Free-text disease classification
Whitaker, Lyn R.
Buttrey, Samuel E.
MetadataShow full item record
Modern medicine produces data with every patient interaction. While many data elements are easily captured and analyzed, the fundamental record of the patient/clinican interaction is captured in written, free-text. This thesis provides the foundation for the Military Health System to begin building an auto classifier for ICD9 diagnostic codes based on free-text clinican notes. Support Vector Machine models are fit to approximately 84,000 free-text records providing a means to predict ICD9 codes for other free-text records. While the research conducted in this thesis does not provide a consumate ICD9 classification model, it does provide the foundation required to further more detailed analysis.
Approved for public release; distribution is unlimited.