Medical Natural Language Processing Enhancing Drug Ordering and Coding

The foundation of Natural Language Processing (NLP) did not surface until the late seventies, when it was discovered that semantic patterns in natural language could be expressed in mathematical formulas. NLP is the technology that allows computers to analyze and generate natural languages, such as English and Dutch. Applications of NLP include search and retrieval, information extraction, data warehousing amongst others.

One of the tasks that an NLP system can perform is the parsing of a sentence to determine its syntax. Determining the meaning (semantics) of a sentence is a much harder task to perform. When an NLP system can achieve this, we talk about Natural Language Understanding (NLU).

“Understanding” language means, amongst other things, recognizing which entities in a given domain of reality a word or phrase stands for, and knowing how to link these entities together in a meaningful way. An approach for a computer to understand natural language, is to create an environment that is a formal (i.e. unique, commonly accepted) representation of a specific domain, which is called an ontology. An ontology consists on its basic level of a group of concepts, representing entities in a specific domain of reality,organized in a network of relationships. To put it another way, an ontology represents knowledge about the world, in the case discussed in this paper the medical world, in a form a computer can understand.