An Effective Method for Matching Patient Records from Multiple Databases using Neural Network
|
10.5120/18253-9178 |
Subitha.s and S.c.punitha. Article: An Effective Method for Matching Patient Records from Multiple Databases using Neural Network. International Journal of Computer Applications 104(12):17-21, October 2014. Full text available. BibTeX
@article{key:article,
author = {Subitha.s and S.c.punitha},
title = {Article: An Effective Method for Matching Patient Records from Multiple Databases using Neural Network},
journal = {International Journal of Computer Applications},
year = {2014},
volume = {104},
number = {12},
pages = {17-21},
month = {October},
note = {Full text available}
}
Abstract
Record matching is the method of identifying records that denote the similar real world entity or item . The record matching method is helpful for matching health care data . Many problems occur while linking medical records from various databases. Comparing these medical data to other data is challenging because even small mistakes, for example data entry errors and lacking data. The earlier research proposed that estimate field matching represent a technique to solve the issue by finding similar string values in several representations. In our proposed system, we are proposing the Neural network based matching patient records in multiple databases. We can enhance the performance of the record matching method by introducing the Neural network approach. This technique is can improve the overall performance of the system. Among many Neural network techniques, we are using the Elman Back propagation network technique.
References
- Xiaoyi Wang,Jiying Ling Multiple valued logic approach for matching patient records in multiple databases, Journal of Biomedical Informatics 45 (2012) 224–230.
- Verykios VS, Elmagarmid AK, Houstis EN. Automating the approximate record matching process. Inform Sci 2000;126:83–98.
- Kukich K. Techniques for automatically correcting words in text. ACM ComputSurv 1992;24(4):377–439
- Kukich K. Spelling correction for the tele-communications network for the deaf. Commun ACM 1992;35(5):80–90.
- Elmagarmid AK, Horowitz B, Karabatis G, Umar A. Issue in multisystem integration for achieving data reconciliation and aspects of solution. Technical report, Bellcore Research; 1996
- Trillium Software. How data profiling & analysis saves companies $millions. White paper in data integration and data quality management.
- Herzog TN, Scheuren FJ, Winkler WE, editors. Data quality and record linkage techniques. Washington, D. C. : Bureau of the Census; 2007.
- Fellegi and A. Sunter, A Theory for Record Linkage, Journal of the American Statistical Association 64 (1969), no. 328, 1183-1210.
- W. E. Winkler. Using the EM algorithm for weight computation in the Fellegi-Sunter model of record linkage. Technical Report RR2000/05, US Bureau of the Census, 2000.
- A. Elmagarmid, P. Ipeirotis, and V. Verykios. Duplicate record detection: A survey. IEEE Transactions on Knowledge and Data Engineering, 19(1):1–16, 2007
- W. E. Winkler. Overview of record linkage and current research directions. Technical Report RR2006/02, US Bureau of the Census, 2006.
- P. Christen and K. Goiser. Quality and complexity measures for data linkage and deduplication. In F. Guillet and H. Hamilton, editors, Quality Measures in Data Mining, volume 43 of Studies in Computational Intelligence. Springer, 2007
- M. Elfeky, V. Verykios, and A. Elmagarmid. TAILOR: A record linkage toolbox. In ICDE'02, pages 17–28, San Jose, 2002.
- I. Bhattacharya and L. Getoor. Collective entity resolution in relational data. ACM Transactions on Knowledge Discovery from Data (TKDD), 1(1), 2007.
- H. Yu, J. Han, and K. C. -C. Chang. PEBL: Positive example based learning for Web page classification using SVM. In ACM KDD'02, pages 239–248, Edmonton, 2002
- H. Yu, C. X. Zhai, and J. Han. Text classification from positive and unlabeled documents. In CIKM'03, pages 232–239, New Orleans, 2003
- Sotir Sotirov, Modelling the backpropagation algorithmof the Elman neural network by a generalized net, 13th Int. Workshop on Generalized Nets London, 29 October 2012, 49–55.