Using Natural Language Processing to Enable In-Depth Analysis of Clinical Messages Posted to an Internet Mailing List
A Feasibility Study
We developed a workflow for finding a manageable number of clinically relevant messages from a much larger corpus of messages posted to an Internet mailing list. Our procedures enable labor-intensive content analyses by retrieving a set of messages tailored to the research question of a qualitative research team.
Type of project: academic
||Tanja Bekhuis (University of Pittsburgh School of Medicine)
|Other involved People:
Marcos Kreinacke, Heiko Spallek, Mei Song, Jean O'Donnell
heiko spallek (89 )
jean o'donnell (3 )
mei song (4 )
Bakhtinur Khudanov (5 )
Marcos Kreinacke (10 )
Beenish Chaudry ( )
|Is the project funded?||yes
|Funding source:||Partially funded by the Pittsburgh Biomedical Informatics Training Program 5T15LM007059
|Papers related to project:||Bekhuis, T., Kreinacke M., Spallek H., Song M., O’Donnell J. (in press). Using Natural Language Processing to
Enable In-depth Analysis of Clinical Messages Posted to an Internet Mailing List: A Feasibility Study.
Journal of Medical Internet Research. doi:10.2196/jmir.1799.
Bekhuis T., Kreinacke M., Spallek H., Song M. (2010). Using the Natural Language Toolkit to reduce the number of
messages for in-depth content analyses: A case study. AMIA 2010 Annu Symp Proc, 981. Washington, DC:
American Medical Informatics Association.|
|tbekhuis (9 ), University of Pittsburgh
tbekhuis's interests: evidence-based dentistry/electronic information resources, research methods, library information sciences, medical research informatics, NLP, machine learning, ontologies