PMCC PMCC

Search tips
Search criteria

Advanced
Results 1-3 (3)
 

Clipboard (0)
None

Select a Filter Below

Journals
Authors
more »
Year of Publication
Document Types
1.  Correction: Building Large Collections of Chinese and English Medical Terms from Semi-Structured and Encyclopedia Websites 
PLoS ONE  2013;8(12):10.1371/annotation/fab3bd89-3ae3-445f-a418-207bbd7d4377.
doi:10.1371/annotation/fab3bd89-3ae3-445f-a418-207bbd7d4377
PMCID: PMC3865328
2.  A classification approach to coreference in discharge summaries: 2011 i2b2 challenge 
Objective
To create a highly accurate coreference system in discharge summaries for the 2011 i2b2 challenge. The coreference categories include Person, Problem, Treatment, and Test.
Design
An integrated coreference resolution system was developed by exploiting Person attributes, contextual semantic clues, and world knowledge. It includes three subsystems: Person coreference system based on three Person attributes, Problem/Treatment/Test system based on numerous contextual semantic extractors and world knowledge, and Pronoun system based on a multi-class support vector machine classifier. The three Person attributes are patient, relative and hospital personnel. Contextual semantic extractors include anatomy, position, medication, indicator, temporal, spatial, section, modifier, equipment, operation, and assertion. The world knowledge is extracted from external resources such as Wikipedia.
Measurements
Micro-averaged precision, recall and F-measure in MUC, BCubed and CEAF were used to evaluate results.
Results
The system achieved an overall micro-averaged precision, recall and F-measure of 0.906, 0.925, and 0.915, respectively, on test data (from four hospitals) released by the challenge organizers. It achieved a precision, recall and F-measure of 0.905, 0.920 and 0.913, respectively, on test data without Pittsburgh data. We ranked the first out of 20 competing teams. Among the four sub-tasks on Person, Problem, Treatment, and Test, the highest F-measure was seen for Person coreference.
Conclusions
This system achieved encouraging results. The Person system can determine whether personal pronouns and proper names are coreferent or not. The Problem/Treatment/Test system benefits from both world knowledge in evaluating the similarity of two mentions and contextual semantic extractors in identifying semantic clues. The Pronoun system can automatically detect whether a Pronoun mention is coreferent to that of the other four types. This study demonstrates that it is feasible to accomplish the coreference task in discharge summaries.
doi:10.1136/amiajnl-2011-000734
PMCID: PMC3422828  PMID: 22505762
Natural language processing; information retrieval; clinical decision support; biomedical informatics; text processing; medical records
3.  Building Large Collections of Chinese and English Medical Terms from Semi-Structured and Encyclopedia Websites 
PLoS ONE  2013;8(7):e67526.
To build large collections of medical terms from semi-structured information sources (e.g. tables, lists, etc.) and encyclopedia sites on the web. The terms are classified into the three semantic categories, Medical Problems, Medications, and Medical Tests, which were used in i2b2 challenge tasks. We developed two systems, one for Chinese and another for English terms. The two systems share the same methodology and use the same software with minimum language dependent parts. We produced large collections of terms by exploiting billions of semi-structured information sources and encyclopedia sites on the Web. The standard performance metric of recall (R) is extended to three different types of Recall to take the surface variability of terms into consideration. They are Surface Recall (), Object Recall (), and Surface Head recall (). We use two test sets for Chinese. For English, we use a collection of terms in the 2010 i2b2 text. Two collections of terms, one for English and the other for Chinese, have been created. The terms in these collections are classified as either of Medical Problems, Medications, or Medical Tests in the i2b2 challenge tasks. The English collection contains 49,249 (Problems), 89,591 (Medications) and 25,107 (Tests) terms, while the Chinese one contains 66,780 (Problems), 101,025 (Medications), and 15,032 (Tests) terms. The proposed method of constructing a large collection of medical terms is both efficient and effective, and, most of all, independent of language. The collections will be made publicly available.
doi:10.1371/journal.pone.0067526
PMCID: PMC3706590  PMID: 23874426

Results 1-3 (3)