• Corpus ID: 35420758

Syntactically-informed semantic category recognition in discharge summaries.

@article{Sibanda2006SyntacticallyinformedSC,
  title={Syntactically-informed semantic category recognition in discharge summaries.},
  author={Tawanda C. Sibanda and Tian He and Peter Szolovits and Ozlem Uzuner},
  journal={AMIA ... Annual Symposium proceedings. AMIA Symposium},
  year={2006},
  pages={
          714-8
        }
}
Semantic category recognition (SCR) contributes to document understanding. Most approaches to SCR fail to make use of syntax. We hypothesize that syntax, if represented appropriately, can improve SCR. We present a statistical semantic category (SC) recognizer trained with syntactic and lexical contextual clues, as well as ontological information from UMLS, to identify eight semantic categories in discharge summaries. Some of our categories, e.g., test results and findings, include complex… 
Does negation really matter?
TLDR
It is concluded that due to the nature of the machine learning classifiers, information on the polarity of phrase-level assertions does not improve performance on data in a multilabel document-level classification task.
Using contextual and lexical features to restructure and validate the classification of biomedical concepts
BackgroundBiomedical ontologies are critical for integration of data from diverse sources and for use by knowledge-based biomedical applications, especially natural language processing as well as
Using Local Grammar for Entity Extraction from Clinical Reports
TLDR
The work presented in this paper uses a local grammar approach to extract medical named entities from French patient clinical reports using a natural language processing (NLP) approach.
Semantic tagging of medical narratives using SNOMED CT
TLDR
This research began with an investigation of using SNOMED CT® for identification of concepts in medical narratives which resulted in the derivation of a tag set which was used to develop three gold standard datasets.
Role of preferred terminology in the classification of medical reports
TLDR
This work explores the role of the Unified Medical Language System Metathesaurus preferred terms in multi-label classification of medical reports and shows that in the data, some reports can be correctly classified not only in the absence of preferred terms, but in some cases, in the presence of direct references to the diseases themselves.
Beyond linear chain: a journey through conditional random fields for information extraction from text
TLDR
A set of increasingly powerful models based on CRFs, including a hierarchical multi-label CRFs scheme that jointly models the overall opinion expressed in a product review and the set of aspect-specific opinions expressed in each of its sentences are proposed.
A study of machine-learning-based approaches to extract clinical entities and their assertions from discharge summaries
TLDR
Systematic evaluation on the training set showed that Conditional Random Fields outperformed Support Vector Machines, and semantic information from existing natural-language-processing systems largely improved performance, although contributions from different types of features varied.
Generation from Computerized Clinical Guidelines
TLDR
A framework has been developed that automatically generates context-specifi c query, and determines its query type, from computerized clinical practice guidelines (CPGs), and the medical literature retrieved and linked is found to be relevant to the knowledge of the computerized CPG.
Automated Transformation of Semi-Structured Text Elements
TLDR
This paper presents a rule-based transformation system that converts semi-structured (annotated) text into standardized formats, such as HL7 CDA, where the templates are selected according to the CDA document type-specific requirements.
Patient friendly Presentation of Electronic Patient Records
TLDR
The conclusion of this thesis is that the Support Vector Machine classifier with character bigrams provides good and accurate disambiguation between Norwegian words and medical terms.
...
...