PRIVACY-PRESERVING DATA ANONYMIZATION TOOL FOR MEDICAL DATA

Background: Medical institutions collect vast amounts of sensitive patient data for personalized treatments and health trend analysis. However, this raises concerns regarding the privacy of patient data, as it contains sensitive and confidential information. Aims: Develop an anonymization tool using diverse techniques to protect data while preserving its utility. Methods: A Python-based data anonymization tool for medical datasets supporting both categorical and numerical data is developed. It employs various methods, including data perturbation, binning, scaling, transformation, and differential privacy. Results: The tool was able to anonymize the sensitive data, both categorical and numerical, while at the same time preserving its utility for further analysis. Discussion: The Privacy-Preserving Data Anonymization Tool advances sensitive medical data management by anonymizing both categorical and numerical data using various techniques while retaining data utility. Conclusions: The Anonymization Tool addresses patient data privacy concerns by balancing data utility with privacy, enabling secure medical data use in research.