Processing of Medical Records from Unstructured Medical Transcript

The work looks at the problem of creating a framework that identifies information in the free text medical records and maps that information into a structured representation containing clinical terms. The content of the medical records are relatively stereotyped sentence types based on its specialized word usage. This regularity makes it possible to determine a set of sublanguage-specific word classes, which correlate with the types of information conveyed in the subfield; these word classes form the bridge between the structure (syntax) of the sublanguage text and their information content (semantics). We can define sublanguages as the part of the English language used in body of the texts dealing with a particular domain. A parser acts between the medical record and the sublanguage, which extracts the medical data from the input document Keywords: Medical records, Medical data, Medical parser, NLP, Rule base systems