Information is essential to delivering effective healthcare. Health information traditionally resides with the entity providing health- care to the patient. However, this is just one model for how information can be situated within a healthcare context.
Decentralized health networks provide the infrastructure to realize a different information and computational model that centers the locus of health information around the patients.
Commonhealth is a framework for building and testing decentralized health networks that enable people/patients to share their data with a decentralized network in order to gain informational value derived from insights that can be gleaned from this collective data.
While decentralized networks disperse control of health information amongst a network of individuals, they require careful design and testing to ensure the networks incentives promote the interests of each member, scale cost- effectively and protect privacy. Deploying a novel decentralized health network without appropriate testing presents multiple risks including risk of data breach, erroneous machine learning model predictions and costly platform management.
To counter these risks, we developed a commonhealth proof of concept system and tested it using a multi-agent approach. We demonstrated in the paper below that this approach can be helpful in testing and refining the creation of such a network such that the incentives are robust, sustainable and less likely to be exploited by bad actors. We found that agentbased approaches can help speed up development of decentralized health networks and build confidence in their scalability, safety and effective functioning before deploying in a real world context with patients
Articles
Matthews, M., Collier, R. & Spendlove, E. (In Review). CommonHealth: multi-agent evaluation of blockchain-based patient-centred health data networks. In European Conference on Multi-Agent Systems.
Code
https://csgitlab.ucd.ie/SirMilt/commonhealth/-/tree/master
