A Novel Hybrid Approach to Automated Negation Detection in Clinical Radiology Reports

Huang, Yang; Lowe, Henry J.

doi:10.1197/jamia.m2284

Cited by 125 publications

(73 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Syntactic information is also useful to resolve this problem. A hybrid approach by combining regular expression matching with grammatical parsing has been purposed to detect negations [13]. The results showed that the structure grammar rules developed using linguistic principles were more powerful than detecting negated concepts at a fixed distance from negation cues.…”

Section: Introductionmentioning

confidence: 99%

Automatic negation detection in narrative pathology reports

Patrick

2015

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Automatic negation detection in narrative pathology reports

Patrick

2015

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

“…This algorithm has been utilized [26] for finding encounter-based events in clinical electronic medical records and for classifying them. The idea of using syntactic and semantic processing for determining the scope of negation cues has been tackled in many other research studies [27][28][29][30][31][32][33][34].…”

Section: Related Workmentioning

confidence: 99%

NegMiner: An Automated Tool for Mining Negations from Electronic Narrative Medical Documents

Elazhary¹

2017

IJISA

View full text Add to dashboard Cite

Abstract-Mining negations from electronic narrative medical documents is one of the prominent data mining applications. Since medical documents are freely written, it is impossible to consider all possible sentence structures in advance and so frequent update of mining algorithms is inevitable. Unfortunately most of the proposed algorithms in the literature are too complex to be easily updated. Besides, most of them cannot be easily ported to other natural languages. The simple NegEx algorithm utilizes only two regular expressions and sets of terms to mine negations from narrative medical documents and so does not suffer from these shortcomings. Meanwhile, it has shown impressive mining results and so it is the most widely adopted algorithm. This paper proposes the Negation Mining (NegMiner) tool to address some of the shortcomings of the NegEx algorithm. The NegMiner exploits some basic syntactic and semantic information to deal with contiguous and multiple negations. It is a user-friendly tool that facilitates the task of knowledge base update and the task of document analysis through the use of PDF files. This also makes it able to deal with the existence of a medical finding several times in a single sentence. Experimental results have shown the superiority of the mining results of the NegMiner in comparison to the simulated NegEx algorithm.

show abstract

“…Previous works have demonstrated the ability to determine positive findings by using NLP to address negation within clinical reports [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Development of automated detection of radiology reports citing adrenal findings

et al. 2011

View full text Add to dashboard Cite

The aim of this study was to determine the feasibility of automated detection of adrenal nodules, a common finding on CT, using a newly developed search engine that mines dictated radiology reports. To ensure Health Insurance Portability and Accountability Act compliance, we utilized a preexisting de-identified database of 32,974 CT reports from February 1, 2009 to February 28, 2010. Common adrenal descriptors from 29 staff radiologists were used to develop an automated rule-based algorithm targeting adrenal findings. Each sentence within the free text of reports was searched with an adapted NegEx negation algorithm. The algorithm was refined using a 2-week test period of reports and subsequently validated using a 6-week period. Manual review of the 3,693 CT reports in the validation period identified 222 positive reports while the algorithm detected 238 positive reports. The algorithm identified one true positive report missed on manual review for a total of 223 true positive reports. This resulted in a precision of 91% (217 of 238) and a recall of 97% (217 of 223). The sensitivity of the query was 97.3% (95% confidence interval (CI), 93.9-98.9%), and the specificity was 99.3% (95% CI, 99.1-99.6%). The positive predictive value of the algorithm was 91.0% (95% CI, 86.6-94.3%), and the negative predictive value was 99.8% (95% CI, 99.6-99.9%). The prevalence of true positive adrenal findings identified by the query (7.1%) was nearly identical to the true prevalence (7.2%). Automated detection of language describing common findings in imaging reports, such as adrenal nodules on CT, is feasible.

show abstract

A Novel Hybrid Approach to Automated Negation Detection in Clinical Radiology Reports

Abstract: This novel hybrid approach can accurately locate negated concepts in clinical radiology reports not only when in close proximity to, but also at a distance from, negation signals.

Cited by 125 publications

References 16 publications

Automatic negation detection in narrative pathology reports

Automatic negation detection in narrative pathology reports

NegMiner: An Automated Tool for Mining Negations from Electronic Narrative Medical Documents

Development of automated detection of radiology reports citing adrenal findings

Contact Info

Product

Resources

About