Assessment of Data Quality in Health Care Using Association Rules
K.Suganya1, S.Dhamodharan2
1K. Suganya, Computer Science and Engineering, Sathyabama University, Chennai, India.
2S.Dhamodharan, Computer Science and Engineering, Sathyabama University, Chennai, India.
Manuscript received on March 23, 2014. | Revised Manuscript received on April 12, 2014. | Manuscript published on April 30, 2014. | PP: 36-37 | Volume-3, Issue-4, April 2014. | Retrieval Number: C2703023314/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: To find the outlier and disease possibility of ten cancer diseases. In the existing system, Transactional data of three companies are taken as input. Association rules are extracted from the input data using open source data mining tool. By applying consistency rule, the outliers are identified. Outliers are manually examined to determine whether any data quality is violation has really occurred. Cost for manual examination is estimated using confusion matrix. In this system, recorded patient details is taken as input. From the input data, association rule is identified and outliers are detected. Weight is assigned to each symptoms of all considered cancer disease. When user enters the symptoms, percentage of cancer disease possibility is calculated.
Keywords: Association rule, Outlier, Consistency rule.