Emma is completing her MD/PhD at University of Wisconsin-Madison, where she works with Matthew Churpek in the ICU Data Science Lab. Her work focuses on how we can better target medical treatments to the right patients using tools from machine learning and causal inference. She completed her master’s degree in bioinformatics in 2018, working with Dr. Sara Mostafavi at the University of British Columbia. Her current projects use clinical data to predict personalized estimates of treatment response for therapies used to treat critical illness and malignancies.

Education

Yale University, Molecular Biochemistry and Biophysics, 2016

University of British Columbia, Master’s in Bioinformatics, 2018

UW-Madison, MD/PhD, 2019-present

Projects

Predicting individualized treatment effect in critical care trials

The efficacy of a particular therapy is typically summarized across the trial population as an average treatment effect. However, averages may mask heterogeneity in treatment effect, with some individuals benefitting more than the average and some individuals benefiting less than the average. We have found that individualized treatment effect models developed in a single critical care trial are able to identify groups of individuals with varying treatment response, highlighting the potential of these models to inform treatment decisions, once validated.

  • Seitz, Kevin., Spicer, A., Casey, J., Buell, K., Qian, E., Graham Linck, E., Churpek, Matt., et al. “Individualized treatment effects of bougie vs stylet for tracheal intubation in critical illness”. American Journal of Respiratory and Critical Care Medicine. 2023.

  • Afshar, M., Graham Linck, E., Spicer, A., Rotrosen, J., Salisbury-Afshar, E., Sinha, P., Semler, C., Churpek, M. “Machine Learning-Driven Analysis of Individualized Treatment Effects Comparing Buprenorphine and Naltrexone in Opioid Use Disorder Relapse Prevention”. Journal of Addiction Medicine. 2024.

  • Graham Linck, E., Goligher, E., Semler, M., Churpek, M. “Towards Precision in Critical Care Research: Methods for Observational and Interventional Studies”. Critical Care Medicine. 2024.

Other research interests

  • Combining observational and randomized trial data to improve individualized treatment effect models
  • Predicting individualized treatment effects for time-to-event outcomes across cancer trials