| Automatic segmentation of clinical texts. | |
| | |
MedLine Citation:
|
PMID: 19965054 Owner: NLM Status: In-Data-Review |
Abstract/OtherAbstract:
|
Clinical narratives, such as radiology and pathology reports, are commonly available in electronic form. However, they are also commonly entered and stored as free text. Knowledge of the structure of clinical narratives is necessary for enhancing the productivity of healthcare departments and facilitating research. This study attempts to automatically segment medical reports into semantic sections. Our goal is to develop a robust and scalable medical report segmentation system requiring minimum user input for efficient retrieval and extraction of information from free-text clinical narratives. Hand-crafted rules were used to automatically identify a high-confidence training set. This automatically created training dataset was later used to develop metrics and an algorithm that determines the semantic structure of the medical reports. A word-vector cosine similarity metric combined with several heuristics was used to classify each report sentence into one of several pre-defined semantic sections. This baseline algorithm achieved 79% accuracy. A Support Vector Machine (SVM) classifier trained on additional formatting and contextual features was able to achieve 90% accuracy. Plans for future work include developing a configurable system that could accommodate various medical report formatting and content standards. |
| | |
Authors:
|
Emilia Apostolova; David S Channin; Dina Demner-Fushman; Jacob Furst; Steven Lytinen; Daniela Raicu |
Related Documents
:
|
10901824 - Basic resuscitation--knowledge and skills of full-time medical practitioners at public ... 10211274 - Reforming higher specialist training in the united kingdom--a step along the continuum ... 17964504 - Simulation-based training: the next revolution in radiology education? 16986484 - Future practice profiles of canadian medical trainees. 7657244 - A historical analysis of medical spending growth, 1960-1993. 18019904 - Smart pumps. |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference Volume: 1 ISSN: 1557-170X ISO Abbreviation: Conf Proc IEEE Eng Med Biol Soc Publication Date: 2009 |
Date Detail:
|
Created Date: 2009-12-07 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 101243413 Medline TA: Conf Proc IEEE Eng Med Biol Soc Country: United States |
Other Details:
|
Languages: eng Pagination: 5905-8 Citation Subset: IM |
Affiliation:
|
College of Computing and Digital Media, DePaul University, Chicago, IL 60604. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: State estimation of walking phase and functional electrical stimulation by wearable device.
Next Document: A list-based method for fast generation of molecular surfaces.