Using nurses’ natural language entries to build a concept-oriented terminology for patients’ chief complaints in the emergency department

2004

Proc of Assoc for Info

Self Cite

When a patient visits the Emergency Department (ED), the reason the patient is seeking care is recorded as the Chief Complaint (CC). Beyond its role in the patient's care, there is interest in the CC for secondary uses. Clinicians and epidemiologists can use CC for research. ED clinicians and administrators incorporate CC data into quality monitoring and improvement efforts. Public health officials can use it as data for health surveillance. But there is no controlled vocabulary for recording CC, or standard for a CC component in the patient record. Travers (2003) completed a crucial first step toward the creation of a thesaurus for CC by analyzing a corpus of CCs to determine the nature of the language used by triage nurses, and the concepts that were expressed. Her analysis also illuminated many issues concerning the content and structure of a CC thesaurus that must be discussed before the thesaurus can be developed. Using Cimino's 1998 article, “Desiderata for Controlled Medical Vocabularies in the Twenty‐First Century”, as a framework, we discuss these issues and the resulting decisions that the thesaurus development team, along with other stakeholders, will encounter.

Section: Discussionmentioning

confidence: 99%

Section: Analysis Of Chief Complaintsmentioning

confidence: 99%

Issues in the development of a thesaurus for patients' chief complaints in the emergency department

2004

Proc of Assoc for Info

Self Cite

“…In a pilot study, the addition of information from TNs led to improved sensitivity for three syndromes, Respiratory, Fever-Rash and Gastrointestinal, from 17% - 40% to over 81%, while specificity was maintained above 80% [11]. However, use of TNs can also increase the risk of false classification, since they can include syndrome-relevant information in non-standard terms, such as abbreviations, misspellings, negated forms, and other expressions characteristic of free-text notes [15]. …”

Section: Introductionmentioning

confidence: 99%

Emergency Medical Text Classifier: New system improves processing and classification of triage notes

Waller

et al. 2014

OJPHI

ObjectiveAutomated syndrome classification aims to aid near real-time syndromic surveillance to serve as an early warning system for disease outbreaks, using Emergency Department (ED) data. We present a system that improves the automatic classification of an ED record with triage note into one or more syndrome categories using the vector space model coupled with a ‘learning’ module that employs a pseudo-relevance feedback mechanism. Materials and Methods: Terms from standard syndrome definitions are used to construct an initial reference dictionary for generating the syndrome and triage note vectors. Based on cosine similarity between the vectors, each record is classified into a syndrome category. We then take terms from the top-ranked records that belong to the syndrome of interest as feedback. These terms are added to the reference dictionary and the process is repeated to determine the final classification. The system was tested on two different datasets for each of three syndromes: Gastro-Intestinal (GI), Respiratory (Resp) and Fever-Rash (FR). Performance was measured in terms of sensitivity (Se) and specificity (Sp). Results: The use of relevance feedback produced high values of sensitivity and specificity for all three syndromes in both test sets: GI: 90% and 71%, Resp: 97% and 73%, FR: 100% and 87%, respectively, in test set 1, and GI: 88% and 69%, Resp: 87% and 61%, FR: 97% and 71%, respectively, in test set 2. Conclusions: The new system for pre-processing and syndromic classification of ED records with triage notes achieved improvements in Se and Sp. Our results also demonstrate that the system can be tuned to achieve different levels of performance based on user requirements.

“…11,12 The current study is part of our ongoing effort to develop a vocabulary standard for ED CCs by using a data-driven approach and the UMLS. 12,13 This approach supports two important goals: to work toward comprehensive coverage of the concepts needed to express CCs and to work toward a concept-oriented vocabulary that allows maximum flexibility in the design of information systems that incorporate it. 11 We began the ongoing project with an analysis of a corpus of ED CC entries, to identify the terms used to describe ED CC concepts.…”

mentioning

confidence: 99%

“…11 We began the ongoing project with an analysis of a corpus of ED CC entries, to identify the terms used to describe ED CC concepts. 13 We then developed a natural language-processing system called Emergency Medical Text Processor (EMT-P), which cleans CC data (e.g., chst pn, chest pai, chert pain) and then maps the processed CCs to standard terms that represent UMLS concepts (e.g., chest pain). EMT-P includes separate modules to address the variability in natural-language CC entries such as acronyms, abbreviations, truncations, and coordinate structures.…”

mentioning

confidence: 99%

Unified Medical Language System Coverage of Emergency-medicine Chief Complaints

Academic Emergency Medicine

2006

Self Cite