Towards Multimodal Information Architecture: A Social-Technical Approach of Artificial Intelligence Development in Inova HFA’s Electronic Health Record (EHR)

The project’s goal is the use of Artificial Intelligence (AI), Distributed Ledger Technology (DLT) and Smart Contracts to solve the registers’ management problems, more specifically, but not only, Electronic Health Record (EHR) problems, like how to use the register to improve patients’ health and at the same time obey the General Personal Data Protection Law (LGPD, Brazilian law number 13.709-2018). Another goal is the early recognition of clinical deterioration, based on the digital medical records. The first part of the study was based on the fact that the use of archival methods and Blockchain and Smart Contracts technologies can positively contribute to the management of electronic patient records. In this study we will focus on present Multimodal Information Architecture contributions on information organizing on training artificial neural networks, aiming to position Information Science as an active body of knowledge in artificial intelligence problems. Make use of Multimodal Information Architecture (MIA) definitions, following the technological phase (implementation of the theoretical-scientific vision with an explanatory and qualitative approach. A five-step procedure is proposed for the design, analysis and transformation of informational spaces used in training and learning methods of neural networks, to complement gaps identified by authors focused on Computer Science implementations. This study is being developed with the support of the Brazilian Armed Forces Hospital (HFA) and is part of the INTERPARES TRUST AI, a multi-national interdisciplinary project aiming to design, develop, and leverage Artificial Intelligence to support the ongoing availability and accessibility of trustworthy public records.