2017/04/20 by Václav Papež, Papez, Vaclav, Spiros Denaxas +3
Computer Science · Biochemistry, Genetics and Molecular Biology · #Machine Learning in Healthcare #Biomedical Text Mining and Ontologies #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1704.08193
Electronic Health Records (EHR) are data generated during routine clinical\ncare. EHR offer researchers unprecedented phenotypic breadth and depth and have\nthe potential to accelerate the pace of precision medicine at scale. A main EHR\nuse-case is creating phenotyping algorithms to define disease status, onset and\nseverity. Currently, no common machine-readable standard exists for defining\nphenotyping algorithms which often are stored in human-readable formats. As a\nresult, the translation of algorithms to implementation code is challenging and\nsharing across the scientific community is problematic. In this paper, we\nevaluate openEHR, a formal EHR data specification, for computable\nrepresentations of EHR phenotyping algorithms.\n