Abstract Healthcare interoperability has traditionally relied on structured standards such as HL7 and Fast Healthcare Interoperability Resources (FHIR), which remain complex and costly to implement and maintain. This article evaluates the potential of Digital Imaging and Communications in Medicine (DICOM), combined with artificial intelligence (AI), as an alternative paradigm for data exchange. Drawing on current literature and real-world implementations, it highlights how DICOM enables standardized, high-fidelity data sharing, while advances in generative and multimodal AI allow extraction of structured clinical insights directly from images. Emerging applications in radiology and pathology demonstrate reduced integration complexity and improved data fidelity, although this approach introduces greater data storage and computational demands. DICOM augmented by AI represents a promising complementary model to traditional interoperability standards; however, HL7 and FHIR are likely to remain relevant within hybrid frameworks as technical, regulatory, and clinical adoption challenges evolve.
Rahul Garg (Thu,) studied this question.