Parsing Unstructured Healthcare Data Using Regular Expressions

Abstract

Healthcare organizations produce a substantial volume of healthcare data on a daily basis, managing and monitoring of the healthcare data is tedious and results in data explosion. The healthcare data generated should be properly maintained in the data repository otherwise leads to privacy threat. Most of the healthcare data are unstructured in nature and needs to be organized in a better format. Extracting the meaningful insights from the unstructured healthcare data is complex and most of the time it results in meaningless data. Unless the unstructured healthcare data is transformed to structured healthcare data, proper insights cannot be drawn from the healthcare data. Parsing Unstructured Healthcare Data (PUHD) using the regular expressions helps in identifying the key value elements from the unstructured healthcare data which are the demographic data of the patient and analysis of the healthcare data from these key value elements becomes easier.  So, there is a need to design a system that achieves automatic extraction of the key value elements from the unstructured healthcare data.