Abstract | ||
---|---|---|
Extracting medication information from clinical records has many potential applications and was the focus of the i2b2 challenge in 2009. We present a hybrid system, comprised of machine learning and rule-based modules, for medication information extraction. With only a handful of template-filling rules, the system's core is a cascade of statistical classifiers for field detection. It achieved good performance that was comparable to the top systems in the i2b2 challenge, demonstrating that a heavily statistical approach can perform as well or better than systems with many sophisticated rules. The system can easily incorporate additional resources such as medication name lists to further improve performance. |
Year | Venue | Keywords |
---|---|---|
2010 | Louhi@NAACL-HLT | discharge summary,statistical approach,hybrid system,statistical classifier,clinical record,good performance,top system,extracting medication information,additional resource,medication name list,medication information extraction |
Field | DocType | Citations |
Medication name,Information retrieval,Computer science,Information extraction,Artificial intelligence,Natural language processing,Hybrid system | Conference | 5 |
PageRank | References | Authors |
0.53 | 7 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Scott Halgrim | 1 | 15 | 1.08 |
Fei Xia | 2 | 180 | 14.23 |
Imre Solti | 3 | 337 | 23.36 |
Eithon Cadag | 4 | 235 | 13.60 |
Özlem Uzuner | 5 | 1045 | 67.09 |