Mission Statement
My long-term research interest is to accelerate clinical and translational science using electronic data while minimizing study design biases and optimizing study results’ generalizability. My approach combines formal methods and socio-technical approaches. I combine text knowledge engineering and health data analytics to improve the efficiency and generalizability of clinical research. My co-authors and I have created a distribution-based method for quantifying the collective generalizability of multiple clinical trials and a novel generalizability index for study traits (GIST), which have enabled scalable and proactive clinical study generalizability assessment. My team also explore the symbiosis between knowledge representation and natural language processing for text knowledge engineering, as reflected in our work on EliXR. I aim to advance the field of clinical research informatics on several fronts, including text knowledge engineering, aggregate analysis of clinical studies, quality-aware computational reuse of electronic patient data and public data, and clinical research workflow optimization in patient care settings towards the achievement of a learning health system. Currently I also spend a significant amount of my time leading the Columbia eMERGE project, as part of a national eMERGE network. I also participate in the Biomedical Data Translator consortia.
My current research focus on these areas:
- Data science and informatics for clinical evidence generation, appraisal, dissemination, and implementation
- EHR-based phenotyping and case or cohort identification
- Knowledge engineering
Chunhua Weng
PhD, FACMI, FIAHSI
Professor of
Biomedical Informatics
Member of
Data Science Institute
Member of
Irving Institute for Clinical and Translational Research
Columbia University
622 West 168 Street, PH-20-room 407
New York, NY 10032
University email account (@columbia.edu): chunhua