Publishing Electronic Medical Record akin to Privacy

Area of Science:

• Health Informatics
• Data Science
• Medical Research

Background:

• Electronic Medical Records (EMR) are crucial for medical learning and research.
• Sharing EMR data with analysts is vital for social welfare but poses privacy challenges.
• Conventional data sanitization methods struggle to balance privacy and data utility.

Purpose of the Study:

• To introduce and evaluate a new technique, Generalized Average Partition (GAP), for EMR data handling.
• To assess the trade-offs between privacy preservation and data utility in EMR data sanitization.
• To compare GAP with conventional methods regarding privacy and accuracy losses.

Main Methods:

• Development of the Generalized Average Partition (GAP) technique specifically for EMR data.
• Calculation and analysis of privacy and accuracy losses for GAP.
• Comparative analysis of GAP against selected conventional data sanitization methods.

Main Results:

• GAP is designed to preserve patient privacy while maintaining data utility in EMR datasets.
• The study quantifies privacy and accuracy losses associated with GAP and conventional methods.
• Results demonstrate GAP's effectiveness in addressing the limitations of existing techniques.

Conclusions:

• Generalized Average Partition (GAP) offers an improved approach to sanitizing Electronic Medical Records.
• Effective EMR data handling requires methods that preserve both patient privacy and analytical accuracy.
• GAP provides a promising solution for secure and reliable medical data analysis for social welfare.