Property | Value |
Name | Comparison of different data mining techniques to predict hospital length of stay |
Description | Research article:-*Tanuja S1, Dr. U. Dinesh Acharya2, *Shailesh K R3 1.Assistant Professor, Department of Computer Science Engineering, MIT, Manipal University, India. 2.Professor and Head, Department of Computer Science Engineering, MIT, Manipal University, India. 3.Assistant Professor (Sr.), Department of Electrical& Electronics,MIT, Manipal University,India. 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.
Key words:- Data Mining, Text Mining, Back propagation, Neural Networks, K-NN, J48, Naive Bayes , Scoring System, missing data replacement. |
Filename | Shailesh K R et. al.(1).pdf |
Filesize | 196.53 kB |
Filetype | pdf (Mime Type: application/pdf) |
Creator | |
Created On: | 06/17/2011 00:00 |
Viewers | Everybody |
Maintained by | Editor |
Hits | 2596 Hits |
Last updated on | 07/12/2011 17:19 |
Homepage | |
CRC Checksum | |
MD5 Checksum |