Data Mining and Knowledge Engineering

K. V. Uma ¹, S. Appavu Alias Balamurugan ²

Affiliations
1 Department of Information Technology, Thiagarajar College of Engineering, Madurai, IN
2 K.L.N. College of Information Technology, Pottapalayam, Sivagangai, IN

Abstract

An adverse drug reaction (ADR) is an expression that describes harm associated with the use of given medications at a normal dosage during normal use. ADRs may occur following a single dose or prolonged administration of a drug or result from the combination of two or more drugs. The data on Adverse Drug Reactions are abundant, incomplete and consumes huge space to store. No quantitative conclusions can be drawn from the reported data in regard to mortality, or the underlying causes of ADRs. Hence two drugs namely vioxx and warfarin taken to show that different reactions are caused when the drug is taken in single and in combinations. Association rules are used to find the association between drug and adverse event. Here association rules are generated using probability analysis method .In this method the 2*2 contingency table is constructed for the drugs and the adverse event and the chi-square statistics is found out based on the goodness of fit. With the chi-square test, it is possible to determine only the relative strength of association, not to distinguish the interaction relationships between the drugs. For that Probabilistic model is constructed and based on that adverse event is found out whether due to single drug or drug in combination. Then patient’s demographic information such as gender, age are taken and drug route is also considered to find out if symptom due to drug and with these additional conditions. They are analyzed using ID3 algorithm.

Keywords

Adverse Drug Reaction, Leverage, Chi-Square, Association Rules, Decision Tree.

Full Text

     

S. Appavu Alias Balamurugan ¹, A. B. Arockia Christopher ¹

Affiliations
1 Department of Information Technology, Thiagarajar College of Engineering, Madurai, IN

Abstract

In real world datasets, lots of redundant and conflicting data exists. The performance of a classification algorithm in data mining is greatly affected by noisy information (i.e. redundant and conflicting data). These parameters not only increase the cost of mining process, but also degrade the detection performance of the classifiers. They have to be removed to increase the efficiency and accuracy of the classifiers. This process is called as the tuning of the dataset. The redundancy check will be performed on the original dataset and the resultant is to be preserved. This resultant dataset is to be then checked for conflicting data and if they will be corrected and updated to the original dataset. This updated dataset is to be then classified using a variety of classifiers like Multilayer perceptron, SVM, Decision stump, Kstar, LWL, Rep tree, Decision table, ID3, J48 and Naïve Bayes. The performance of the updated datasets on these classifiers is to be found. The results will show a significant improvement in the classification accuracy when redundancy and conflicts are to be removed. The conflicts after correction ate be updated to the original dataset, and when the performance of the classifier is to be evaluated, great improvement is to be witnessed.

Keywords

Data Mining, Classification Algorithm, Redundancy, Conflicting Data.

Full Text