Comparison of Different Data Mining Techniques to Predict Hospital Length of Stay

Tanuja , S and Acharya, Dinesh U and Shailesh, K R (2011) Comparison of Different Data Mining Techniques to Predict Hospital Length of Stay. JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL SCIENCES, 7 (7). ISSN 2230 - 7885

[img] PDF
Shailesh_K_R_et._al.(1).pdf - Published Version
Download (201kB)
Official URL: http://jpbms.info/index.php?option=com_docman&task...

Abstract

In this paper we present the performance analysis of different data mining techniques to predict the inpatient hospital length of stay in a super specialty hospital. Data set used for the analysis is real time data taken from super specialty hospital. Pre-processed data set is generated from the electronic discharge summaries obtained from the hospital. This data set consists of 401 records with 16 parameters. In this paper we have investigated four data mining techniques: Multilayer back propagation NN, Naive Bayes Classifier, K-NN method, J48 class of C4.5 decision tree. We found from the analysis that Neural Network has achieved better performance compared to the other three techniques.

Item Type: Article
Uncontrolled Keywords: Data Mining, Text Mining, Back propagation, Neural Networks, K-NN, J48, Naive Bayes , Scoring System, missing data replacement.
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Engineering > MIT Manipal > Electrical and Electronics
Depositing User: MIT Library
Date Deposited: 16 Jul 2011 04:22
Last Modified: 16 Jul 2011 04:22
URI: http://eprints.manipal.edu/id/eprint/757

Actions (login required)

View Item View Item