Development and Algorithmization of a Method for Analyzing the Degree of Uniqueness of Personal Medical Data

Abstract

The purpose of this investigation is to develop a method for quantitative assessment of the uniqueness of personal medical data (PMD) to improve their protection in medical information systems (MIS). The relevance of the goal is due to the fact that impersonal PMD can form unique combinations that are potentially of interest to intruders and threaten to reveal the patient's identity and medical confidentiality. Existing approaches were analyzed, and a new method for quantifying the degree of uniqueness of PMD was proposed. A weakness in existing approaches is the assumption that an attacker will use exact matching to identify people. The novelty of the method proposed in this paper lies in the fact that it is not limited to this hypothesis, although it has its limitations: it is not applicable to small samples. The developed method for determining the PMD uniqueness coefficient is based on the assumption of a multidimensional distribution of features, characterized by a covariance matrix, and a normal distribution, which provides the most reliable reflection of the existing relationships between features when analyzing large data samples. The results obtained in computational experiments show that efficiency is no worse than that of focus groups of specialized experts. Doi: 10.28991/HIJ-2023-04-01-09 Full Text: PDF