Do Nursing Vocabularies Capture the Meaning of Terms Used by Patients in E-mail Messages to Nurses?

2.50
Hdl Handle:
http://hdl.handle.net/10755/159220
Type:
Presentation
Title:
Do Nursing Vocabularies Capture the Meaning of Terms Used by Patients in E-mail Messages to Nurses?
Abstract:
Do Nursing Vocabularies Capture the Meaning of Terms Used by Patients in E-mail Messages to Nurses?
Conference Sponsor:Midwest Nursing Research Society
Conference Year:2004
Author:Hardardottir, Gudrun, MSN, RN
Contact Address: c/o Dr. Connie Delaney, CON, 101 Nursing Building, Iowa City, IA, 52242-1121, USA
Co-Authors:Yichuan Hsieh, MS, RN, Doctoral Student; Patricia F. Brennan, PhD, RN, FAAN, Professor of Nursing
Several studies have evaluated different natural language processing (NLP) systems. To capture concepts from text a system needs to be able to extract the concepts and change to computerized format. With increasing amounts of health information on the Internet it becomes important to understand the terms consumers use while seeking such information. This project evaluated matches (using MetaMap) between the free-text word supplied by patients and one or more concepts in formal nursing vocabularies. Research questions were: 1) Do the nursing classification systems capture the meaning of a parsed word used by patients in electronic mail messages to nurses? 2) Was there a difference between properly capturing the parsed word’s linguistic meaning and its meaning within a sentence? A data set consisting of 241 electronic mail messages from patients to nurses was used. Twenty messages were randomly selected for evaluation by both researchers independently. Inter-rater reliability was 98 %. Descriptive statistics were used to illustrate the degree of meaning captured. Four out of six nursing classification systems captured more than 50 % of the parsed word’s linguistic meaning. NOC (Nursing Outcomes Classification) performed best overall while NANDA (North American Nursing Diagnosis Association) better captured the meaning of the parsed word within a sentence. There was a significant difference (p < 0.01 using a paired t-test) between capturing a parsed word’s linguistic meaning and its meaning in context within a sentence. Using the NLP tool to match terms used by patients can provide linkage to relevant and accurate knowledge resources and support health care providers in automated question interpretation and answer generation. Although directly matching parsed words to standard vocabularies yields a high rate of matching, results are not always compatible with the actual meaning of the word in context within a sentence. More efforts should focus on improving the NLP tool’s accuracy.
Repository Posting Date:
26-Oct-2011
Date of Publication:
17-Oct-2011
Sponsors:
Midwest Nursing Research Society

Full metadata record

DC FieldValue Language
dc.typePresentationen_GB
dc.titleDo Nursing Vocabularies Capture the Meaning of Terms Used by Patients in E-mail Messages to Nurses?en_GB
dc.identifier.urihttp://hdl.handle.net/10755/159220-
dc.description.abstract<table><tr><td colspan="2" class="item-title">Do Nursing Vocabularies Capture the Meaning of Terms Used by Patients in E-mail Messages to Nurses?</td></tr><tr class="item-sponsor"><td class="label">Conference Sponsor:</td><td class="value">Midwest Nursing Research Society</td></tr><tr class="item-year"><td class="label">Conference Year:</td><td class="value">2004</td></tr><tr class="item-author"><td class="label">Author:</td><td class="value">Hardardottir, Gudrun, MSN, RN</td></tr><tr class="item-address"><td class="label">Contact Address:</td><td class="value"> c/o Dr. Connie Delaney, CON, 101 Nursing Building, Iowa City, IA, 52242-1121, USA</td></tr><tr class="item-co-authors"><td class="label">Co-Authors:</td><td class="value">Yichuan Hsieh, MS, RN, Doctoral Student; Patricia F. Brennan, PhD, RN, FAAN, Professor of Nursing</td></tr><tr><td colspan="2" class="item-abstract">Several studies have evaluated different natural language processing (NLP) systems. To capture concepts from text a system needs to be able to extract the concepts and change to computerized format. With increasing amounts of health information on the Internet it becomes important to understand the terms consumers use while seeking such information. This project evaluated matches (using MetaMap) between the free-text word supplied by patients and one or more concepts in formal nursing vocabularies. Research questions were: 1) Do the nursing classification systems capture the meaning of a parsed word used by patients in electronic mail messages to nurses? 2) Was there a difference between properly capturing the parsed word&rsquo;s linguistic meaning and its meaning within a sentence? A data set consisting of 241 electronic mail messages from patients to nurses was used. Twenty messages were randomly selected for evaluation by both researchers independently. Inter-rater reliability was 98 %. Descriptive statistics were used to illustrate the degree of meaning captured. Four out of six nursing classification systems captured more than 50 % of the parsed word&rsquo;s linguistic meaning. NOC (Nursing Outcomes Classification) performed best overall while NANDA (North American Nursing Diagnosis Association) better captured the meaning of the parsed word within a sentence. There was a significant difference (p &lt; 0.01 using a paired t-test) between capturing a parsed word&rsquo;s linguistic meaning and its meaning in context within a sentence. Using the NLP tool to match terms used by patients can provide linkage to relevant and accurate knowledge resources and support health care providers in automated question interpretation and answer generation. Although directly matching parsed words to standard vocabularies yields a high rate of matching, results are not always compatible with the actual meaning of the word in context within a sentence. More efforts should focus on improving the NLP tool&rsquo;s accuracy. </td></tr></table>en_GB
dc.date.available2011-10-26T21:49:01Z-
dc.date.issued2011-10-17en_GB
dc.date.accessioned2011-10-26T21:49:01Z-
dc.description.sponsorshipMidwest Nursing Research Societyen_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.