Impact of Data Imputation Methods in Data Analytics for Healthcare Data

Abstract

The healthcare industry has a lot of data which could be used effectively to predict or classify diseases with the help of data mining and machine learning techniques. However, the missing data is a very common occurrence in healthcare and can have grave impacts on the conclusions that can be drawn from the data. Developing a generalized imputation strategy that can be used across a variety of datasets is difficult as each dataset has its own attributes, characteristics, and intrinsic structures. The objective of this paper is to classify the popular data imputation methods for healthcare data and analyze and compare their performance.