Extracting Phenotypes of Cancer Patients from Electronic Health Records

In recent years, the rapid development of electronic health record (EHR) provides numerous opportunities for improving quality of healthcare. The EHR-based phenotyping is one of the important topics. It can facilitate many research and applications in the domain, such as diagnosis summary, novel phenotype discovery, identify patients for clinical trials and selecting cohort for clinical and generic research [1]. In general, a computable phenotype refers to a clinical condition or characteristic that can be ascertained by a computerized query to an EHR system or clinical data repository [2]. This ongoing project is aimed to extract the phenotypes of breast cancer patients to support the future research.