JMIR Publications

ABSTRACT

Background:

In recent years, an increasing number of researchers have made significant effort in advancing the blockchain technology. This technology, with distinct features of decentralization and security, can be applied to many fields. On the aspects of health data and resource sharing, the application blockchain technology is emerging.

Objective:

In this study, we propose a cloud health resource sharing model based on consensus-oriented blockchain technology and develop a simulation study on the service of breast tumor diagnosis.

Methods:

The proposed platform is built on a consortium or federated blockchain which possesses the features of both centralization and decentralization. The consensus mechanisms generate the operating standards for the proposed model. The open source Ethereum code is employed to provide the blockchain environment. Proof-of-Authority (PoA) is selected as the consensus algorithm of block generation.

Results:

Based on the proposed model, a simulation case study for breast tumor classification is constructed. The simulation includes 9893 service requests from 100 users. 22 service providers are equipped with 22 different classification methods, respectively. Each request is fulfilled by a service provider which is recommended by the weighted k-nearest neighbors (KNN) algorithm. It is shown that the majority of service requests tend to be taken by 9 providers and the provider’s score of service evaluation tends to be stabilize. Also, the user priority on KNN weights significantly affects the system operation outcome.

Conclusions:

The proposed model is feasible based on the simulation case study for the cloud service of breast tumor diagnosis and has potential to be applied to many other purposes.