Skip Navigation
Lister Hill Center Logo  

Search Tips
About the Lister Hill Center
Innovative Research
Publications and Lectures
Training and Employment
LHNCBC: Document Abstract
Year: 2003Adobe Acrobat Reader
Download Free Adobe Acrobat Reader
2003-014
Genomic Research Within Clinical Pediatrics
John Pestian, Ph.D., MBA
2003-09-25
A discussion of a project to do genomic research within clinical pediatrics using the clinical records from the Cincinnati Children's Hospital Medical Center. Using MetaMap (MMTx) on clinical records to extract concepts, Dr. Pestian has issues with the recall that he is getting from MMTx and upon further investigation has found that there are two principle causes. The first is the lack of use of a part of speech tagger within MMTx; the second is coverage within the UMLS to pediatric clinical terms.Dr. Pestian aims to overcome both issues. He is having built a tagger trained on his clinical records. The hard and expensive part of this task is having people hand tag a substantial number of records to enable a tagger to adequately learn within this genre. He has contracted out a substantial body of records to be hand tagged both using the SPECIALIST's Lexicon's tag set and the Penn Treebank's tag set.Dr. Pestian wants to address the second issue of coverage by building a pediatric clinical vocabulary to augment the vocabularies within the UMLS.