23 July 2019 in Journal of Medical Internet Research
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). 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.
21 February 2019 in JMIR Preprints
BACKGROUND In recent years, researchers have made significant efforts in advancing blockchain technology. This technology, with distinct features of decentralization and security, can be applied to many fields. In areas of health data and resource sharing, applications of blockchain technology are also emerging. OBJECTIVE In this study, we propose a cloud health resource-sharing model based on consensus-oriented blockchain technology and have developed a simulation study on breast tumor diagnosis. METHODS The proposed platform is built on a consortium or federated blockchain that possesses features of both centralization and decentralization. The consensus mechanisms generate operating standards for the proposed model. Open source Ethereum code is employed to provide the blockchain environment. Proof of Authority 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. Each request is fulfilled by a service provider recommended by the weighted k-nearest neighbors (KNN) algorithm. The majority of service requests are handled by 9 providers, and provider service evaluation scores tend to stabilize. Also, 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 the potential to be applied to other applications.