Information extraction from multi-institutional radiology reports
作者：
Highlights：
• We described an information extraction system for radiology report narrative.
• The system finds clinically significant concepts according to an information model.
• Our evaluation showed the effectiveness and generalizability of our approach.
• CMM and CRF named-entity recognition models are equally effective in our system.
• Our machine learning system outperforms the commonly used dictionary-based approach.
摘要
•We described an information extraction system for radiology report narrative.•The system finds clinically significant concepts according to an information model.•Our evaluation showed the effectiveness and generalizability of our approach.•CMM and CRF named-entity recognition models are equally effective in our system.•Our machine learning system outperforms the commonly used dictionary-based approach.
论文关键词：Natural language processing,Information extraction,Discriminative sequence classifier,Radiology report narrative
论文评审过程：Received 6 April 2015, Revised 22 August 2015, Accepted 24 September 2015, Available online 3 October 2015, Version of Record 26 February 2016.
论文官网地址：https://doi.org/10.1016/j.artmed.2015.09.007
