作者: Joshua C. Denny , Hua Xu
DOI: 10.1016/B978-0-12-401678-1.00012-9
关键词: Data science 、 Repurposing 、 Operationalization 、 Health care quality 、 Decision support system 、 Medicine 、 Data mining 、 Medical diagnosis 、 Documentation 、 Personalized medicine 、 Biobank
摘要: Electronic Health Records (EHRs) are a powerful tool to improve health care quality while reducing its costs. As longitudinal repository of patient diagnoses, treatments, and responses treatment, EHRs also being increasingly recognized as an important for research well clinical care. By coupling with DNA biobanks, can provide phenotypes genomic studies. This chapter summarizes the role needed methods use EHR data discovery implementation into There number challenges accurate interpretation repurposing research. Typically, investigators employ multimodal “phenotype algorithms” find cases controls. Such algorithms integrate billing codes, medication records, laboratory test result data, notes achieve necessary recall precision. Since much content in record is unstructured (narrative) documentation, natural language processing often required. Despite these challenges, researchers have been successful replicating known genetic associations making new discoveries using data. Early demonstration projects show that EHR, coupled advanced genome-enabled decision support, may be ideal operationalize use.