Session 5 : <em>Assessing Heterogeneity in Maternal-Child Outcomes: Insights from Machine Learning</em>

This talk will explore the application of machine learning to uncover heterogeneous treatment effects in health outcomes. Drawing on my published and ongoing research, I will discuss how causal forest analysis has been utilized to identify subgroup-specific responses to medical interventions, including hip fracture treatments, the long-term health impacts of very preterm birth, and the mental health consequences of miscarriage. This work will highlight the importance of leveraging advanced methods to guide and optimize healthcare resource allocation, and address disparities in patient outcomes.