When appropriate, research data should be de-identified to prevent accidental disclosure of private information. De-identified is necessary because it will not allow the information collected or gathered to be used for somebody else. This will protect the privacy of the individuals involved in the research data.
De-identification is the process used in preventing someone’s identity from been exposed or revealed. For example the research data of an individual might be de-identified for the purpose of keeping it away from other participant in the research.
De-identification process involves the removal of direct data that can reveal individual information such as addresses, name, and phone numbers, etc. Though some data may contain indirect identifiers such as occupation, post code, age or ethnic, that do not reveal the identity of individual on their own, but such data could be merged with other information to reveal the identity of individual and therefore should be considered to be removed based on the data collected.
De-identification is embraced as a viable means to protect data privacy of individuals. It is used broadly in communication, data mining, social networks, web, and audio-video monitoring.
De-identification can be costly and time-consuming and sometimes the process of removing identifiable data elements could also result to loss of data value.
KEYWORDS:
- research data
- reveal the identity
- identity of individual