Relevance Ranking of Intensive Care Nursing Narratives
Current computer-based patient records provide many capabilities to assist nurses’ work in intensive care units, but the possibilities to utilize existing free-text documentation are limited without the appropriate tools. To ease this limitation, we present an adaptation of the Regularized Least-Squares (RLS) algorithm for ranking pieces of nursing notes with respect to their relevance to breathing, blood circulation, and pain. We assessed the ranking results by using Kendall’s τ b as a measure of association between the output of the RLS algorithm and the desired ranking. The values of τ b were 0.62, 0.69, and 0.44 for breathing, blood circulation, and pain, respectively. These values indicate that a machine learning approach can successfully be used to rank nursing notes, and encourage further research on the use of ranking techniques when developing intelligent tools for the utilization of nursing narratives.
KeywordsBlood Circulation Reproduce Kernel Hilbert Space Machine Learning Approach Intelligent Tool Relevance Ranking
Unable to display preview. Download preview PDF.
- 2.Pakhomov, S.V., Buntrock, J.D., Chute, C.G.: Using compound codes for automatic classification of clinical diagnoses. Medinfo. 11, 411–415 (2004)Google Scholar
- 6.Rifkin, R.M.: Everything old is new again: A fresh look at historical approaches in machine learning. PhD Thesis, Massachusetts Institute of Technology (2002)Google Scholar
- 11.Gélinas, C., Fortier, M., Viens, C., Fillion, L., Puntillo, K.: Pain assessment and management in critically ill intubated patients: a retrospective study. Am. J. Crit. Care 13, 126–135 (2004)Google Scholar
- 13.Hiissa, M., Pahikkala, T., Suominen, H., Lehtikunnas, T., Back, B., Karsten, H., Salanterä, S., Salakoski, T.: Towards automated classification of intensive care nursing narratives. In: The 20th International Congress of the European Federation for Medical Informatics (MIE 2006), Maastricht, the Netherlands, August 27–30 (to be presented, 2006)Google Scholar
- 15.Snowball, the Finnish stemming algorithm. Martin Porter; c, and (for the Java developments) Richard Boulton; c2002 [updated 2005 May 23; cited 2006 Jan 10]. (2001), http://snowball.tartarus.org/algorithms/finnish/stemmer.html
- 16.Kendall, M.G.: Rank correlation methods, 4th edn., Griffin, London (1970)Google Scholar