You are here
Post-Doctoral Fellow Kim Submits NIH R21 Application
Kudos to post-doctoral fellow Kate Kim and her entire team for the submission of their NIH R21 application entitled "The Influences of Chronic Stress on Preterm Birth: Race/Ethnicity Specific Algorithms Using a Machine Learning Approach." This proposal requests funding for a two-year period with a start date of April 1, 2019.
Racial/ethnic disparities in preterm birth (PTB) are persistent in the U.S. with a higher prevalence of PTB among racial/ethnic minority women than their non-Hispanic (N-H) White counterparts. However, the underlying mechanism of such racial/ethnic differences is not well understood. Even a large number of biomedical, behavioral, and sociodemographic risk factors could explain only about a half of the PTB incidence. Instead, chronic stress has received considerable attention among racial/ethnic minority groups as a robust predictor of PTB. Nevertheless, the existing chronic stress models produced inconsistent or even conflicting results on the chronic stress-PTB association mainly due to a potential heterogeneity of the chronic stress pathways to PTB in different racial/ethnic minority groups
The purpose of this study is to build chronic stress algorithms for PTB with high predictive power unique to each of four major racial/ethnic groups of pregnant women in the U.S. (e.g., N-H White, N-H Black, Hispanic, and Asian). The specific aims are to a) evaluate the performance of three ML algorithms of chronic stress for PTB—Random Forest, Multivariate Adaptive Regression Splines, and Artificial Neural Network—in each racial/ethnic group using the sensitivity, specificity, and area under the receiver operating characteristic curve; b) determine the racial/ethnic differences in the significant chronic stressors and their effect on PTB.
The long-term goals are to (a) ascertain chronic stress risk profiles for PTB unique to each race/ethnicity; (b) develop valid tools to aid care providers’ decision-making; (c) optimize the allocation of the limited prenatal care resources to high-risk women via algorithm-based risk calculation. This study could efficiently reduce the racial/ethnic disparities in PTB by providing women of different race/ethnicity with personalized solutions to strengthen their reproductive health potential by mitigating their chronic stress.