Cluster analysis identifying clinical phenotypes of preterm birth and related maternal and neonatal outcomes from the Brazilian Multicentre Study on Preterm Birth

Abstract

Objective: To explore a conceptual framework of clinical conditions associated with preterm birth (PTB) by cluster analysis, assessing determinants for different PTB subtypes and related maternal and neonatal outcomes.

Methods: Secondary analysis of the Brazilian Multicentre Study on Preterm Birth of 33 740 births in 20 maternity hospitals between April 2011 and July 2012. In accordance with a prototype concept based on maternal, fetal, and placental conditions, an adapted k-means model and fuzzy algorithm were used to identify clusters using predefined conditions. The mains outcomes were phenotype clusters and maternal and neonatal outcomes.

Results: Among 4150 PTBs, three clusters of PTB phenotypes were identified: women who had PTB without any predefined conditions; women with mixed conditions; and women who had pre-eclampsia, eclampsia, HELLP syndrome and fetal growth restriction. The prevalence of different preterm subtypes differed significantly in the three clusters, varying from 80.95% of provider-initiated PTBs in cluster 3-6.62% in cluster 1 (P<0.001). Although some maternal characteristics differed among the clusters, maternal and neonatal outcomes did not.

Conclusions: The analysis identified three clusters with distinct phenotypes. Women from the different clusters had different subtypes of PTB and maternal and pregnancy characteristics.

Keywords: Cluster; Maternal outcomes; Neonatal outcomes; Phenotypes; Preterm birth; k-means.