Key points are not available for this paper at this time.
The digitization of the healthcare domain has the potential to drastically improve healthcare services, reduce the time to diagnosis, and lower costs. However, digital applications for the healthcare domain need to be interoperable to maximize their potential. Additionally, with the rapid expansion of Artificial Intelligence (AI) and, specifically, Machine Learning (ML), large amounts of diverse types of data are being utilized. Thus, to achieve interoperability in such applications, the adoption of common semantic data models becomes imperative. In this paper, we describe the adoption of such a common semantic data model, using the well-known Health Level Seven Fast Health Interoperability Resources (HL7 FHIR) standard, in a platform that assists in the creation and storage of a plethora of AI-based applications for several medical conditions. The server's efficiency is being showcased by using it in an application predicting coronary artery stenosis as well as for managing the platform's key performance indicators.
Rigas et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: