Mining free-text medical records.

  • 1 January 2001
    • journal article
    • p. 254-8
Abstract
Text mining projects can be characterized along four parameters: 1) the demands of the market in terms of target domain and specificity and depth of queries; 2) the volume and quality of text in the target domain; 3) the text mining process requirements; and 4) the quality assurance process that validates the extracted data. In this paper, we provide lessons learned and results from a large-scale commercial project using Natural Language Processing (NLP) for mining the transcriptions of dictated clinical records in a variety of medical specialties. We conclude that the current state-of-the-art in NLP is suitable for mining information of moderate content depth across a diverse collection of medical settings and specialties.

This publication has 0 references indexed in Scilit: