Paper: Lexically-Triggered Hidden Markov Models for Clinical Document Coding

ACL ID P11-1075
Title Lexically-Triggered Hidden Markov Models for Clinical Document Coding
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

The automatic coding of clinical documents is an important task for today’s healthcare providers. Though it can be viewed as multi-label document classification, the cod- ing problem has the interesting property that most code assignments can be supported by a single phrase found in the input docu- ment. We propose a Lexically-Triggered Hid- den Markov Model (LT-HMM) that leverages thesephrasestoimprovecodingaccuracy. The LT-HMM works in two stages: first, a lexical match is performed against a term dictionary to collect a set of candidate codes for a docu- ment. Next, a discriminative HMM selects the best subset of codes to assign to the document by tagging candidates as present or absent. By confirming codes proposed by a dictio- nary, the LT-HMM can share features across codes, enabli...