Natural language processing for biomedical text currently focuses mostly on entity and relation extraction. These entities and relations are usually pre-specified entities, e.g., proteins, and pre-specified relations, e.g., inhibit relations. A shallow parser that captures the relations between noun phrases automatically from free text has been developed and evaluated. It uses heuristics and a noun phraser to capture entities of interest in the text. Cascaded finite state automata structure the relations between individual entities. The automata are based on closed-class English words and model generic relations not limited to specific words. The parser also recognizes coordinating conjunctions and captures negation in text, a feature usually ignored by others. Three cancer researchers evaluated 330 relations extracted from 26 abstracts of interest to them. There were 296 relations correctly extracted from the abstracts resulting in 90% precision of the relations and an average of 11 correct relations per abstract.

negation and their scopes

Proceedings

We describe and evaluate three systems for automatically predicting the ICD-9-CM codes of radiology reports from short excerpts of text. The first system benefits from an open source search engine, Lucene, and takes advantage of the relevance of reports to one another based on individual words. The second uses BoosTexter, a boosting algorithm based on n-grams (sequences of consecutive words) and s-grams (sequences of non-consecutive words) extracted from the reports. The third employs a set of hand-crafted rules that capture lexical elements (short, meaningful, strings of words) derived from BoosTexter’s n-grams, and that are enhanced by shallow semantic information in the form of negation, synonymy, and uncertainty. Our evaluation shows that semantic information significantly contributes to ICD-9-CM coding with lexical elements. Also, a simple hand-crafted rule-based system with lexical elements and semantic information can outperform algorithmically more complex systems, such as Lucene and BoosTexter, when these systems base their ICD-9-CM predictions only upon individual words, n-grams, or s-grams.

Applications using automatically indexed clinical conditions must account for contextual features such as whether a condition is negated, historical or hypothetical, or experienced by someone other than the patient. We developed and evaluated an algorithm called ConText, an extension of the NegEx negation algorithm, which relies on trigger terms, pseudo-trigger terms, and termination terms for identifying the values of three contextual features. In spite of its simplicity, ConText performed well at identifying negation and hypothetical status. ConText performed moderately at identifying whether a condition was experienced by someone other than the patient and whether the condition occurred historically. 1

Background: The medical problem list is an important part of the electronic medical record in development in our institution. To serve the functions it is designed for, the problem list has to be as accurate and timely as possible. However, the current problem list is usually incomplete and inaccurate, and is often totally unused. To alleviate this issue, we are building an environment where the problem list can be easily and effectively maintained. Methods: For this project, 80 medical problems were selected for their frequency of use in our future clinical field of evaluation (cardiovascular). We have developed an Automated Problem List system composed of two main components: a background and a foreground application. The background application uses Natural Language Processing (NLP) to harvest potential problem list entries from the list of 80 targeted problems detected in the multiple free-text electronic documents available in our electronic medical record. These proposed medical problems drive the foreground application designed for management of the problem list. Within this application, the extracted problems are proposed to the physicians for addition to the official problem list. Results: The set of 80 targeted medical problems selected for this project covered about 5 % of

Human annotators and natural language applications are able to identify smoking status from discharge summaries with high accuracy when explicit evidence regarding their smoking status is present in the summary. We explore the possibility of identifying the smoking status from discharge summaries when these smoking terms have been removed. We present results using a Naïve Bayes classifier on a smoke-blind set of discharge summaries and compare this to the performance of human annotators on the same dataset.

This Provisional PDF corresponds to the article as it appeared upon acceptance. Fully formatted PDF and full text (HTML) versions will be made available soon. A framework for enhancing spatial and temporal granularity in report-based health surveillance systems

Abstract not found

Health professionals are faced with challenges when they have to exploit the semantics of concepts present in clinical terminologies in support of research activities. The difficulty lies in the fact that this semantics is represented not only through the labels of concepts, but also their position in the hierarchy, and, when available, their logical and textual definitions. We investigate and contrast the lexical, hierarchical, and logical representations of concepts in SNOMED CT through the example of Anemia and three other disorders. The four use cases we developed suggest that the lexical, hierarchical, and logical representations of concepts have a limited degree of overlap, but are complementary. Finally, we draw practical implications from our findings for SNOMED CT users and developers.