Medical i2b2 NLP smoking challenge: The A-life system architecture and methodology

被引:21
作者
Heinze, Daniel T. [1 ]
Morsch, Mark L. [1 ]
Potter, Brian C. [1 ]
Sheffer, Ronald E., Jr. [1 ]
机构
[1] A Life Med Inc, San Diego, CA USA
关键词
D O I
10.1197/jamia.M2438
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We describe the architecture of LifeCode (R) (A-Life Medical, Inc.), a natural language processing system for free-text clinical information extraction, our methodology in applying LifeCode (R) to the i2b2 smoking challenge, and statistical measures for performance evaluation. Due to the limited test size and the coefficient of variation in the test standard, it is difficult to draw conclusions regarding the relative efficacy of approaches that were applied to this challenge.
引用
收藏
页码:40 / 43
页数:4
相关论文
共 6 条
[1]  
[Anonymous], SPEC MAN NAT IMPL HO
[2]  
*DEP HHS, RAT STATS 2007 COMP
[3]  
HEINZE D, 2006, AHIMA WORKSH SOFTW S
[4]  
Heinze DT, 2001, AI MAG, V22, P76
[5]  
Morris WC, 2000, J AM MED INFORM ASSN, P595
[6]  
MORSCH M, 2006, P 18 C INN APPL ART