Main content
Assistant Professor gets grant for Race/Ethnicity-Specific Algorithms of Chronic Stress Exposures for Preterm Birth Risk: Machine Learning Approach
Sangmi Kim

The National Institute of Nursing Research (NINR) has awarded its grant for Race/Ethnicity-Specific Algorithms of Chronic Stress Exposures for Preterm Birth Risk: Machine Learning Approach to Sangmi Kim, PhD, MPH, RN, an assistant professor with Emory University’s Nell Hodgson Woodruff School of Nursing. The K01 Research Project grant provides funding for three years of $440,863 to develop machine learning algorithms to compute women’s complex chronic stress exposures and then identify women at high PTB risk.  

Racial/ethnic disparities in preterm birth (PTB) are persistent in the U.S., with a higher prevalence of PTB in non-Hispanic (N-H) Black women than their N-H White counterparts. However, the underlying mechanism of such Black-White differences is not well understood. Even extensive biomedical, behavioral, and socio-demographic risk factors can explain only about half of the PTB incidence. Chronic stress has received significant attention as a robust predictor of PTB, particularly among racial/ethnic minority groups. Literature shows inconsistent evidence on the relationships between race/ethnicity, chronic stress, and PTB, mainly because of the complexities involved in assessing women’s chronic stress exposures. Accurate chronic stress measures should capture the nature of stressors: cumulative, interactive, and population-specific. In this regard, conventional statistical models (e.g., linear regression) have limited ability to model chronic stress exposures with high precision.  

 The K01 Research Project grant gives Dr. Kim and her team the opportunity to develop simple, accurate, and explainable machine learning algorithms for chronic stress exposures to predict PTB risk by building a hybrid algorithm (multivariate adaptive regression splines + deep neural networks) specific to N-H White and N-H Black women and computing SHAP (SHapley Additive exPlanations) values.  

Dr. Sangmi Kim is an Assistant Professor tenure track and joined the Nell Hodgson Woodruff School of Nursing in August 2019. Dr. Kim earned her doctoral degree at the University Of Pennsylvania School Of Nursing with her dissertation addressing the role of chronic stress in the different maternal age patterns of PTB among four major racial/ethnic groups of pregnant women in the U.S. Her former training in Health Demography during a master’s program contributed to shaping her areas of research that analyze population-level health phenomena through biopsychosocial and cultural lenses. Her research in this field continued and deepened during her two-year postdoc training at Duke University School of Nursing. Her postdoctoral research proposed to use machine learning in order to investigate racial/ethnic groups’ potentially unique exposures and responses to chronic social stress that would determine an individual woman’s likelihood of PTB.

For more information on Dr. Sangmi Kim, visit her faculty profile. To learn more about the K01 Research Project grant, visit the National Institute of Health website.


Recent News