Anonimização de informação clínica

Abstract

Over the past years, with the progress of technology, the amount of data being collected by the IT systems has exponentially grown. By using data mining techniques, this data can be analyzed to find trends and statistics, which are really useful for all companies and industries. The analysis and data sharing for studies became a large industry, with a great impact in all sectors. However, with this comes the concern with individual privacy - there is a huge amount of data which is private and should not be public in any circumstances - so, it is highly needed to find a solution to share and analyse data while protecting privacy. Nevertheless, it is truly important to take into account performance issues as the anonymization process should not hinder the normal functioning of the operational system. The focus goes to clinical data, which allows medical researchers to learn trends, statistics and relations between certain clinical attributes, such as correlations between gender and a specific disease. These studies and data analysis are very important as they can bring great benefits and knowledge in healthcare. However, maintaining individual privacy is crucial. In order to solve this problem, a new solution will be proposed and developed to efficiently anonymize data. With this solution, the user can quickly and efficiently anonymize a given dataset, according to the initially provided configurations. The tool receives as input the dataset to anonymize and a minimal configuration to specify the required anonymization parameters, and returns as output the corresponding anonymized dataset. The anonymization is done recurring to well known models and algorithms to protect privacy, associated with specific clinical criteria, restrictions and hierarchies. This solution will be validated using a subset of clinical data that needs to be anonymized. After the anonymization process, an anonymized version of the subset is expected that meets the selected privacy model, balancing enough privacy versus keeping research value. As well as the result, the performance will be evaluated in order to validate the solution's applicability. It is intended with this solution to surpass the issue of individual data privacy when sharing data and to have impact in healthcare studies, allowing them to continue without connecting any data to any specific identity, protecting individual privacy.