Medical data security sharing method based on block chain and federated learning

Abstract

The invention discloses a medical data security sharing method based on a block chain and federated learning. The data applicant can use the data after being authorized on the chain of the data provider; the data fingerprint carries out hash abstract chaining on authorized data, the problem that the authorized data is maliciously tampered to cause data inconsistency is prevented, the use right ofthe original data is shared in the whole process, a data user cannot directly obtain the data, and the value of the data can be mined only through federated learning. In each round of iterative computation of federated learning, asset chaining is carried out on model parameters and aggregation results, and credible traceability of federated learning computation can be achieved. Each step of operation in the data sharing process is subjected to related auditing by a supervisor, such as identity auditing, data checking, transaction detail auditing and the like. According to the invention, aggregation calculation is carried out without the help of a central server, decentralized federated learning is realized, aggregation calculation is realized through an intelligent contract, and maliciousaggregation calculation results received by each node due to malicious control of the central server are avoided.

Description

technical field [0001] The invention relates to the fields of blockchain and medical data security, in particular to a method for safely sharing medical data based on blockchain and federated learning. Background technique [0002] For a hospital, medical scientific research is to use advanced scientific and technological means to focus on solving practical problems in clinical work. This is an important means for the hospital's discipline construction and personnel training, and it is also the most powerful guarantee for the hospital's continuous, steady and rapid development. . Data is one of the important driving forces for the development of the information age, among which medical data play a major role in clinical medical research. The combination of artificial intelligence, big data, blockchain and other cutting-edge technologies and medical data through the combination of medical and industrial methods can assist Doctors carry out patient disease screening, patholog...

AI Technical Summary

Problems solved by technology

However, considering issues such as industry competition, data privacy security, etc., I am extremely worried that the core data of my own business will be leaked and abused, so large and small "data islands" have formed. Not only is it difficult to share data across departments within the same organization, but also between different organizations. of data sharing faces huge obstacles

[0003] For a long time, hospital researchers have directly copied the relevant data through the traditional method of mobile hard disks. Although paper guarantees such as relevant data usage applications and data confidentiality agreements are signed offline before data copying, there are still problems such as slow manual application efficiency and data leakage.

Because clinical scientific research experiments in hospitals usually require large-scale data support, data isolation exists on multiple platforms within the hospital, and data between hospitals cannot be interconnected. If only part of the data in the hospital is used for scientific research and analysis, the experimental results will inevitably lack Authoritative and persuasive, so it is urgent to formulate a set of data sharing standards and build a platform to realize medical data sharing, so as to promote the development of medical research and the transformation of achievements

At present, some medical data sharing products have been developed and put into use. However, most of the existing medical data sharing platforms converge the shared data to the platform. Data aggregation will increase the data storage burden of the platform, and the data stored on the platform Without encryption measures, the data user cannot realize the follow-up control and tracking of the data after downloading the data from the platform, which may lead to malicious use of the data, and there is a risk of data leakage, which will seriously violate the privacy rights of patients and cause inevitable medical disputes serious social problems

Images