Digital Infrastructures and Data Interoperability in Radiology for Prevention: From Digital Health to AI-enabled, Quantitative Imaging Workflows
放射学中用于预防的数字基础设施与数据互操作性 - 生物通
Summary
This article discusses digital infrastructure and data interoperability in radiology, explaining AI-enabled quantitative imaging workflows aimed at preventative care. It emphasizes that the integration of standards like DICOM and HL7 FHIR is crucial and indispensable for future AI utilization.
Details
The paper delves into digital infrastructures and data interoperability in radiology, focusing on AI-enabled quantitative imaging workflows designed for application in preventative medicine. Specifically, it points out the limitations of traditional DICOM formats and stresses the necessity of enhancing data linkage by utilizing standards such as HL7 FHIR and IHE. Technically, effective information sharing between systems like PACS (Picture Archiving and Communication System) and EHR (Electronic Health Record) is vital. The text highlights that developing APIs and interfaces to integrate AI analysis results into the workflow is necessary. Furthermore, the transition from DICOM to HL7 FHIR is described not merely as a format change but as a paradigm shift toward achieving information exchange within a clinical context. Additionally, it is stated that utilizing specialized terminologies like SNOMED CT and RadLex, along with setting up Scheduled Workflows, are key to effectively leveraging AI and providing high-quality medical care. These standardized data exchange foundations are deeply related to international healthcare IT trends.
Original content copyright by respective publishers