2012
DOI: 10.1136/amiajnl-2011-000774
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning-based coreference resolution of concepts in clinical documents

Abstract: Our machine learning approach is a promising solution for recognizing coreferent concepts, which in turn is useful for practical applications such as the assembly of problem and medication lists from clinical documents.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0

Year Published

2012
2012
2018
2018

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 12 publications
(7 citation statements)
references
References 8 publications
0
7
0
Order By: Relevance
“…From Table 1, we see that we get the best results on both clinical and pathology sections of ODIE dataset. Table 2 shows a comparison of our system with previous state-of-the-art approaches [8,14,42,43,2,13,11,19,40] on i2b2 dataset. Just like for Table 1, the numbers shown in Table 2 correspond to average F1 score across all the i2b2 categories ("test", "treatment" etc.).…”
Section: When Gold Mentions Are Givenmentioning
confidence: 98%
“…From Table 1, we see that we get the best results on both clinical and pathology sections of ODIE dataset. Table 2 shows a comparison of our system with previous state-of-the-art approaches [8,14,42,43,2,13,11,19,40] on i2b2 dataset. Just like for Table 1, the numbers shown in Table 2 correspond to average F1 score across all the i2b2 categories ("test", "treatment" etc.).…”
Section: When Gold Mentions Are Givenmentioning
confidence: 98%
“…Parameters such as target lesions, tumor measurements, response, performance status and others need to be agreed upon and embedded in the EMR. While there have been enormous efforts on electronic language capture or natural language processing, these systems cannot extract data that does not exist (despite predictive 'neural' algorithms) nor substitute, in our opinion, for quality, standardized information entered at the point-of-care or alternatively, collected and then entered by data-entry personnel [6][7][8].…”
Section: Data Warehouse and Biorepositorymentioning
confidence: 99%
“…Co-reference resolution aims to recognize two mentions that refer to the same entity in a sentence or across sentences [67]. Current co-reference resolution studies use rule-based [68,69], machine learning [35,70,71] and hybrid systems [72] to identify noun phrases, including person, pronoun, and concepts such as medical tests. The performance of these systems varies depending on the data quality [73].…”
Section: Natural Language Processingmentioning
confidence: 99%