Document Detail


Automatic analysis of medical dialogue in the home hemodialysis domain: structure induction and summarization.
MedLine Citation:
PMID:  16488194     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Spoken medical dialogue is a valuable source of information for patients and caregivers. This work presents a first step towards automatic analysis and summarization of spoken medical dialogue. We first abstract a dialogue into a sequence of semantic categories using linguistic and contextual features integrated in a supervised machine-learning framework. Our model has a classification accuracy of 73%, compared to 33% achieved by a majority baseline (p<0.01). We then describe and implement a summarizer that utilizes this automatically induced structure. Our evaluation results indicate that automatically generated summaries exhibit high resemblance to summaries written by humans. In addition, task-based evaluation shows that physicians can reasonably answer questions related to patient care by looking at the automatically generated summaries alone, in contrast to the physicians' performance when they were given summaries from a naïve summarizer (p<0.05). This work demonstrates the feasibility of automatically structuring and summarizing spoken medical dialogue.
Authors:
Ronilda C Lacson; Regina Barzilay; William J Long
Related Documents :
12952014 - Revised medical criteria for evaluating amyotrophic lateral sclerosis. final rules.
22195194 - Variability in drug formularies and implications in decision support.
12829384 - Detection of escherichia coli shiga toxin (stx) and enterotoxin (esta and elt) genes in...
19852174 - Different directions for the biological evaluation of biomaterials.
10899804 - Behavioral phenotype of neurofibromatosis, type 1.
8780474 - Assessment of lung auscultation by paramedics.
Publication Detail:
Type:  Journal Article; Research Support, U.S. Gov't, Non-P.H.S.     Date:  2006-02-02
Journal Detail:
Title:  Journal of biomedical informatics     Volume:  39     ISSN:  1532-0480     ISO Abbreviation:  J Biomed Inform     Publication Date:  2006 Oct 
Date Detail:
Created Date:  2006-09-11     Completed Date:  2006-10-10     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  100970413     Medline TA:  J Biomed Inform     Country:  United States    
Other Details:
Languages:  eng     Pagination:  541-55     Citation Subset:  IM    
Affiliation:
Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), Cambridge, MA, USA. rclacson@mit.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Artificial Intelligence*
Communication*
Hemodialysis, Home*
Humans
Information Storage and Retrieval / methods
Patient Education as Topic / methods

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Blockade of TNF-alpha decreases both inflammation and efficacy of intrapulmonary Ad.IFNbeta immunoth...
Next Document:  Transient expression of SOX9 protein during follicular development in the adult mouse ovary.