We describe the architecture of LifeCode (A-Life Medical, Inc.), a natural language processing system for free-text clinical information extraction, our methodology in applying LifeCode 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.
No takes yet. Share an insight, caveat, or question.
Heinze et al. (2007) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: