Information maximizing component analysis of left ventricular remodeling due to myocardial infarction.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: BioMed Central Country of Publication: England NLM ID: 101190741 Publication Model: Electronic Cited Medium: Internet ISSN: 1479-5876 (Electronic) Linking ISSN: 14795876 NLM ISO Abbreviation: J Transl Med Subsets: MEDLINE
    • Publication Information:
      Original Publication: [London] : BioMed Central, 2003-
    • Subject Terms:
      Ventricular Remodeling*; Heart Ventricles/*physiopathology ; Myocardial Infarction/*physiopathology; Adult ; Aged ; Aged, 80 and over ; Algorithms ; Bayes Theorem ; Data Collection ; Discriminant Analysis ; Female ; Humans ; Male ; Middle Aged ; Models, Cardiovascular ; Models, Statistical ; Principal Component Analysis ; Ventricular Function, Left
    • Abstract:
      Background: Although adverse left ventricular shape changes (remodeling) after myocardial infarction (MI) are predictive of morbidity and mortality, current clinical assessment is limited to simple mass and volume measures, or dimension ratios such as length to width ratio. We hypothesized that information maximizing component analysis (IMCA), a supervised feature extraction method, can provide more efficient and sensitive indices of overall remodeling.
      Methods: IMCA was compared to linear discriminant analysis (LDA), both supervised methods, to extract the most discriminatory global shape changes associated with remodeling after MI. Finite element shape models from 300 patients with myocardial infarction from the DETERMINE study (age 31-86, mean age 63, 20 % women) were compared with 1991 asymptomatic cases from the MESA study (age 44-84, mean age 62, 52 % women) available from the Cardiac Atlas Project. IMCA and LDA were each used to identify a single mode of global remodeling best discriminating the two groups. Logistic regression was employed to determine the association between the remodeling index and MI. Goodness-of-fit results were compared against a baseline logistic model comprising standard clinical indices.
      Results: A single IMCA mode simultaneously describing end-diastolic and end-systolic shapes achieved best results (lowest Deviance, Akaike information criterion and Bayesian information criterion, and the largest area under the receiver-operating-characteristic curve). This mode provided a continuous scale where remodeling can be quantified and visualized, showing that MI patients tend to present larger size and more spherical shape, more bulging of the apex, and thinner wall thickness.
      Conclusions: IMCA enables better characterization of global remodeling than LDA, and can be used to quantify progression of disease and the effect of treatment. These data and results are available from the Cardiac Atlas Project ( http://www.cardiacatlas.org ).
    • References:
      IEEE Trans Biomed Eng. 2004 Nov;51(11):1923-31. (PMID: 15536894)
      JACC Heart Fail. 2014 Oct;2(5):512-22. (PMID: 25194295)
      Bioinformatics. 2011 Aug 15;27(16):2288-95. (PMID: 21737439)
      Radiology. 2000 Aug;216(2):597-602. (PMID: 10924592)
      J Cardiovasc Magn Reson. 2013 Sep 13;15:80. (PMID: 24033990)
      Am J Epidemiol. 2002 Nov 1;156(9):871-81. (PMID: 12397006)
      IEEE Trans Neural Netw. 2003;14(1):195-200. (PMID: 18238001)
      J Am Coll Cardiol. 2002 Mar 20;39(6):1055-60. (PMID: 11897450)
      PLoS One. 2014 Oct 31;9(10):e110243. (PMID: 25360520)
      Physiol Rep. 2013 Jul;1(2):e0007. (PMID: 24303121)
      Med Image Comput Comput Assist Interv. 2008;11(Pt 2):450-7. (PMID: 18982636)
      Trends Ecol Evol. 2004 Feb;19(2):101-8. (PMID: 16701236)
      JACC Cardiovasc Imaging. 2010 Aug;3(8):860-6. (PMID: 20705268)
      JACC Cardiovasc Imaging. 2014 Sep;7(9):870-8. (PMID: 25129518)
      Circulation. 1987 Jul;76(1):44-51. (PMID: 3594774)
      J Cardiovasc Electrophysiol. 2009 Sep;20(9):982-7. (PMID: 19493153)
      Exp Physiol. 2009 May;94(5):578-96. (PMID: 19098087)
      IEEE Trans Med Imaging. 2001 Jan;20(1):2-25. (PMID: 11293688)
      Nat Rev Cardiol. 2011 Oct 25;8(12):673-85. (PMID: 22027657)
      Med Image Comput Comput Assist Interv. 2012;15(Pt 2):502-10. (PMID: 23286086)
      IEEE Trans Inf Technol Biomed. 2010 Jul;14(4):1106-13. (PMID: 20501348)
      J Cardiovasc Magn Reson. 2014 Jul 30;16:56. (PMID: 25160814)
      IEEE Trans Med Imaging. 2014 Feb;33(2):481-94. (PMID: 24184708)
      Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132)
      Am J Cardiol. 2004 Nov 15;94(10):1270-5. (PMID: 15541243)
    • Grant Information:
      UL1 RR025005 United States RR NCRR NIH HHS; UL1-RR-025005 United States RR NCRR NIH HHS; UL1 TR001079 United States TR NCATS NIH HHS; N01HC95169 United States HL NHLBI NIH HHS; UL1-RR-024156 United States RR NCRR NIH HHS; UL1 RR024156 United States RR NCRR NIH HHS; N01-HC-95159 United States HC NHLBI NIH HHS; R01HL087773 United States HL NHLBI NIH HHS; United States Intramural NIH HHS; N01-HC-95169 United States HC NHLBI NIH HHS; N01HC95159 United States HL NHLBI NIH HHS; R01 HL087773 United States HL NHLBI NIH HHS; R01HL121754 United States HL NHLBI NIH HHS; R01 HL121754 United States HL NHLBI NIH HHS; R01 HL091069 United States HL NHLBI NIH HHS; R01HL91069 United States HL NHLBI NIH HHS
    • Publication Date:
      Date Created: 20151105 Date Completed: 20160726 Latest Revision: 20231111
    • Publication Date:
      20231215
    • Accession Number:
      PMC4632345
    • Accession Number:
      10.1186/s12967-015-0709-4
    • Accession Number:
      26531126