A three-component biomarker panel for prediction of dengue hemorrhagic fever

Allan R. Brasier, Hyunsu Ju, Josefina Garcia, Heidi Spratt, Sundar S. Victor, Brett M. Forshey, Eric S. Halsey, Guillermo Comach, Gloria Sierra, Patrick J. Blair, Claudio Rocha, Amy C. Morrison, Thomas W. Scott, Isabel Bazan, Tadeusz J. Kochel, Iris Villalobos, Carlos Espino

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

Dengue virus infections are a major cause of morbidity in tropical countries. Early detection of dengue hemorrhagic fever (DHF) may help identify individuals that would benefit from intensive therapy. Predictive modeling was performed using 11 laboratory values of 51 individuals (38 DF and 13 DHF) obtained on initial presentation using logistic regression. We produced a robust model with an area under the curve of 0.9615 that retained IL-10 levels, platelets, and lymphocytes as the major predictive features. A classification and regression tree was developed on these features that were 86% accurate on cross-validation. The IL-10 levels and platelet counts were also identified as the most informative features associated with DHF using a Random Forest classifier. In the presence of polymerase chain reaction-proven acute dengue infections, we suggest a complete blood count and rapid measurement of IL-10 can assist in the triage of potential DHF cases for close follow-up or clinical intervention improving clinical outcome.

Original languageEnglish (US)
Pages (from-to)341-348
Number of pages8
JournalAmerican Journal of Tropical Medicine and Hygiene
Volume86
Issue number2
DOIs
StatePublished - Feb 2012

Fingerprint

Severe Dengue
Biomarkers
Interleukin-10
Dengue Virus
Blood Cell Count
Dengue
Triage
Virus Diseases
Platelet Count
Area Under Curve
Blood Platelets
Logistic Models
Lymphocytes
Morbidity
Polymerase Chain Reaction
Infection

ASJC Scopus subject areas

  • Parasitology
  • Infectious Diseases
  • Virology

Cite this

A three-component biomarker panel for prediction of dengue hemorrhagic fever. / Brasier, Allan R.; Ju, Hyunsu; Garcia, Josefina; Spratt, Heidi; Victor, Sundar S.; Forshey, Brett M.; Halsey, Eric S.; Comach, Guillermo; Sierra, Gloria; Blair, Patrick J.; Rocha, Claudio; Morrison, Amy C.; Scott, Thomas W.; Bazan, Isabel; Kochel, Tadeusz J.; Villalobos, Iris; Espino, Carlos.

In: American Journal of Tropical Medicine and Hygiene, Vol. 86, No. 2, 02.2012, p. 341-348.

Research output: Contribution to journalArticle

Brasier, AR, Ju, H, Garcia, J, Spratt, H, Victor, SS, Forshey, BM, Halsey, ES, Comach, G, Sierra, G, Blair, PJ, Rocha, C, Morrison, AC, Scott, TW, Bazan, I, Kochel, TJ, Villalobos, I & Espino, C 2012, 'A three-component biomarker panel for prediction of dengue hemorrhagic fever', American Journal of Tropical Medicine and Hygiene, vol. 86, no. 2, pp. 341-348. https://doi.org/10.4269/ajtmh.2012.11-0469
Brasier, Allan R. ; Ju, Hyunsu ; Garcia, Josefina ; Spratt, Heidi ; Victor, Sundar S. ; Forshey, Brett M. ; Halsey, Eric S. ; Comach, Guillermo ; Sierra, Gloria ; Blair, Patrick J. ; Rocha, Claudio ; Morrison, Amy C. ; Scott, Thomas W. ; Bazan, Isabel ; Kochel, Tadeusz J. ; Villalobos, Iris ; Espino, Carlos. / A three-component biomarker panel for prediction of dengue hemorrhagic fever. In: American Journal of Tropical Medicine and Hygiene. 2012 ; Vol. 86, No. 2. pp. 341-348.
@article{f464910a61ce47618b7a3787fb9a664c,
title = "A three-component biomarker panel for prediction of dengue hemorrhagic fever",
abstract = "Dengue virus infections are a major cause of morbidity in tropical countries. Early detection of dengue hemorrhagic fever (DHF) may help identify individuals that would benefit from intensive therapy. Predictive modeling was performed using 11 laboratory values of 51 individuals (38 DF and 13 DHF) obtained on initial presentation using logistic regression. We produced a robust model with an area under the curve of 0.9615 that retained IL-10 levels, platelets, and lymphocytes as the major predictive features. A classification and regression tree was developed on these features that were 86{\%} accurate on cross-validation. The IL-10 levels and platelet counts were also identified as the most informative features associated with DHF using a Random Forest classifier. In the presence of polymerase chain reaction-proven acute dengue infections, we suggest a complete blood count and rapid measurement of IL-10 can assist in the triage of potential DHF cases for close follow-up or clinical intervention improving clinical outcome.",
author = "Brasier, {Allan R.} and Hyunsu Ju and Josefina Garcia and Heidi Spratt and Victor, {Sundar S.} and Forshey, {Brett M.} and Halsey, {Eric S.} and Guillermo Comach and Gloria Sierra and Blair, {Patrick J.} and Claudio Rocha and Morrison, {Amy C.} and Scott, {Thomas W.} and Isabel Bazan and Kochel, {Tadeusz J.} and Iris Villalobos and Carlos Espino",
year = "2012",
month = "2",
doi = "10.4269/ajtmh.2012.11-0469",
language = "English (US)",
volume = "86",
pages = "341--348",
journal = "American Journal of Tropical Medicine and Hygiene",
issn = "0002-9637",
publisher = "American Society of Tropical Medicine and Hygiene",
number = "2",

}

TY - JOUR

T1 - A three-component biomarker panel for prediction of dengue hemorrhagic fever

AU - Brasier, Allan R.

AU - Ju, Hyunsu

AU - Garcia, Josefina

AU - Spratt, Heidi

AU - Victor, Sundar S.

AU - Forshey, Brett M.

AU - Halsey, Eric S.

AU - Comach, Guillermo

AU - Sierra, Gloria

AU - Blair, Patrick J.

AU - Rocha, Claudio

AU - Morrison, Amy C.

AU - Scott, Thomas W.

AU - Bazan, Isabel

AU - Kochel, Tadeusz J.

AU - Villalobos, Iris

AU - Espino, Carlos

PY - 2012/2

Y1 - 2012/2

N2 - Dengue virus infections are a major cause of morbidity in tropical countries. Early detection of dengue hemorrhagic fever (DHF) may help identify individuals that would benefit from intensive therapy. Predictive modeling was performed using 11 laboratory values of 51 individuals (38 DF and 13 DHF) obtained on initial presentation using logistic regression. We produced a robust model with an area under the curve of 0.9615 that retained IL-10 levels, platelets, and lymphocytes as the major predictive features. A classification and regression tree was developed on these features that were 86% accurate on cross-validation. The IL-10 levels and platelet counts were also identified as the most informative features associated with DHF using a Random Forest classifier. In the presence of polymerase chain reaction-proven acute dengue infections, we suggest a complete blood count and rapid measurement of IL-10 can assist in the triage of potential DHF cases for close follow-up or clinical intervention improving clinical outcome.

AB - Dengue virus infections are a major cause of morbidity in tropical countries. Early detection of dengue hemorrhagic fever (DHF) may help identify individuals that would benefit from intensive therapy. Predictive modeling was performed using 11 laboratory values of 51 individuals (38 DF and 13 DHF) obtained on initial presentation using logistic regression. We produced a robust model with an area under the curve of 0.9615 that retained IL-10 levels, platelets, and lymphocytes as the major predictive features. A classification and regression tree was developed on these features that were 86% accurate on cross-validation. The IL-10 levels and platelet counts were also identified as the most informative features associated with DHF using a Random Forest classifier. In the presence of polymerase chain reaction-proven acute dengue infections, we suggest a complete blood count and rapid measurement of IL-10 can assist in the triage of potential DHF cases for close follow-up or clinical intervention improving clinical outcome.

UR - http://www.scopus.com/inward/record.url?scp=84863396299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863396299&partnerID=8YFLogxK

U2 - 10.4269/ajtmh.2012.11-0469

DO - 10.4269/ajtmh.2012.11-0469

M3 - Article

VL - 86

SP - 341

EP - 348

JO - American Journal of Tropical Medicine and Hygiene

JF - American Journal of Tropical Medicine and Hygiene

SN - 0002-9637

IS - 2

ER -