Multivariate adaptive regression splines analysis to predict biomarkers of spontaneous preterm birth

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Objective To develop classification models of demographic/clinical factors and biomarker data from spontaneous preterm birth in African Americans and Caucasians. Design Secondary analysis of biomarker data using multivariate adaptive regression splines (MARS), a supervised machine learning algorithm method. Setting Analysis of data on 36 biomarkers from 191 women was reduced by MARS to develop predictive models for preterm birth in African Americans and Caucasians. Samples Maternal plasma, cord plasma collected at admission for preterm or term labor and amniotic fluid at delivery. Methods Data were partitioned into training and testing sets. Variable importance, a relative indicator (0-100%) and area under the receiver operating characteristic curve (AUC) characterized results. Results Multivariate adaptive regression splines generated models for combined and racially stratified biomarker data. Clinical and demographic data did not contribute to the model. Racial stratification of data produced distinct models in all three compartments. In African Americans maternal plasma samples IL-1RA, TNF-α, angiopoietin 2, TNFRI, IL-5, MIP1α, IL-1β and TGF-α modeled preterm birth (AUC train: 0.98, AUC test: 0.86). In Caucasians TNFR1, ICAM-1 and IL-1RA contributed to the model (AUC train: 0.84, AUC test: 0.68). African Americans cord plasma samples produced IL-12P70, IL-8 (AUC train: 0.82, AUC test: 0.66). Cord plasma in Caucasians modeled IGFII, PDGFBB, TGF-β1, IL-12P70, and TIMP1 (AUC train: 0.99, AUC test: 0.82). Amniotic fluid in African Americans modeled FasL, TNFRII, RANTES, KGF, IGFI (AUC train: 0.95, AUC test: 0.89) and in Caucasians, TNF-α, MCP3, TGF-β3, TNFR1 and angiopoietin 2 (AUC train: 0.94 AUC test: 0.79). Conclusions Multivariate adaptive regression splines models multiple biomarkers associated with preterm birth and demonstrated racial disparity.

Original languageEnglish (US)
Pages (from-to)382-391
Number of pages10
JournalActa Obstetricia et Gynecologica Scandinavica
Volume93
Issue number4
DOIs
StatePublished - 2014

Fingerprint

Premature Birth
Area Under Curve
Biomarkers
Regression Analysis
African Americans
Angiopoietin-2
Receptors, Tumor Necrosis Factor, Type I
Amniotic Fluid
Interleukin-1
Mothers
Demography
Chemokine CCL5
Interleukin-5
Intercellular Adhesion Molecule-1
Interleukin-8
ROC Curve

Keywords

  • biomarkers
  • cytokines
  • inflammation
  • interactions
  • Prediction model
  • preterm birth

ASJC Scopus subject areas

  • Obstetrics and Gynecology

Cite this

@article{22dc650f5b014b15a9914abfad42e116,
title = "Multivariate adaptive regression splines analysis to predict biomarkers of spontaneous preterm birth",
abstract = "Objective To develop classification models of demographic/clinical factors and biomarker data from spontaneous preterm birth in African Americans and Caucasians. Design Secondary analysis of biomarker data using multivariate adaptive regression splines (MARS), a supervised machine learning algorithm method. Setting Analysis of data on 36 biomarkers from 191 women was reduced by MARS to develop predictive models for preterm birth in African Americans and Caucasians. Samples Maternal plasma, cord plasma collected at admission for preterm or term labor and amniotic fluid at delivery. Methods Data were partitioned into training and testing sets. Variable importance, a relative indicator (0-100{\%}) and area under the receiver operating characteristic curve (AUC) characterized results. Results Multivariate adaptive regression splines generated models for combined and racially stratified biomarker data. Clinical and demographic data did not contribute to the model. Racial stratification of data produced distinct models in all three compartments. In African Americans maternal plasma samples IL-1RA, TNF-α, angiopoietin 2, TNFRI, IL-5, MIP1α, IL-1β and TGF-α modeled preterm birth (AUC train: 0.98, AUC test: 0.86). In Caucasians TNFR1, ICAM-1 and IL-1RA contributed to the model (AUC train: 0.84, AUC test: 0.68). African Americans cord plasma samples produced IL-12P70, IL-8 (AUC train: 0.82, AUC test: 0.66). Cord plasma in Caucasians modeled IGFII, PDGFBB, TGF-β1, IL-12P70, and TIMP1 (AUC train: 0.99, AUC test: 0.82). Amniotic fluid in African Americans modeled FasL, TNFRII, RANTES, KGF, IGFI (AUC train: 0.95, AUC test: 0.89) and in Caucasians, TNF-α, MCP3, TGF-β3, TNFR1 and angiopoietin 2 (AUC train: 0.94 AUC test: 0.79). Conclusions Multivariate adaptive regression splines models multiple biomarkers associated with preterm birth and demonstrated racial disparity.",
keywords = "biomarkers, cytokines, inflammation, interactions, Prediction model, preterm birth",
author = "Ramkumar Menon and Geeta Bhat and George Saade and Heidi Spratt",
year = "2014",
doi = "10.1111/aogs.12344",
language = "English (US)",
volume = "93",
pages = "382--391",
journal = "Acta Obstetricia et Gynecologica Scandinavica",
issn = "0001-6349",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Multivariate adaptive regression splines analysis to predict biomarkers of spontaneous preterm birth

AU - Menon, Ramkumar

AU - Bhat, Geeta

AU - Saade, George

AU - Spratt, Heidi

PY - 2014

Y1 - 2014

N2 - Objective To develop classification models of demographic/clinical factors and biomarker data from spontaneous preterm birth in African Americans and Caucasians. Design Secondary analysis of biomarker data using multivariate adaptive regression splines (MARS), a supervised machine learning algorithm method. Setting Analysis of data on 36 biomarkers from 191 women was reduced by MARS to develop predictive models for preterm birth in African Americans and Caucasians. Samples Maternal plasma, cord plasma collected at admission for preterm or term labor and amniotic fluid at delivery. Methods Data were partitioned into training and testing sets. Variable importance, a relative indicator (0-100%) and area under the receiver operating characteristic curve (AUC) characterized results. Results Multivariate adaptive regression splines generated models for combined and racially stratified biomarker data. Clinical and demographic data did not contribute to the model. Racial stratification of data produced distinct models in all three compartments. In African Americans maternal plasma samples IL-1RA, TNF-α, angiopoietin 2, TNFRI, IL-5, MIP1α, IL-1β and TGF-α modeled preterm birth (AUC train: 0.98, AUC test: 0.86). In Caucasians TNFR1, ICAM-1 and IL-1RA contributed to the model (AUC train: 0.84, AUC test: 0.68). African Americans cord plasma samples produced IL-12P70, IL-8 (AUC train: 0.82, AUC test: 0.66). Cord plasma in Caucasians modeled IGFII, PDGFBB, TGF-β1, IL-12P70, and TIMP1 (AUC train: 0.99, AUC test: 0.82). Amniotic fluid in African Americans modeled FasL, TNFRII, RANTES, KGF, IGFI (AUC train: 0.95, AUC test: 0.89) and in Caucasians, TNF-α, MCP3, TGF-β3, TNFR1 and angiopoietin 2 (AUC train: 0.94 AUC test: 0.79). Conclusions Multivariate adaptive regression splines models multiple biomarkers associated with preterm birth and demonstrated racial disparity.

AB - Objective To develop classification models of demographic/clinical factors and biomarker data from spontaneous preterm birth in African Americans and Caucasians. Design Secondary analysis of biomarker data using multivariate adaptive regression splines (MARS), a supervised machine learning algorithm method. Setting Analysis of data on 36 biomarkers from 191 women was reduced by MARS to develop predictive models for preterm birth in African Americans and Caucasians. Samples Maternal plasma, cord plasma collected at admission for preterm or term labor and amniotic fluid at delivery. Methods Data were partitioned into training and testing sets. Variable importance, a relative indicator (0-100%) and area under the receiver operating characteristic curve (AUC) characterized results. Results Multivariate adaptive regression splines generated models for combined and racially stratified biomarker data. Clinical and demographic data did not contribute to the model. Racial stratification of data produced distinct models in all three compartments. In African Americans maternal plasma samples IL-1RA, TNF-α, angiopoietin 2, TNFRI, IL-5, MIP1α, IL-1β and TGF-α modeled preterm birth (AUC train: 0.98, AUC test: 0.86). In Caucasians TNFR1, ICAM-1 and IL-1RA contributed to the model (AUC train: 0.84, AUC test: 0.68). African Americans cord plasma samples produced IL-12P70, IL-8 (AUC train: 0.82, AUC test: 0.66). Cord plasma in Caucasians modeled IGFII, PDGFBB, TGF-β1, IL-12P70, and TIMP1 (AUC train: 0.99, AUC test: 0.82). Amniotic fluid in African Americans modeled FasL, TNFRII, RANTES, KGF, IGFI (AUC train: 0.95, AUC test: 0.89) and in Caucasians, TNF-α, MCP3, TGF-β3, TNFR1 and angiopoietin 2 (AUC train: 0.94 AUC test: 0.79). Conclusions Multivariate adaptive regression splines models multiple biomarkers associated with preterm birth and demonstrated racial disparity.

KW - biomarkers

KW - cytokines

KW - inflammation

KW - interactions

KW - Prediction model

KW - preterm birth

UR - http://www.scopus.com/inward/record.url?scp=84897006299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897006299&partnerID=8YFLogxK

U2 - 10.1111/aogs.12344

DO - 10.1111/aogs.12344

M3 - Article

VL - 93

SP - 382

EP - 391

JO - Acta Obstetricia et Gynecologica Scandinavica

JF - Acta Obstetricia et Gynecologica Scandinavica

SN - 0001-6349

IS - 4

ER -