Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
    • Publication Information:
      Original Publication: San Francisco, CA : Public Library of Science
    • Subject Terms:
      Myocardial Infarction/*mortality ; Risk Assessment/*methods; Acute Disease/mortality ; Aged ; Area Under Curve ; Deep Learning ; Female ; Hospital Mortality ; Humans ; Machine Learning ; Male ; Middle Aged ; Non-ST Elevated Myocardial Infarction/mortality ; ROC Curve ; Registries ; Republic of Korea/epidemiology ; Risk Factors ; ST Elevation Myocardial Infarction/mortality ; Time Factors
    • Abstract:
      Objective: Conventional risk stratification models for mortality of acute myocardial infarction (AMI) have potential limitations. This study aimed to develop and validate deep-learning-based risk stratification for the mortality of patients with AMI (DAMI).
      Methods: The data of 22,875 AMI patients from the Korean working group of the myocardial infarction (KorMI) registry were exclusively divided into 12,152 derivation data of 36 hospitals and 10,723 validation data of 23 hospitals. The predictor variables were the initial demographic and laboratory data. The endpoints were in-hospital mortality and 12-months mortality. We compared the DAMI performance with the global registry of acute coronary event (GRACE) score, acute coronary treatment and intervention outcomes network (ACTION) score, and the thrombolysis in myocardial infarction (TIMI) score using the validation data.
      Results: In-hospital mortality for the study subjects was 4.4% and 6-month mortality after survival upon discharge was 2.2%. The areas under the receiver operating characteristic curves (AUCs) of the DAMI were 0.905 [95% confidence interval 0.902-0.909] and 0.870 [0.865-0.876] for the ST elevation myocardial infarction (STEMI) and non ST elevation myocardial infarction (NSTEMI) patients, respectively; these results significantly outperformed those of the GRACE (0.851 [0.846-0.856], 0.810 [0.803-0.819]), ACTION (0.852 [0.847-0.857], 0.806 [0.799-0.814] and TIMI score (0.781 [0.775-0.787], 0.593[0.585-0.603]). DAMI predicted 30.9% of patients more accurately than the GRACE score. As secondary outcome, during the 6-month follow-up, the high risk group, defined by the DAMI, has a significantly higher mortality rate than the low risk group (17.1% vs. 0.5%, p < 0.001).
      Conclusions: The DAMI predicted in-hospital mortality and 12-month mortality of AMI patients more accurately than the existing risk scores and other machine-learning methods.
      Competing Interests: The authors have declared that no competing interests exist.
    • References:
      JAMA. 2004 Jun 9;291(22):2727-33. (PMID: 15187054)
      JAMA. 2016 Dec 13;316(22):2402-2410. (PMID: 27898976)
      N Engl J Med. 2009 Sep 10;361(11):1045-57. (PMID: 19717846)
      PLoS One. 2016 Nov 11;11(11):e0166391. (PMID: 27835698)
      Nature. 2015 May 28;521(7553):436-44. (PMID: 26017442)
      Am Heart J. 2009 Sep;158(3):392-9. (PMID: 19699862)
      Circulation. 2015 Sep 29;132(13):1224-33. (PMID: 26330412)
      N Engl J Med. 2012 Oct 4;367(14):1297-309. (PMID: 22920930)
      J Clin Epidemiol. 1996 Aug;49(8):907-16. (PMID: 8699212)
      Nature. 2017 Feb 2;542(7639):115-118. (PMID: 28117445)
      Glob Heart. 2014 Mar;9(1):91-9. (PMID: 24977114)
      Contemp Clin Trials. 2012 May;33(3):507-14. (PMID: 22265976)
      JAMA. 2000 Aug 16;284(7):835-42. (PMID: 10938172)
      J Cardiol. 2010 Jul;56(1):1-7. (PMID: 20554156)
      J Am Heart Assoc. 2015 Feb 09;4(2):null. (PMID: 25666368)
      Korean Circ J. 2018 Jun;48(6):492-504. (PMID: 29856143)
      Eur J Clin Pharmacol. 2013 Dec;69(12):2001-9. (PMID: 23942733)
      J Am Coll Cardiol. 2016 Aug 9;68(6):626-635. (PMID: 27491907)
      BMJ Open. 2014 Feb 21;4(2):e004425. (PMID: 24561498)
      Int J Cardiol. 2017 Nov 1;246:7-13. (PMID: 28867023)
      Crit Care Med. 2016 Feb;44(2):368-74. (PMID: 26771782)
      J Clin Epidemiol. 2001 Oct;54(10):979-85. (PMID: 11576808)
      J Am Heart Assoc. 2018 Jun 26;7(13):. (PMID: 29945914)
      J Epidemiol Community Health. 2015 Oct;69(10):1000-5. (PMID: 26136081)
      BMC Med Inform Decis Mak. 2011 Jul 29;11:51. (PMID: 21801360)
      IEEE Trans Pattern Anal Mach Intell. 2013 Aug;35(8):1798-828. (PMID: 23787338)
      Am Heart J. 2016 May;175:56-65. (PMID: 27179724)
    • Publication Date:
      Date Created: 20191101 Date Completed: 20200313 Latest Revision: 20200313
    • Publication Date:
      20240104
    • Accession Number:
      PMC6822714
    • Accession Number:
      10.1371/journal.pone.0224502
    • Accession Number:
      31671144