The increasing complexity of today’s biomedical research requires more than traditional, single point-of-view approaches. In particular, data-driven approaches that can reveal patterns in massive heterogeneous datasets and make clinically relevant predictions are becoming increasingly common in translational research. I have a strong, multi-disciplinary background in the analysis of real-world data such as those from the electronic health records (EHRs) and medical claims, data integration, predictive modeling, causal modeling and inference, mediation and moderation analysis, patient-reported outcomes, psychometric analysis, social media data analysis, and social media-delivered health interventions. Together, my areas of expertise serve an overarching research theme: data-driven precision health supporting clinical (shared) decision making and multilevel health interventions. Under the overarching theme, my research areas and expertise can be divided into four key methodologies: (1) EHR-based phenotyping and risk stratification – the identification of sub-populations with certain conditions or at higher risk for diseases; (2) Causal modeling and inference – the examination of causal relationships and pathways in clinical research, particularly treatment studies; (3) Patient-reported outcomes (PROs) in clinical and public health applications – the development, validation, assessment, analysis, and reporting of PROs among various populations, especially vulnerable populations; and (4) Social media analysis and social media-delivered intervention – mining social media data to study health behavior and health outcomes in various populations and developing social media-delivered interventions that promote public and consumer health.

My areas of expertise serve an overarching research theme: data-driven precision and public health supporting clinical (shared) decision making and multilevel health interventions. Under the overarching theme, my research areas and expertise can be divided into: 1) Electronic health records (EHR)-based phenotyping and risk stratification – the identification of sub-populations with certain conditions or at higher risk for diseases; 2) Causal modeling and inference – the examination of causal relationships and pathways in clinical and public health research, particularly treatment studies; 3) Patient-reported outcomes (PROs) in clinical and public health applications – the development, validation, assessment, analysis, and reporting of PROs among various populations, especially vulnerable populations; and 4) Social media analysis and social media-delivered intervention – mining social media data to study health behavior and health outcomes in various populations and developing social media-delivered interventions that promote public and consumer health.

0000-0003-0587-4105