Semantic analysis of free text and its application on automatically assigning ICD-9-CM codes to patient records

Free text written in natural languages is lack of definite structures, and semantic analysis of such text is critically important to many Natural Language Processing applications. In this paper, based on dependency parsing, we present a semantic analytic technique to automatically assign clinical ICD-9-CM codes to complex medical patient records written in English. Our semantics analysis method includes dependency parsing of clinical records obtained from testing and training data sets and the calculation of semantic matching scores. Our ultimate goal is to develop an automated disease diagnosis tool through accurate clinical code assignments. We evaluated our technique with a real-world corpus utilized in the 2007 International Natural Language Processing Challenge administered by the Computational Medicine Center at the Cincinnati Children´s Hospital, and obtained promising results.