Combining Markov Models and Association Analysis for Disease Prediction

被引:0
作者
Folino, Francesco [1 ]
Pizzuti, Clara [1 ]
机构
[1] Natl Res Council Italy CNR, Inst High Performance Comp & Networking ICAR, I-87036 Arcavacata Di Rende, CS, Italy
来源
INFORMATION TECHNOLOGY IN BIO- AND MEDICAL INFORMATICS: SECOND INTERNATIONAL CONFERENCE, ITBAM 2011 | 2011年 / 6865卷
关键词
CARE;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
An approach for disease prediction that combines clustering, Markov models and association analysis techniques is proposed. Patient medical records are clustered and a Markov model for each cluster is generated to perform prediction of illnesses a patient could likely be affected in the future. However, when the probability of the most likely state in the Markov models is not sufficiently high, it resorts to sequential association analysis, by considering the items induced by high confidence rules generated by recurring sequential disease patterns. Experimental results show that the combination of different models enhances predictive accuracy and is a feasible way to diagnose diseases.
引用
收藏
页码:39 / 52
页数:14
相关论文
共 19 条
[1]  
AGRAWAL R, 1996, LNCS, V1057
[2]  
Agrawal R., P 20 INT C VERY LARG
[3]  
[Anonymous], 2006, Introduction to Data Mining
[4]  
[Anonymous], Probability, Random Variables and Stochastic Processes
[5]  
[Anonymous], 2000, WORKSHOP ARTIFICIAL
[6]  
[Anonymous], 2008, P ACSC 08 WOLL AUSTR
[7]  
Davis D., 2008, Predicting individual disease risk based on medical history, P769
[8]   Time to CARE: a collaborative engine for practical disease prediction [J].
Davis, Darcy A. ;
Chawla, Nitesh V. ;
Christakis, Nicholas A. ;
Barabasi, Albert-Laszlo .
DATA MINING AND KNOWLEDGE DISCOVERY, 2010, 20 (03) :388-415
[9]  
Deshpande M., 2004, ACM T INTERNET TECHN, V4, P163, DOI DOI 10.1145/990301.990304
[10]  
Folino F., 2010, 2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS 2010), P6, DOI 10.1109/CBMS.2010.6042664