Dr. Mila Sun is an assistant professor of population health sciences in the Division of Biostatistics. She joins Weill Cornell Medicine from the Harvard T.H. Chan School of Public Health, where she was a postdoctoral researcher.
How did you first become involved in your field?
My path in biostatistics started during my PhD training at McGill University, where I focused on causal quantile treatment effects. While developing methodology, I collaborated on projects related to drug safety, efficacy, and cognitive impairment, which demonstrated the impact statistical methods can have on clinical questions.
Dr. Mila Sun
During my postdoctoral fellowship at the Harvard T.H. Chan School of Public Health, I broadened my work in causal inference to include trial emulation, matching, network interference, and methods for handling missing data using large-scale electronic health records (EHR). At the same time, I built close collaborations with the neurology department at Massachusetts General Hospital. Working with clinicians not only deepened my appreciation for the complexities of real-world data but also reinforced how much can be accomplished when methodologists and physicians tackle questions together.
What expertise do you bring to this role?
My research expertise is centered on causal inference, with a focus on developing methods that address real-world complexities, including skewed data, missingness, trial emulation, network interference, time-varying treatment, and partial compliance. I work across observational data, including large-scale EHR and claims data, and clinical trials, where methodological challenges are particularly relevant.
My applied work extends to areas such as COVID-19 and health policy, obesity, antihypertensive treatment, and lung cancer. In addition to methodological development, I have collaborated with clinicians on studies of cognitive impairment, stroke, seizure, epilepsy, fall-related injuries, and other neurological disorders. Through these collaborations, I aim to ensure that advanced methods are rigorous and informative to clinical practice and public health.
What brings you to Weill Cornell Medicine?
I was drawn to Weill Cornell Medicine because of its collaborative environment and the strength of the Department of Population Health Sciences, which provides an ideal platform to advance methodological research while addressing important clinical and public health challenges. The department’s vision and interdisciplinary culture create opportunities to connect statistical innovation with real-world applications. The broader academic ecosystem, spanning Weill Cornell Medicine, NewYork-Presbyterian, and Memorial Sloan Kettering Cancer Center, also brings together exceptionally talented researchers. This environment fosters collaborations that inspire the development of new statistical and computational tools while generating evidence to improve patient outcomes.
Are there any trends or issues you are currently following in your field?
I am particularly interested in how causal inference methodology is shifting to address the complexities of modern health data. Traditional approaches often rely on assumptions that are too restrictive, and there is growing need for methods that better account for transportability, partial compliance in clinical trials, and network interference.
Precision medicine highlights the importance of quantifying treatment heterogeneity and ensuring that evidence can be generalized across patient populations. At the same time, the increasing availability of multi-source, large-scale EHR and clinical data is reshaping the field. These resources create exciting opportunities for generating evidence at scale. However, they also raise challenges related to missing data, measurement heterogeneity, and data integration across systems. I am following how these methodological and data-driven advances intersect with broad public health and biomedical questions. These are areas where rigorous evidence is critical, and new approaches can have a substantial impact.
- Highlights