Clinical Ontologies for Discovery Applications

Lussier, Yves A.; Bodenreider, Olivier

doi:10.1007/978-0-387-48438-9_6

Cited by 11 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The entities in the schemas could be pre-coordinated (coding as a single field) or post-coordinated (reassembled after storing individual components separately). Two problems associated with pre-coordination [70] are: a) updates to the cross index could be slow because of the knowledge resources needed and b) computation ambiguity of the reuse of the concept. Given the ability of distributional semantics to detect words appearing in similar context and to predict the appropriateness of a concept to a context, it is possible that we could automatically address both these problems.…”

Section: Discussionmentioning

confidence: 99%

Enhancing clinical concept extraction with distributional semantics

Jonnalagadda

Cohen

et al. 2012

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Extracting concepts (such as drugs, symptoms, and diagnoses) from clinical narratives constitutes a basic enabling technology to unlock the knowledge within and support more advanced reasoning applications such as diagnosis explanation, disease progression modeling, and intelligent analysis of the effectiveness of treatment. The recent release of annotated training sets of de-identified clinical narratives has contributed to the development and refinement of concept extraction methods. However, as the annotation process is labor-intensive, training data are necessarily limited in the concepts and concept patterns covered, which impacts the performance of supervised machine learning applications trained with these data. This paper proposes an approach to minimize this limitation by combining supervised machine learning with empirical learning of semantic relatedness from the distribution of the relevant words in additional unannotated text. The approach uses a sequential discriminative classifier (Conditional Random Fields) to extract the mentions of medical problems, treatments and tests from clinical narratives. It takes advantage of all Medline abstracts indexed as being of the publication type “clinical trials” to estimate the relatedness between words in the i2b2/VA training and testing corpora. In addition to the traditional features such as dictionary matching, pattern matching and part-of-speech tags, we also used as a feature words that appear in similar contexts to the word in question (that is, words that have a similar vector representation measured with the commonly used cosine metric, where vector representations are derived using methods of distributional semantics). To the best of our knowledge, this is the first effort exploring the use of distributional semantics, the semantics derived empirically from unannotated text often using vector space models, for a sequence classification task such as concept extraction. Therefore, we first experimented with different sliding window models and found the model with parameters that led to best performance in a preliminary sequence labeling task. The evaluation of this approach, performed against the i2b2/VA concept extraction corpus, showed that incorporating features based on the distribution of words across a large unannotated corpus significantly aids concept extraction. Compared to a supervised-only approach as a baseline, the micro-averaged f-measure for exact match increased from 80.3% to 82.3% and the micro-averaged f-measure based on inexact match increased from 89.7% to 91.3%. These improvements are highly significant according to the bootstrap resampling method and also considering the performance of other systems. Thus, distributional semantic features significantly improve the performance of concept extraction from clinical narratives by taking advantage of word distribution information obtained from unannotated data.

show abstract

Section: Discussionmentioning

confidence: 99%

Enhancing clinical concept extraction with distributional semantics

Jonnalagadda

Cohen

et al. 2012

Journal of Biomedical Informatics

View full text Add to dashboard Cite

show abstract

“…that has been generated during the last years [16]. This necessity has led to the development of multiple biomedical ontologies, which are stored in large-scale ontology repositories available for researchers.…”

Section: Ontologies and Bio-ontologiesmentioning

confidence: 99%

Developing a system for advanced monitoring and intelligent drug administration in critical care units using ontologies

Martínez-Romero

Vázquez-Naya

Pereira

et al. 2013

KES

View full text Add to dashboard Cite

When a patient enters an intensive care unit (ICU), either after surgery or due to a serious clinical condition, his vital signs are continually changing, forcing the medical experts to make rapid and complex decisions, which frequently imply modifications on the dosage of drugs being administered. Life of patients at critical units depends largely on the wisdom of such decisions. However, the human factor is sometimes a source of mistakes that lead to incorrect or inaccurate actions. This work presents an expert system based on a domain ontology that acquires the vital parameters from the patient monitor, analyzes them and provides the expert with a recommendation regarding the treatment that should be administered. If the expert agrees, the system modifies the drug infusion rates being supplied at the infusion pumps in order to improve the patient's physiological status. The system is being developed at the IMEDIR Center (A Coruña, Spain) and it is being tested at the cardiac intensive care unit (CICU) of the Meixoeiro Hospital (Vigo, Spain), which is a specific type of ICU exclusively aimed to treat patients who have underwent heart surgery or that are affected by a serious coronary disorder.

show abstract

“…In general, a limited number of articles have presented the role played by several biomedical ontologies in specific applications, such as clinical decision support (Huff, 2007) and discovery applications (Lussier & Bodenreider, 2007), or in a specific domain, such as bioinformatics (Stevens et al, 2004). The papers of this special issue grew out of contributions to the Second International Workshop on Formal Biomedical Knowledge Representation (KR-MED 2006), held in Baltimore, MD, on November 8, 2006(KR-MED, 2006.…”

Section: Biomedical Ontology In Actionmentioning

confidence: 99%