MITRE system for clinical assertion status classification

Clark, Cheryl; Aberdeen, John S.; Coarr, Matthew; Tresner-Kirsch, David; Wellner, Ben; Yeh, Alexander; Hirschman, Lynette

doi:10.1136/amiajnl-2011-000164

Cited by 32 publications

(25 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others are modelled as named entity recognition systems and use structured prediction for detecting text chunks that function as cues for speculation (Tang et al, 2010;Clark et al, 2011).…”

Section: Previous Researchmentioning

confidence: 99%

Detecting speculations, contrasts and conditionals in consumer reviews

Skeppstedt

Schamp-Bjerede²,

Sahlgren³

et al. 2015

Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

View full text Add to dashboard Cite

A support vector classifier was compared to a lexicon-based approach for the task of detecting the stance categories speculation, contrast and conditional in English consumer reviews. Around 3,000 training instances were required to achieve a stable performance of an F-score of 90 for speculation. This outperformed the lexicon-based approach, for which an Fscore of just above 80 was achieved. The machine learning results for the other two categories showed a lower average (an approximate F-score of 60 for contrast and 70 for conditional), as well as a larger variance, and were only slightly better than lexicon matching. Therefore, while machine learning was successful for detecting speculation, a well-curated lexicon might be a more suitable approach for detecting contrast and conditional.

show abstract

“…Others are modelled as named entity recognition systems and use structured prediction for detecting text chunks that function as cues for speculation (Tang et al, 2010;Clark et al, 2011).…”

Section: Previous Researchmentioning

confidence: 99%

Detecting speculations, contrasts and conditionals in consumer reviews

Skeppstedt

Schamp-Bjerede²,

Sahlgren³

et al. 2015

Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

View full text Add to dashboard Cite

show abstract

“…For instance, NegEx [15], NegFinder [16], and NegExpander [17] achieve high performance for detecting negated disorders, using cue lexicons and heuristics. For uncertainty, NLP tools achieve moderate to high performance for asserting the uncertainty level of disorders, using rule-based and machine-learning approaches, including StAC [18], CARAFE [19], pyConTextNLP [11], and others [9]. Traditionally, assertion classification consists of two processing steps: (1) detecting an assertion cue (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…Several studies have described the effect of coverage and scope of uncertainty cues for uncertainty classification tasks [9, 11, 18, 19]. …”

Section: Introductionmentioning

confidence: 99%

“…Clark et al integrated CARAFE, a conditional random fields model trained to detect negation and uncertainty cues and their scopes, with a rule-based module to assert whether a disorder was present , absent , or possible [19]. Word features such as unigrams within the disorder as well as words within a ±3 token window of the disorder contributed most to assertion performance, resulting in an F-score of 91%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cue-based assertion classification for Swedish clinical text—Developing a lexicon for pyConTextSwe

Velupillai

Skeppstedt

Kvist

et al. 2014

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Objective The ability of a cue-based system to accurately assert whether a disorder is affirmed, negated, or uncertain is dependent, in part, on its cue lexicon. In this paper, we continue our study of porting an assertion system (pyConTextNLP) from English to Swedish (pyConTextSwe) by creating an optimized assertion lexicon for clinical Swedish. Methods and material We integrated cues from four external lexicons, along with generated inflections and combinations. We used subsets of a clinical corpus in Swedish. We applied four assertion classes (definite existence, probable existence, probable negated existence and definite negated existence) and two binary classes (existence yes/no and uncertainty yes/no) to pyConTextSwe. We compared pyConTextSwe’s performance with and without the added cues on a development set, and improved the lexicon further after an error analysis. On a separate evaluation set, we calculated the system’s final performance. Results Following integration steps, we added 454 cues to pyConTextSwe. The optimized lexicon developed after an error analysis resulted in statistically significant improvements on the development set (83% F-score, overall). The system’s final F-scores on an evaluation set were 81% (overall). For the individual assertion classes, F-score results were 88% (definite existence), 81% (probable existence), 55% (probable negated existence), and 63% (definite negated existence). For the binary classifications existence yes/no and uncertainty yes/no, final system performance was 97%/87% and 78%/86% F-score, respectively. Conclusions We have successfully ported pyConTextNLP to Swedish (pyConTextSwe). We have created an extensive and useful assertion lexicon for Swedish clinical text, which could form a valuable resource for similar studies, and which is publicly available.

show abstract

“…In addition to standard bag of words features for representing context, this system used Brown clusters to abstract away from surface feature representations. The MITRE system (Clark et al, 2011) used conditional random fields to tag cues and their scopes, then incorporated cue information, section features, semantic and syntactic class features, and lexical surface features into a maximum entropy classifier. Finally, Wu et al (2014) incorporated many of the dependency features from rule-based DepNeg system (Sohn et al, 2012) and the best features from the i2b2 Challenge into a machine learning system.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Domain Adaptation for Clinical Negation Detection

Miller¹,

Bethard²,

Amiri³

et al. 2017

BioNLP 2017

View full text Add to dashboard Cite

Detecting negated concepts in clinical texts is an important part of NLP information extraction systems. However, generalizability of negation systems is lacking, as cross-domain experiments suffer dramatic performance losses. We examine the performance of multiple unsupervised domain adaptation algorithms on clinical negation detection, finding only modest gains that fall well short of in-domain performance.

show abstract

MITRE system for clinical assertion status classification

Cited by 32 publications

References 14 publications

Detecting speculations, contrasts and conditionals in consumer reviews

Detecting speculations, contrasts and conditionals in consumer reviews

Cue-based assertion classification for Swedish clinical text—Developing a lexicon for pyConTextSwe

Unsupervised Domain Adaptation for Clinical Negation Detection

Contact Info

Product

Resources

About