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

Xingyu Zhang; Bharath Ambale-Venkatesh; David A. Bluemke; Brett R. Cowan; J. Paul Finn; Alan H. Kadish; Daniel C. Lee; Joao A C Lima; William G. Hundley; Avan Suinesiaputra; Alistair A. Young; Pau Medrano-Gracia

doi:10.1186/s12967-015-0709-4

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

Xingyu Zhang, Bharath Ambale-Venkatesh, David A. Bluemke, Brett R. Cowan, J. Paul Finn, Alan H. Kadish, Daniel C. Lee, Joao A C Lima, William G. Hundley, Avan Suinesiaputra, Alistair A. Young, Pau Medrano-Gracia^*

^*Corresponding author for this work

Medicine, Cardiology Division

Research output: Contribution to journal › Article › peer-review

22 Scopus citations

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 criterionand Bayesian information criterion, and the largest area under thereceiver-operating-characteristiccurve). 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 ).

Original language	English (US)
Article number	343
Journal	Journal of Translational Medicine
Volume	13
Issue number	1
DOIs	https://doi.org/10.1186/s12967-015-0709-4
State	Published - Nov 3 2015

Funding

This project was supported by award numbers R01HL087773 and R01HL121754 from the National Heart, Lung, and Blood Institute. MESA was supported by contracts N01\u2011HC\u201195159 through N01\u2011HC\u201195169 from the NHLBI and by grants UL1\u2011RR\u2011024156 and UL1\u2011RR\u2011025005 from NCRR. DETERMINE was supported by St. Jude Medical, Inc; and the National Heart, Lung and Blood Institute (R01HL91069). A list of participating DETERMINE investigators can be found at http://www.clinicaltrials.gov. David A. Bluemke is supported by the NIH intramural research program. Xingyu Zhang would like to gratefully acknowledge financial support from the China Scholarship Council.

Keywords

Cardiac remodeling
Information maximizing component analysis
Linear discriminant analysis
Logistic regression
Magnetic resonance imaging

ASJC Scopus subject areas

General Biochemistry, Genetics and Molecular Biology

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1186/s12967-015-0709-4

Cite this

Zhang, X., Ambale-Venkatesh, B., Bluemke, D. A., Cowan, B. R., Finn, J. P., Kadish, A. H., Lee, D. C., Lima, J. A. C., Hundley, W. G., Suinesiaputra, A., Young, A. A., & Medrano-Gracia, P. (2015). Information maximizing component analysis of left ventricular remodeling due to myocardial infarction. Journal of Translational Medicine, 13(1), Article 343. https://doi.org/10.1186/s12967-015-0709-4

@article{76728551157a43829205264db0b4be97,

title = "Information maximizing component analysis of left ventricular remodeling due to myocardial infarction",

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 criterionand Bayesian information criterion, and the largest area under thereceiver-operating-characteristiccurve). 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 ).",

keywords = "Cardiac remodeling, Information maximizing component analysis, Linear discriminant analysis, Logistic regression, Magnetic resonance imaging",

author = "Xingyu Zhang and Bharath Ambale-Venkatesh and Bluemke, {David A.} and Cowan, {Brett R.} and Finn, {J. Paul} and Kadish, {Alan H.} and Lee, {Daniel C.} and Lima, {Joao A C} and Hundley, {William G.} and Avan Suinesiaputra and Young, {Alistair A.} and Pau Medrano-Gracia",

note = "Publisher Copyright: {\textcopyright} 2015 Zhang et al.",

year = "2015",

month = nov,

day = "3",

doi = "10.1186/s12967-015-0709-4",

language = "English (US)",

volume = "13",

journal = "Journal of Translational Medicine",

issn = "1479-5876",

publisher = "BioMed Central",

number = "1",

}

TY - JOUR

T1 - Information maximizing component analysis of left ventricular remodeling due to myocardial infarction

AU - Zhang, Xingyu

AU - Ambale-Venkatesh, Bharath

AU - Bluemke, David A.

AU - Cowan, Brett R.

AU - Finn, J. Paul

AU - Kadish, Alan H.

AU - Lee, Daniel C.

AU - Lima, Joao A C

AU - Hundley, William G.

AU - Suinesiaputra, Avan

AU - Young, Alistair A.

AU - Medrano-Gracia, Pau

PY - 2015/11/3

Y1 - 2015/11/3

N2 - 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 criterionand Bayesian information criterion, and the largest area under thereceiver-operating-characteristiccurve). 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 ).

AB - 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 criterionand Bayesian information criterion, and the largest area under thereceiver-operating-characteristiccurve). 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 ).

KW - Cardiac remodeling

KW - Information maximizing component analysis

KW - Linear discriminant analysis

KW - Logistic regression

KW - Magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=84946082272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946082272&partnerID=8YFLogxK

U2 - 10.1186/s12967-015-0709-4

DO - 10.1186/s12967-015-0709-4

M3 - Article

C2 - 26531126

AN - SCOPUS:84946082272

SN - 1479-5876

VL - 13

JO - Journal of Translational Medicine

JF - Journal of Translational Medicine

IS - 1

M1 - 343

ER -

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

Abstract

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this