Birth registration is a critical element of newborn care. Increasing the coverage of birth registration is an essential part of the strategy to improve newborn survival globally, and is central to achieving greater health, social, and economic equity as defined under the United Nations Sustainable Development Goals. Parts of Eastern and Southern Africa have some of the lowest birth registration rates in the world. Mobile technologies have been used successfully with mothers and health workers in Africa to increase coverage of essential newborn care, including birth registration. However, mounting concerns about data ownership and data protection in the digital age are driving the search for scalable, user-centered, privacy protecting identity solutions. There is increasing interest in understanding if a self-sovereign identity (SSI) approach can help lower the barriers to birth registration by empowering families with a smartphone based process while providing high levels of data privacy and security in populations where birth registration rates are low. The process of birth registration and the barriers experienced by stakeholders are highly contextual. There is currently a gap in the literature with regard to modeling birth registration using SSI technology. This paper describes the development of a smartphone-based prototype system that allows interaction between families and health workers to carry out the initial steps of birth registration and linkage of mothers-baby pairs in an urban Kenyan setting using verifiable credentials, decentralized identifiers, and the emerging standards for their implementation in identity systems. The goal of the project was to develop a high fidelity prototype that could be used to obtain end-user feedback related to the feasibility and acceptability of an SSI approach in a particular Kenyan healthcare context. This paper will focus on how this technology was adapted for the specific context and implications for future research.

Adopting shared data resources requires scientists to place trust in the originators of the data. When shared data is later used in the development of artificial intelligence (AI) systems or machine learning (ML) models, the trust lineage extends to the users of the system, typically practitioners in fields such as healthcare and finance. Practitioners rely on AI developers to have used relevant, trustworthy data, but may have limited insight and recourse. This article introduces a software architecture and implementation of a system based on design patterns from the field of self-sovereign identity.Scientists can issue signed credentials attesting to qualities of their data resources.Data contributions to ML models are recorded in a bill of materials (BOM), which is stored with the model as a verifiable credential. The BOM provides a traceable record of the supply chain for an AI system, which facilitates on-going scrutiny of the qualities of the contributing components. The verified BOM, and its linkage to certified data qualities, is used in the AI scrutineer, a web-based tool designed to offer practitioners insight into ML model constituents and highlight any problems with adopted datasets, should they be found to have biased data or be otherwise discredited.

No abstract

No abstract

No abstract