Open AccessMultivariate adaptive regression splines analysis to predict biomarkers of spontaneous preterm birth
Author(s) -
Me Ramkumar,
Bhat Geeta,
Saade George R.,
Spratt Heidi
Publication year - 2014
Publication title -
acta obstetricia et gynecologica scandinavica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.401
H-Index - 102
eISSN - 1600-0412
pISSN - 0001-6349
DOI - 10.1111/aogs.12344
Subject(s) - medicine , multivariate adaptive regression splines , angiopoietin 2 , biomarker , receiver operating characteristic , multivariate statistics , area under the curve , regression analysis , obstetrics , statistics , bayesian multivariate linear regression , biology , biochemistry , mathematics , vascular endothelial growth factor , vegf receptors
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 ‐1 RA , TNF ‐α, angiopoietin 2, TNFRI , IL ‐5, MIP 1α, IL ‐1β and TGF ‐α modeled preterm birth ( AUC train: 0.98, AUC test: 0.86). In Caucasians TNFR 1, ICAM ‐1 and IL ‐1 RA 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 ‐β 1 , IL ‐12P70, and TIMP 1 ( 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, MCP 3, TGF ‐β 3 , TNFR 1 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.