Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Differential privacy protection method for medical data release

A differential privacy and medical data technology, applied in digital data protection, electronic digital data processing, instruments, etc., can solve the problem of leaking patients' personal information and achieve the effect of preventing the risk of patient information leakage

Active Publication Date: 2018-04-20
GUANGXI NORMAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is still possible to leak the personal information of the patient, and others (attackers) can re-identify the patient corresponding to a record through the combination of some quasi-identifier information (such as gender, age, address, occupation)

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Differential privacy protection method for medical data release
  • Differential privacy protection method for medical data release
  • Differential privacy protection method for medical data release

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described in detail below in conjunction with specific embodiments.

[0035] Explanation of related terms used in the present invention:

[0036] 1. Attribute: Each column in the data table is an attribute, such as age, gender, occupation, disease, etc.

[0037] 2. Attribute value: In the attribute value hierarchy tree corresponding to each attribute, each node can be used as the attribute value of the attribute, but the semantic scope represented by nodes at different levels is different. For example, in the hierarchical tree of occupational attribute values, the two sub-nodes of blue-collar workers are technicians and non-skilled workers respectively, then we can generalize the attribute values ​​of skilled workers and non-skilled workers into blue-collar workers (that is, through generalization, we can use The attribute value of the upper layer node represents the associated lower layer attribute value); similarly, the upper lay...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a differential privacy protection method of medical data dissemination. A K-anonymous technology and a differential privacy technology are effectively combined to solve the problems that the statistical information of data can not guaranteed to be prevented from being leaked when the K-anonymous technology is solely used, a great quantity of noise is introduced while the differential privacy technology is solely used to only protect the statistical information, a data distortion degree becomes high to lower data utilizability; and therefore, on the premise that the medical data is guaranteed to be available, the risk of patient information leakage when the medical data is collected and disseminated can be effectively avoided so as to perform the efficacy of the medical data during statistics and mining.

Description

technical field [0001] The invention relates to the technical field of data classification, in particular to a differential privacy protection method for publishing medical data. Background technique [0002] At present, most of the electronic medical record information systems that have been promoted and used in hospitals in my country use patients as processing objects to provide transaction processing, generally including patient personal information, disease names, and operation records, etc. Raw records, which contain both numeric and discrete data. Electronic medical records are mainly for the purpose of quickly and effectively completing the registration of patients and the storage, query, viewing and settlement of diagnosis and treatment expenses of patients and medical records. Various departments in the hospital can effectively manage and count data in such a medical record management system, such as the average treatment cost of inpatients, the number of inpatient...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F21/62
CPCG06F21/6245G06F2221/2107
Inventor 李先贤钟盛海刘鹏王利娥
Owner GUANGXI NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products