A Personalized BEST: Characterization of Latent Clinical Classes of Nonischemic Heart Failure That Predict Outcomes and Response to Bucindolol

David P. Kao, Brandie D. Wagner, Alastair D. Robertson, Michael R. Bristow, Brian D Lowes

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Background: Heart failure patients with reduced ejection fraction (HFREF) are heterogenous, and our ability to identify patients likely to respond to therapy is limited. We present a method of identifying disease subtypes using high-dimensional clinical phenotyping and latent class analysis that may be useful in personalizing prognosis and treatment in HFREF. Methods: A total of 1121 patients with nonischemic HFREF from the β-blocker Evaluation of Survival Trial were categorized according to 27 clinical features. Latent class analysis was used to generate two latent class models, LCM A and B, to identify HFREF subtypes. LCM A consisted of features associated with HF pathogenesis, whereas LCM B consisted of markers of HF progression and severity. The Seattle Heart Failure Model (SHFM) Score was also calculated for all patients. Mortality, improvement in left ventricular ejection fraction (LVEF) defined as an increase in LVEF ≥5% and a final LVEF of 35% after 12 months, and effect of bucindolol on both outcomes were compared across HFREF subtypes. Performance of models that included a combination of LCM subtypes and SHFM scores towards predicting mortality and LVEF response was estimated and subsequently validated using leave-one-out cross-validation and data from the Multicenter Oral Carvedilol Heart Failure Assessment Trial. Results: A total of 6 subtypes were identified using LCM A and 5 subtypes using LCM B. Several subtypes resembled familiar clinical phenotypes. Prognosis, improvement in LVEF, and the effect of bucindolol treatment differed significantly between subtypes. Prediction improved with addition of both latent class models to SHFM for both 1-year mortality and LVEF response outcomes. Conclusions: The combination of high-dimensional phenotyping and latent class analysis identifies subtypes of HFREF with implications for prognosis and response to specific therapies that may provide insight into mechanisms of disease. These subtypes may facilitate development of personalized treatment plans.

Original languageEnglish (US)
Article numbere48184
JournalPloS one
Volume7
Issue number11
DOIs
StatePublished - Nov 7 2012

Fingerprint

heart failure
Heart Failure
Stroke Volume
prognosis
phenotype
Mortality
bucindolol
Therapeutics
therapeutics
mouth
pathogenesis
Phenotype
prediction
Survival

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • General

Cite this

A Personalized BEST : Characterization of Latent Clinical Classes of Nonischemic Heart Failure That Predict Outcomes and Response to Bucindolol. / Kao, David P.; Wagner, Brandie D.; Robertson, Alastair D.; Bristow, Michael R.; Lowes, Brian D.

In: PloS one, Vol. 7, No. 11, e48184, 07.11.2012.

Research output: Contribution to journalArticle

Kao, David P. ; Wagner, Brandie D. ; Robertson, Alastair D. ; Bristow, Michael R. ; Lowes, Brian D. / A Personalized BEST : Characterization of Latent Clinical Classes of Nonischemic Heart Failure That Predict Outcomes and Response to Bucindolol. In: PloS one. 2012 ; Vol. 7, No. 11.
@article{81a7b4041c9b4d1abd83bc4bc87c1302,
title = "A Personalized BEST: Characterization of Latent Clinical Classes of Nonischemic Heart Failure That Predict Outcomes and Response to Bucindolol",
abstract = "Background: Heart failure patients with reduced ejection fraction (HFREF) are heterogenous, and our ability to identify patients likely to respond to therapy is limited. We present a method of identifying disease subtypes using high-dimensional clinical phenotyping and latent class analysis that may be useful in personalizing prognosis and treatment in HFREF. Methods: A total of 1121 patients with nonischemic HFREF from the β-blocker Evaluation of Survival Trial were categorized according to 27 clinical features. Latent class analysis was used to generate two latent class models, LCM A and B, to identify HFREF subtypes. LCM A consisted of features associated with HF pathogenesis, whereas LCM B consisted of markers of HF progression and severity. The Seattle Heart Failure Model (SHFM) Score was also calculated for all patients. Mortality, improvement in left ventricular ejection fraction (LVEF) defined as an increase in LVEF ≥5{\%} and a final LVEF of 35{\%} after 12 months, and effect of bucindolol on both outcomes were compared across HFREF subtypes. Performance of models that included a combination of LCM subtypes and SHFM scores towards predicting mortality and LVEF response was estimated and subsequently validated using leave-one-out cross-validation and data from the Multicenter Oral Carvedilol Heart Failure Assessment Trial. Results: A total of 6 subtypes were identified using LCM A and 5 subtypes using LCM B. Several subtypes resembled familiar clinical phenotypes. Prognosis, improvement in LVEF, and the effect of bucindolol treatment differed significantly between subtypes. Prediction improved with addition of both latent class models to SHFM for both 1-year mortality and LVEF response outcomes. Conclusions: The combination of high-dimensional phenotyping and latent class analysis identifies subtypes of HFREF with implications for prognosis and response to specific therapies that may provide insight into mechanisms of disease. These subtypes may facilitate development of personalized treatment plans.",
author = "Kao, {David P.} and Wagner, {Brandie D.} and Robertson, {Alastair D.} and Bristow, {Michael R.} and Lowes, {Brian D}",
year = "2012",
month = "11",
day = "7",
doi = "10.1371/journal.pone.0048184",
language = "English (US)",
volume = "7",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "11",

}

TY - JOUR

T1 - A Personalized BEST

T2 - Characterization of Latent Clinical Classes of Nonischemic Heart Failure That Predict Outcomes and Response to Bucindolol

AU - Kao, David P.

AU - Wagner, Brandie D.

AU - Robertson, Alastair D.

AU - Bristow, Michael R.

AU - Lowes, Brian D

PY - 2012/11/7

Y1 - 2012/11/7

N2 - Background: Heart failure patients with reduced ejection fraction (HFREF) are heterogenous, and our ability to identify patients likely to respond to therapy is limited. We present a method of identifying disease subtypes using high-dimensional clinical phenotyping and latent class analysis that may be useful in personalizing prognosis and treatment in HFREF. Methods: A total of 1121 patients with nonischemic HFREF from the β-blocker Evaluation of Survival Trial were categorized according to 27 clinical features. Latent class analysis was used to generate two latent class models, LCM A and B, to identify HFREF subtypes. LCM A consisted of features associated with HF pathogenesis, whereas LCM B consisted of markers of HF progression and severity. The Seattle Heart Failure Model (SHFM) Score was also calculated for all patients. Mortality, improvement in left ventricular ejection fraction (LVEF) defined as an increase in LVEF ≥5% and a final LVEF of 35% after 12 months, and effect of bucindolol on both outcomes were compared across HFREF subtypes. Performance of models that included a combination of LCM subtypes and SHFM scores towards predicting mortality and LVEF response was estimated and subsequently validated using leave-one-out cross-validation and data from the Multicenter Oral Carvedilol Heart Failure Assessment Trial. Results: A total of 6 subtypes were identified using LCM A and 5 subtypes using LCM B. Several subtypes resembled familiar clinical phenotypes. Prognosis, improvement in LVEF, and the effect of bucindolol treatment differed significantly between subtypes. Prediction improved with addition of both latent class models to SHFM for both 1-year mortality and LVEF response outcomes. Conclusions: The combination of high-dimensional phenotyping and latent class analysis identifies subtypes of HFREF with implications for prognosis and response to specific therapies that may provide insight into mechanisms of disease. These subtypes may facilitate development of personalized treatment plans.

AB - Background: Heart failure patients with reduced ejection fraction (HFREF) are heterogenous, and our ability to identify patients likely to respond to therapy is limited. We present a method of identifying disease subtypes using high-dimensional clinical phenotyping and latent class analysis that may be useful in personalizing prognosis and treatment in HFREF. Methods: A total of 1121 patients with nonischemic HFREF from the β-blocker Evaluation of Survival Trial were categorized according to 27 clinical features. Latent class analysis was used to generate two latent class models, LCM A and B, to identify HFREF subtypes. LCM A consisted of features associated with HF pathogenesis, whereas LCM B consisted of markers of HF progression and severity. The Seattle Heart Failure Model (SHFM) Score was also calculated for all patients. Mortality, improvement in left ventricular ejection fraction (LVEF) defined as an increase in LVEF ≥5% and a final LVEF of 35% after 12 months, and effect of bucindolol on both outcomes were compared across HFREF subtypes. Performance of models that included a combination of LCM subtypes and SHFM scores towards predicting mortality and LVEF response was estimated and subsequently validated using leave-one-out cross-validation and data from the Multicenter Oral Carvedilol Heart Failure Assessment Trial. Results: A total of 6 subtypes were identified using LCM A and 5 subtypes using LCM B. Several subtypes resembled familiar clinical phenotypes. Prognosis, improvement in LVEF, and the effect of bucindolol treatment differed significantly between subtypes. Prediction improved with addition of both latent class models to SHFM for both 1-year mortality and LVEF response outcomes. Conclusions: The combination of high-dimensional phenotyping and latent class analysis identifies subtypes of HFREF with implications for prognosis and response to specific therapies that may provide insight into mechanisms of disease. These subtypes may facilitate development of personalized treatment plans.

UR - http://www.scopus.com/inward/record.url?scp=84868697486&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868697486&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0048184

DO - 10.1371/journal.pone.0048184

M3 - Article

C2 - 23144856

AN - SCOPUS:84868697486

VL - 7

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 11

M1 - e48184

ER -