Using Blockchain and Distributed Machine Learning to Manage Decentralized but Trustworthy Disease Data

ABSTRACT

Public health surveillance systems for infectious diseases, that can turn pandemic, need a regular intervention for diagnosis, treatment and control. For an effective disease monitoring and control system, there is a need to model a solution for organizing, sharing and analyzing the disease data with trusted, privacy-preserving and interoperable methodologies to improve the outreach, time and cost-effectiveness for disease-control and treatment interventions. Blockchain has emerged as one of the promising technologies owing to its unique features like decentralization, transparency, immutability, data provenance and cryptography. The primary aim of this study is to perform a bibliometric analysis of literature on the applications of blockchain in disease data management systems. Secondly, it is aimed to survey the suitability of existing blockchain platforms for disease data storage, sharing and analytics. This study also explored literature on the design of privacy-preserving machine learning models on blockchain applications for collaborative learning. Conclusively, the presented survey opens opportunities to the building of privacy-preserving, trusted, interoperable and inferring disease data management systems with blockchain and machine learning.

KEYWORDS:

• Blockchain
• Privacy-preserving
• Distributed machine learning
• Electronic Healthcare Records
• Bibliometric analysis

Declaration of interest statement

Madhuri Hiwale, Dr. Shraddha Phansalkar, Dr. Ketan Kotecha declare that they have no conflict of interest.