Min Feature Replacement Algorithm Based Multiple Imputation Based Gap Analysis for Clinical Data
M. Sangeetha1, M. Senthil Kumaran2

1M.Sangeetha, Department of Information Technology, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
2M.Senthil Kumaran, Department of Computer Science and Engineering, SCSVMV, Kanchipuram (Tamil Nadu), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 633-637 | Volume-8 Issue-5, March 2019 | Retrieval Number: E3297038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: The impact of technology has expanded its wings in many fields and medical domain has great impact from technology development. The technology development has been enforced in medical organization to convert the patient details from the charts to electronic form of health records. The patient records have numerous information and not all of them are important and they have been visited for specific purposes like medical reimbursement from insurance corporations. There are departments in medical organization which consists of doctors, specialists and nurses. They always look for the precise information regarding the patient about their diagnosis results and treatments. They focus on generating documentation in efficient way which provides necessary information in accurate manner. The problem of clinical document improvement has been well studied. There are number of issues has been identified from the way the clinical documents has been published. This work, present a min feature replacement based multiple imputation technique for efficient gap analysis. The method reads the input data set and identifies the list of features and estimates the minimum feature values. Second for each record, the method identifies the missing values, and replaces them with min feature value identified. The replaced imputed data set has been used to perform disease prediction. The method produces higher performance in multiple imputations and improves the performance of prediction.
Keyword: Multiple Imputations, Missing Values, HCS, CDI, Gap Analysis, Publication.
Scope of the Article: Data Visualization