significant impact on morbidity, mortality and health costs for children and adults. Research regarding the risk of pre-surgical mortality is scarce. Objectives Our goal is to generate a predictive model calculator adapted to the regional reality focused on individual mortality prediction among patients with congenital heart disease undergoing cardiac surgery. Methods Two thousand two hundred forty CHD consecutive patients' data from InCor's heart surgery program was used to develop and validate the preoperative risk-of-death prediction model of congenital patients undergoing heart surgery. There were six artificial intelligence models most cited in medical references used in this study: Multilayer Perceptron (MLP), Random Forest (RF), Extra Trees (ET), Stochastic Gradient Boosting (SGB), Ada Boost Classification (ABC) and Bag Decision Trees (BDT). Results The top performing areas under the curve were achieved using Random Forest (0.902). Most influential predictors included previous admission to ICU, diagnostic group, patient's height, hypoplastic left heart syndrome, body mass, arterial oxygen saturation, and pulmonary atresia. These combined predictor variables represent 67.8% of importance for the risk of mortality in the Random Forest algorithm. Conclusions The representativeness of ""hospital death"" is greater in patients up to 66 cm in height and body mass index below 13.0 for InCor's patients. The proportion of ""hospital death"" declines with the increased arterial oxygen saturation index. Patients with prior hospitalization before surgery had higher ""hospital death"" rates than who did not required such intervention. The diagnoses groups having the higher fatal outcomes probability are aligned with the international literature. A web application is presented where researchers and providers can calculate predicted mortality based on the CgntSCORE on any web browser or smartphone.
Palavras-chave
URI
https://observatorio.fm.usp.br/handle/OPI/37688
Referências
  1. [Anonymous], 2011, J AM COLL CARDIOL, V58, pe44, DOI 10.1016/j.jacc.2011.08.007
  2. [Anonymous], 2017, KIDNEY INT S, V7, P1, DOI 10.1016/j.kisu.2017.04.001
  3. [Anonymous], 2016, EVIDENCE, V8, pe1000
  4. Awad A, 2017, INT J MED INFORM, V108, P185, DOI 10.1016/j.ijmedinf.2017.10.002
  5. Awad A, 2017, HEALTH SERV MANAG RE, V30, P105, DOI 10.1177/0951484817696212
  6. Bader-El-Den M, 2016, IEEE IJCNN, P3584, DOI 10.1109/IJCNN.2016.7727660
  7. BENJAMIN E.J., 2017, HEART DIS STROKE STA
  8. Blagus R, 2015, BMC BIOINFORMATICS, V16, DOI 10.1186/s12859-015-0723-9
  9. Browne MW, 2000, J MATH PSYCHOL, V44, P108, DOI 10.1006/jmps.1999.1279
  10. Carmona F, 2017, BRAZ J CARDIOVA SURG, V32, P260, DOI 10.21470/1678-9741-2016-0074
  11. Chawla NV, 2002, J ARTIF INTELL RES, V16, P321, DOI 10.1613/jair.953
  12. CHURPEK M. M., 2017, CRIT CARE MED, V44, P298
  13. DAVIS J., 2006, RELATIONSHIP PRECISI
  14. Fawcett T., 2004, MACH LEARN, V31, P1, DOI 10.1016/J.PATREC.2005.10.010
  15. Hajian-Tilaki K, 2013, CASP J INTERN MED, V4, P627
  16. Hastie T., 2009, ELEMENTS STAT LEARNI
  17. Hawkins DM, 2004, J CHEM INF COMP SCI, V44, P1, DOI 10.1021/ci0342472
  18. Haykin S, 2001, ADAPT LEARN SYST SIG, P1
  19. HoRER J., 2016, WORLD J PEDIAT CONGE
  20. Jacobs JP, 2019, ANN THORAC SURG, V108, P558, DOI 10.1016/j.athoracsur.2019.01.069
  21. Jacobs JP, 2018, WORLD J PEDIATR CONG, V9, P392, DOI 10.1177/2150135118775962
  22. JENKINS K. J., 2002, J THORACIC CARDIOVAS
  23. Jenkins Kathy J, 2004, Semin Thorac Cardiovasc Surg Pediatr Card Surg Annu, V7, P180, DOI 10.1053/j.pcsu.2004.02.009
  24. Jenkins KJ, 2002, J THORAC CARDIOV SUR, V124, P97, DOI 10.1067/mtc.2002.122311
  25. Kohavi R., 1995, INT JOINT C ART INT
  26. Lacour-Gayet F, 2004, EUR J CARDIO-THORAC, V25, P911, DOI 10.1016/j.ejcts.2004.03.027
  27. LI H., 2017, MED US
  28. Lin K, 2019, INT J MED INFORM, V125, P55, DOI 10.1016/j.ijmedinf.2019.02.002
  29. McParlin C, 2010, BMC PREGNANCY CHILDB, V10, DOI 10.1186/1471-2393-10-76
  30. Mitchell T., 1997, MACHINE LEARNING
  31. Nina Rachel Vilela de Abreu Haickel, 2007, Braz. J. Cardiovasc. Surg., V22, P425, DOI 10.1590/S0102-76382007000400008
  32. O M, 2015, J INTENSIVE CARE, V3, P42
  33. Provost F, 2001, MACH LEARN, V42, P203, DOI 10.1023/A:1007601015854
  34. RUIZ-FERNaNDEZ D., 2016, COMPUTER METHODS PRO
  35. Saito T, 2015, PLOS ONE, V10, DOI 10.1371/journal.pone.0118432
  36. SILVA I. N. DA, 2010, REDES NEURAIS ARTIFI
  37. Wen SP, 2019, IEEE T SYST MAN CY-S, V49, P1787, DOI 10.1109/TSMC.2018.2825021
  38. XU J., DATA MINING ICU MORT, V16

Coleções
Artigos e Materiais de Revistas Científicas - FM/MCP
Artigos e Materiais de Revistas Científicas - HC/InCor
Artigos e Materiais de Revistas Científicas - LIM/11
Artigos e Materiais de Revistas Científicas - LIM/65
Artigos e Materiais de Revistas Científicas - ODS/03