# Decentralized Health Intelligence Network (DHIN)

arXiv: https://arxiv.org/abs/2408.06240 · HTML: https://mlsanity.com/paper/2408.06240/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 50 references that are in the map.
- First posted on arXiv 12 Aug 2024.

## Builds on (most cited first, 11 of 11)

- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments](https://mlsanity.com/paper/2104.14380/) (2021)
- [IPFS - Content Addressed, Versioned, P2P File System](https://mlsanity.com/paper/1407.3561/) (2014)
- [BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learning](https://mlsanity.com/paper/2007.03856/) (2020)
- [Federated Learning at the Network Edge: When Not All Nodes are Created Equal](https://mlsanity.com/paper/2101.01995/) (2021)
- [A blockchain-orchestrated Federated Learning architecture for healthcare consortia](https://mlsanity.com/paper/1910.12603/) (2019)
- [FHIRChain: Applying Blockchain to Securely and Scalably Share Clinical Data](https://mlsanity.com/paper/1807.03227/) (2018)
- [2CP: Decentralized Protocols to Transparently Evaluate Contributivity in Blockchain Federated Learning Environments](https://mlsanity.com/paper/2011.07516/) (2020)
- [Libertas: Privacy-Preserving Collective Computation for Decentralised Personal Data Stores](https://mlsanity.com/paper/2309.16365/) (2023)
- [Secret Sharing Sharing For Highly Scalable Secure Aggregation](https://mlsanity.com/paper/2201.00864/) (2022)
- [Decentralized Intelligence Network (DIN)](https://mlsanity.com/paper/2407.02461/) (2024)

## Abstract (arXiv)

Decentralized Health Intelligence Network (DHIN) extends the Decentralized Intelligence Network (DIN) framework to address challenges in healthcare data sovereignty and AI utilization. Building upon DIN's core principles, DHIN introduces healthcare-specific components to tackle data fragmentation across providers and institutions, establishing a sovereign architecture for healthcare provision. It facilitates effective AI utilization by overcoming barriers to accessing diverse health data sources. This comprehensive framework leverages: 1) self-sovereign identity architecture coupled with a personal health record (PHR), extending DIN's personal data stores concept to ensure health data sovereignty; 2) a scalable federated learning (FL) protocol implemented on a public blockchain for decentralized AI training in healthcare, tailored for medical data; and 3) a scalable, trustless rewards mechanism adapted from DIN to incentivize participation in healthcare AI development. DHIN operates on a public blockchain with an immutable record, ensuring that no entity can control access to health data or determine financial benefits. It supports effective AI training while allowing patients to maintain control over their health data, benefit financially, and contribute to a decentralized ecosystem. Unique to DHIN, patients receive rewards in digital wallets as an incentive to opt into the FL protocol, with a long-term roadmap to fund decentralized insurance solutions. This approach introduces a novel, self-financed healthcare model that adapts to individual needs, complements existing systems, and redefines universal coverage, showcasing how DIN principles can transform healthcare data management and AI utilization while empowering patients.