Towards automated classification of intensive care nursing narratives

Marketta Hiissa, Tapio Pahikkala, Hanna Suominen, Tuija Lehtikunnas, Barbro Back, Helena Karsten, Sanna Salanterä, Tapio I. Salakoski

Research output: A Conference proceeding or a Chapter in BookConference contribution

2 Citations (Scopus)
5 Downloads (Pure)

Abstract

Nursing narratives are an important part of patient documentation, but the possibilities to utilize them in the direct care process are limited due to the lack of proper tools. One solution to facilitate the utilization of narrative data could be to classify them according to their content. In this paper, we addressed two issues related to designing an automated classifier: domain experts' agreement on the content of the classes into which the data are to be classified, and the ability of the machine-learning algorithm to perform the classification on an acceptable level. The data we used were a set of Finnish intensive care nursing narratives. By using Cohen's κ, we assessed the agreement of three nurses on the content of the classes Breathing, Blood Circulation and Pain, and by using the area under ROC curve (AUC), we measured the ability of the Least Squares Support Vector Machine (LS-SVM) algorithm to learn the classification patterns of the nurses. On average, the values of κ were around 0.8. The agreement was highest in the class Blood Circulation, and lowest in the class Breathing. The LS-SVM algorithm was able to learn the classification patterns of the three nurses on an acceptable level; the values of AUC were generally around 0.85. Our results indicate that one way to develop electronic patient records could be tools that handle the free text in nursing documentation.

Original languageEnglish
Title of host publicationUbiquity: Technologies for Better Health in Aging Societies
Subtitle of host publicationProceedings of MIE2006
PublisherIOS Press
Pages789-794
Number of pages6
Volume124
ISBN (Print)9781586036475, 9781586036478
Publication statusPublished - 2006
Externally publishedYes
Event20th International Congress of the European Federation for Medical Informatics, MIE 2006 - Maastricht, Netherlands
Duration: 27 Aug 200630 Aug 2006

Conference

Conference20th International Congress of the European Federation for Medical Informatics, MIE 2006
CountryNetherlands
CityMaastricht
Period27/08/0630/08/06

Fingerprint

Critical Care Nursing
Nursing
Aptitude
Blood Circulation
Nurses
Hemodynamics
Least-Squares Analysis
ROC Curve
Documentation
Pattern recognition
Area Under Curve
Support vector machines
Respiration
Learning algorithms
Learning systems
Classifiers
Pain
Support Vector Machine

Cite this

Hiissa, M., Pahikkala, T., Suominen, H., Lehtikunnas, T., Back, B., Karsten, H., ... Salakoski, T. I. (2006). Towards automated classification of intensive care nursing narratives. In Ubiquity: Technologies for Better Health in Aging Societies: Proceedings of MIE2006 (Vol. 124, pp. 789-794). IOS Press.
Hiissa, Marketta ; Pahikkala, Tapio ; Suominen, Hanna ; Lehtikunnas, Tuija ; Back, Barbro ; Karsten, Helena ; Salanterä, Sanna ; Salakoski, Tapio I. / Towards automated classification of intensive care nursing narratives. Ubiquity: Technologies for Better Health in Aging Societies: Proceedings of MIE2006. Vol. 124 IOS Press, 2006. pp. 789-794
@inproceedings{e2cd92454f9b411385add7a94e6f3507,
title = "Towards automated classification of intensive care nursing narratives",
abstract = "Nursing narratives are an important part of patient documentation, but the possibilities to utilize them in the direct care process are limited due to the lack of proper tools. One solution to facilitate the utilization of narrative data could be to classify them according to their content. In this paper, we addressed two issues related to designing an automated classifier: domain experts' agreement on the content of the classes into which the data are to be classified, and the ability of the machine-learning algorithm to perform the classification on an acceptable level. The data we used were a set of Finnish intensive care nursing narratives. By using Cohen's κ, we assessed the agreement of three nurses on the content of the classes Breathing, Blood Circulation and Pain, and by using the area under ROC curve (AUC), we measured the ability of the Least Squares Support Vector Machine (LS-SVM) algorithm to learn the classification patterns of the nurses. On average, the values of κ were around 0.8. The agreement was highest in the class Blood Circulation, and lowest in the class Breathing. The LS-SVM algorithm was able to learn the classification patterns of the three nurses on an acceptable level; the values of AUC were generally around 0.85. Our results indicate that one way to develop electronic patient records could be tools that handle the free text in nursing documentation.",
keywords = "Computerized Patient Records, Natural Language Processing, Nursing",
author = "Marketta Hiissa and Tapio Pahikkala and Hanna Suominen and Tuija Lehtikunnas and Barbro Back and Helena Karsten and Sanna Salanter{\"a} and Salakoski, {Tapio I.}",
year = "2006",
language = "English",
isbn = "9781586036475",
volume = "124",
pages = "789--794",
booktitle = "Ubiquity: Technologies for Better Health in Aging Societies",
publisher = "IOS Press",
address = "Netherlands",

}

Hiissa, M, Pahikkala, T, Suominen, H, Lehtikunnas, T, Back, B, Karsten, H, Salanterä, S & Salakoski, TI 2006, Towards automated classification of intensive care nursing narratives. in Ubiquity: Technologies for Better Health in Aging Societies: Proceedings of MIE2006. vol. 124, IOS Press, pp. 789-794, 20th International Congress of the European Federation for Medical Informatics, MIE 2006, Maastricht, Netherlands, 27/08/06.

Towards automated classification of intensive care nursing narratives. / Hiissa, Marketta; Pahikkala, Tapio; Suominen, Hanna; Lehtikunnas, Tuija; Back, Barbro; Karsten, Helena; Salanterä, Sanna; Salakoski, Tapio I.

Ubiquity: Technologies for Better Health in Aging Societies: Proceedings of MIE2006. Vol. 124 IOS Press, 2006. p. 789-794.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Towards automated classification of intensive care nursing narratives

AU - Hiissa, Marketta

AU - Pahikkala, Tapio

AU - Suominen, Hanna

AU - Lehtikunnas, Tuija

AU - Back, Barbro

AU - Karsten, Helena

AU - Salanterä, Sanna

AU - Salakoski, Tapio I.

PY - 2006

Y1 - 2006

N2 - Nursing narratives are an important part of patient documentation, but the possibilities to utilize them in the direct care process are limited due to the lack of proper tools. One solution to facilitate the utilization of narrative data could be to classify them according to their content. In this paper, we addressed two issues related to designing an automated classifier: domain experts' agreement on the content of the classes into which the data are to be classified, and the ability of the machine-learning algorithm to perform the classification on an acceptable level. The data we used were a set of Finnish intensive care nursing narratives. By using Cohen's κ, we assessed the agreement of three nurses on the content of the classes Breathing, Blood Circulation and Pain, and by using the area under ROC curve (AUC), we measured the ability of the Least Squares Support Vector Machine (LS-SVM) algorithm to learn the classification patterns of the nurses. On average, the values of κ were around 0.8. The agreement was highest in the class Blood Circulation, and lowest in the class Breathing. The LS-SVM algorithm was able to learn the classification patterns of the three nurses on an acceptable level; the values of AUC were generally around 0.85. Our results indicate that one way to develop electronic patient records could be tools that handle the free text in nursing documentation.

AB - Nursing narratives are an important part of patient documentation, but the possibilities to utilize them in the direct care process are limited due to the lack of proper tools. One solution to facilitate the utilization of narrative data could be to classify them according to their content. In this paper, we addressed two issues related to designing an automated classifier: domain experts' agreement on the content of the classes into which the data are to be classified, and the ability of the machine-learning algorithm to perform the classification on an acceptable level. The data we used were a set of Finnish intensive care nursing narratives. By using Cohen's κ, we assessed the agreement of three nurses on the content of the classes Breathing, Blood Circulation and Pain, and by using the area under ROC curve (AUC), we measured the ability of the Least Squares Support Vector Machine (LS-SVM) algorithm to learn the classification patterns of the nurses. On average, the values of κ were around 0.8. The agreement was highest in the class Blood Circulation, and lowest in the class Breathing. The LS-SVM algorithm was able to learn the classification patterns of the three nurses on an acceptable level; the values of AUC were generally around 0.85. Our results indicate that one way to develop electronic patient records could be tools that handle the free text in nursing documentation.

KW - Computerized Patient Records

KW - Natural Language Processing

KW - Nursing

M3 - Conference contribution

SN - 9781586036475

SN - 9781586036478

VL - 124

SP - 789

EP - 794

BT - Ubiquity: Technologies for Better Health in Aging Societies

PB - IOS Press

ER -

Hiissa M, Pahikkala T, Suominen H, Lehtikunnas T, Back B, Karsten H et al. Towards automated classification of intensive care nursing narratives. In Ubiquity: Technologies for Better Health in Aging Societies: Proceedings of MIE2006. Vol. 124. IOS Press. 2006. p. 789-794