@inproceedings{newman-griffis-fosler-lussier-2019-writing,
    title = "Writing habits and telltale neighbors: analyzing clinical concept usage patterns with sublanguage embeddings",
    author = "Newman-Griffis, Denis  and
      Fosler-Lussier, Eric",
    editor = "Holderness, Eben  and
      Jimeno Yepes, Antonio  and
      Lavelli, Alberto  and
      Minard, Anne-Lyse  and
      Pustejovsky, James  and
      Rinaldi, Fabio",
    booktitle = "Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)",
    month = nov,
    year = "2019",
    address = "Hong Kong",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/D19-6218/",
    doi = "10.18653/v1/D19-6218",
    pages = "146--156",
    abstract = "Natural language processing techniques are being applied to increasingly diverse types of electronic health records, and can benefit from in-depth understanding of the distinguishing characteristics of medical document types. We present a method for characterizing the usage patterns of clinical concepts among different document types, in order to capture semantic differences beyond the lexical level. By training concept embeddings on clinical documents of different types and measuring the differences in their nearest neighborhood structures, we are able to measure divergences in concept usage while correcting for noise in embedding learning. Experiments on the MIMIC-III corpus demonstrate that our approach captures clinically-relevant differences in concept usage and provides an intuitive way to explore semantic characteristics of clinical document collections."
}