Secure Survival Data Processing System for Privacy-Preserving Logrank Tests
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional logrank tests using plaintext calculations pose a risk of privacy infringement when dealing with sensitive clinical data, as they do not effectively conceal survival time data, making it difficult to obtain the number of survivors or deaths without revealing the underlying information.
Innovation Solution
A secure survival time data processing system utilizing at least three secure computing apparatuses to calculate shares of the number of survivors and deaths, employing methods such as secret sharing and secure batch mapping to maintain data confidentiality, allowing for secure computation of statistical differences while concealing the original data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If plaintext calculations are used in logrank tests, then calculation simplicity is maintained, but privacy protection is compromised
Solution Approach 1:
The patent divides the calculation process into multiple stages where intermediate results are distributed among multiple computing devices. Each device holds only a portion of the data or intermediate results, preventing any single device from accessing complete survival time data. This segmentation maintains calculation simplicity while protecting privacy through distributed computation.
Solution Approach 2:
The patent introduces an intermediary mechanism where a third-party computing device facilitates the logrank test calculations. This intermediary handles the complex secure computation operations, allowing the original data holders to perform simple data submission while the intermediary performs the privacy-preserving calculations and returns only final results.
2Object-affected harmful factors
If secure computing methods are applied to conceal survival time data, then privacy protection is improved, but the ability to obtain number of survivors or deaths is compromised
Solution Approach 1:
The patent performs preliminary sorting and grouping of survival time data before the actual logrank test calculations. By pre-organizing the data into time-based groups and identifying which specimens are still surviving at each time point, the system enables subsequent calculations of survival counts and death counts without needing to access or reveal the underlying concealed survival time data during the test execution.
Solution Approach 2:
The patent replaces direct mechanical access to survival time data with cryptographic and statistical methods. Instead of physically examining the data to count survivors or deaths, the system uses secure computation protocols, secret sharing, and statistical aggregation techniques to derive these counts from concealed data representations.
3Adaptability or versatility
If conventional logrank test procedures are used, then statistical analysis capability is maintained, but data confidentiality is lost
Solution Approach 1:
The patent transitions the logrank test from operating on raw survival time data to operating on transformed representations such as encrypted data, secret-shared values, or aggregated statistics. This dimensional transformation allows the statistical analysis to proceed on a different level of data abstraction, preserving confidentiality while maintaining analytical capability.
Data Source
AI summary
The present invention provides techniques to calculate the number of surviving and the number of deaths while still concealing survival time data. The present invention includes: a group data position calculation means configured to calculate a share [[gA]] of a sequence gA and a share [[gB]] of a sequence gB represented by predetermined equations from a share [[g]] of a sequence g of values of group of survival time data included in a survival time data set D; a group data number calculation means configured to calculate a share [[sA]] and a share [[sB]] from a share [[t]] of a sequence t of values of time of survival time data included in the survival time data set D, the share [[gA]], and the share [[gB]], by [[sA]]=GroupSum ([[gA]], [[t]]), [[sB]]=GroupSum ([[gB]], [[t]]); and a survival number calculation means.


