AI-Enabled Interoperability and Cloud Orchestration: Redefining Healthcare Information Management for a Connected Ecosystem

Available online www.ejaet.com European Journal of Advances in Engineering and Technology, 2022, 9(6):103-109 Research Article ISSN: 2394 - 658X 103 AI-Enabled Interoperability and Cloud Orchestration: Redefining Healthcare Information Management for a Connected Ecosystem Sudhir Vishnubhatla Senior Software Developer - Tampa, USA _____________________________________________________________________________________________ ABSTRACT The healthcare sector has experienced a significant shift as artificial intelligence (AI), interoperability standards, and cloud orchestration converged to create more intelligent, scalable, and secure information ecosystems. Historically, healthcare information management relied on fragmented systems, manual processes, and static data silos that limited collaboration and real-time insights. By the early 2020s, increasing regulatory mandates for data accessibility, the widespread adoption of FHIR-based interoperability frameworks, and advancements in AIdriven orchestration platforms transformed these limitations into opportunities for seamless integration and automation. These technologies enabled health systems to securely exchange and process clinical data in real time, support advanced analytics, and personalize care delivery. This article explores the evolution of healthcare information architectures, the cloud-native technologies enabling these transformations, and how AI enhances predictive insights, regulatory compliance, and patient-centered outcomes. Keywords: Healthcare Information Management, Cloud Orchestration, AI in Healthcare, Interoperability, FHIR, DICOMweb, openEHR, TEFCA, HIPAA, Digital Health Data, Workflow Automation _____________________________________________________________________________________________ INTRODUCTION For decades, healthcare information systems were designed primarily for administrative efficiency and internal record-keeping rather than for interoperability or cross-institutional collaboration. These systems were built as proprietary, closed platforms that often required expensive, rigid integrations to communicate with external applications. Hospitals relied heavily on on-premises databases that stored patient data in isolated silos, making it difficult to share information with other departments or external providers. Manual data entry was the norm, and interfaces between systems were mostly point-to-point connections, which were brittle, expensive to maintain, and incapable of supporting large-scale, real-time data exchange. As a result, patient data was fragmented across multiple systems, leading to incomplete care histories and operational inefficiencies that affected both clinical outcomes and administrative workflows. The explosion of digital health data in the 2010s fundamentally challenged this legacy architecture. Electronic Health Records (EHRs) began generating massive volumes of structured and unstructured data, while new data streams emerged from wearable devices, remote monitoring solutions, genomic sequencing technologies, and highresolution medical imaging systems. Traditional health IT infrastructures were not designed to handle this scale and complexity, creating an urgent need for more flexible and scalable solutions. Clinicians and administrators struggled to gain a holistic view of patient information, and the lack of interoperability meant critical data often remained trapped in departmental systems. This fragmentation impeded population health management, slowed down clinical research, and created barriers to implementing AI-driven diagnostic and predictive tools. At the same time, regulatory and policy landscapes began to evolve rapidly to address these interoperability gaps. The introduction of the Health Insurance Portability and Accountability Act (HIPAA) in 2000 laid the foundation for secure health information exchange, focusing on patient privacy and data security. Over the following two decades, interoperability standards such as HL7 FHIR emerged to provide standardized formats and APIs for data exchange between disparate health systems. These standards made it possible to unify fragmented data sources into interoperable ecosystems where different healthcare stakeholders, hospitals, labs, insurers, public health agencies, and patients could access and share relevant information in real time. These regulatory and interoperability milestones set the foundation for the technological renaissance that followed — powered by cloud-native infrastructure and intelligent automation. Vishnubhatla S Euro. J. Adv. Engg. Tech., 2022, 9(6):103-109 104 The rise of cloud computing added another transformative layer. Cloud-native orchestration platforms enabled healthcare organizations to migrate from static on-premises systems to elastic, secure, and scalable infrastructures. These platforms leveraged containerized workflows and managed orchestration tools such as Kubernetes and serverless pipelines to achieve high scalability, resilience, and automation in healthcare workloads. Services offered by major cloud providers made it possible to build FHIR-enabled data lakes, integrate DICOMweb for imaging, and securely manage patient identity and consent through APIs and OAuth-based authentication frameworks. These capabilities unlocked real-time data processing, advanced analytics, and AI-assisted decision support while maintaining compliance with regulatory standards. AI technologies further amplified these transformations by enabling intelligent data interpretation, automated triage, predictive diagnostics, and personalized treatment planning. Machine learning models could analyze vast amounts of structured and unstructured clinical data to identify patterns, detect anomalies, and support preventive care initiatives. When combined with interoperability standards and cloud orchestration, AI allowed healthcare systems to transition from fragmented, reactive processes to proactive, data-driven care delivery. This convergence of regulatory frameworks, interoperability standards, cloud-native platforms, and AI has fundamentally redefined healthcare information management, creating secure, scalable, and patient-centered ecosystems built for the future of medicine. EVOLUTION OF HEALTHCARE INFORMATION SYSTEMS In the early 2000s, health information management operated within a highly rigid, fragmented, and technically constrained environment. Most healthcare systems relied on static data exchange mechanisms, typically built on HL7 v2 messaging standards developed decades earlier. While HL7 v2 provided a way for disparate systems to communicate, its messaging was linear, limited in flexibility, and often customized differently across institutions, leading to compatibility issues. Patient data was stored in isolated Electronic Health Records (EHR) systems and document repositories, each with its own schema, identifiers, and formats. This created significant operational overhead for healthcare staff, who frequently had to manually reconcile patient records across systems. Duplicate charts, incomplete patient histories, and inconsistencies in demographic and clinical data were common, undermining the promise of digital healthcare. Moreover, these static interfaces lacked the ability to support modern use cases like real-time decision support, multi-institutional data sharing, or advanced analytics. The growing complexity and volume of clinical data, combined with the expansion of health networks, made these legacy approaches unsustainable. By the mid-2010s, the rapid adoption of cloud computing offered healthcare organizations an entirely new architectural model. Instead of relying on tightly coupled, on-premises systems, health data could now be stored, accessed, and processed in secure, scalable cloud environments. This shift dramatically reduced infrastructure constraints and enabled interoperability at a speed and scale previously impossible. A key turning point came with the emergence of Fast Healthcare Interoperability Resources (FHIR), developed by HL7 International. Unlike HL7 v2, FHIR was designed with modern web technologies and RESTful APIs, making it far easier for systems to exchange structured health data in standardized formats. FHIR’s resource-based model allowed granular, flexible access to clinical information, ranging from demographics and laboratory results to imaging studies and care plans. This eliminated many of the inefficiencies caused by rigid, batch-oriented data exchange models. Recognizing FHIR’s potential, major cloud service providers introduced managed FHIR services that handled security, compliance, and scalability out of the box. Solutions such as Google Cloud Healthcare API, Amazon HealthLake, and Azure API for FHIR allowed organizations to integrate EHR data, IoT streams, and imaging data into unified cloud-native architectures. These platforms also supported emerging interoperability initiatives such as the FHIR Bulk Data Access (Flat FHIR) specification, enabling population-level data exchange and analytics at scale. These services also supported advanced security controls such as OAuth 2.0 authentication and encryption in transit and at rest, ensuring compliance with regulatory frameworks like HIPAA. One of the most transformative outcomes of these architectures was the elimination of latency and rigidity inherent in point-to-point interfaces. Instead of waiting for batch updates or manually transferring records, data could flow continuously between systems in real time. This enabled health systems to build automated orchestration pipelines that connected labs, pharmacies, imaging centers, primary care providers, and insurers seamlessly. AI and machine learning tools could then be embedded into these pipelines to perform real-time risk scoring, anomaly detection, clinical decision support, and predictive modeling. By modernizing the data exchange foundation and embracing FHIR-enabled cloud platforms, healthcare organizations unlocked a new level of agility and intelligence. The shift not only streamlined operational workflows but also laid the groundwork for patient-centered care models, interoperability-driven research, and advanced public health analytics. In many ways, this transition marked the beginning of a new era in healthcare IT, one defined by continuous data flow, intelligent orchestration, and scalable innovation. Vishnubhatla S Euro. J. Adv. Engg. Tech., 2022, 9(6):103-109 105 CLOUD INTEROPERABILITY ARCHITECTURE Cloud interoperability has become the structural foundation for modern healthcare information exchange, enabling seamless integration across previously disconnected systems. Traditional health IT infrastructures, with their rigid point-to-point integrations, struggled to scale and adapt as data volumes and use cases grew more complex. Cloud platforms address this limitation by introducing standardized, modular, and secure ways to manage and exchange healthcare data. Through managed interoperability services, healthcare organizations can move away from monolithic systems and instead build dynamic ecosystems where EHR systems, medical imaging platforms, laboratory systems, payer networks, and third-party applications communicate effortlessly in real time. Figure 1: Cloud Health Data Interoperability Architecture As illustrated in Figure 1, the reference architecture positions a secure API gateway as the central entry point for all inbound and outbound data exchanges. Requests are authenticated and authorized using modern identity and access management standards such as OAuth 2.0 and OpenID Connect, ensuring that only trusted applications and users can interact with sensitive health information. Once access is granted, the architecture leverages Fast Healthcare Interoperability Resources (FHIR) APIs and DICOMweb services to standardize the way data is represented and exchanged. This eliminates the inconsistencies common in older HL7 v2 systems and allows applications to interoperate seamlessly regardless of their origin. At the heart of this design is a cloud-native data lake or FHIR repository that stores structured and unstructured data in a secure, scalable environment. Clinical notes, lab results, imaging studies, genomics data, and remote monitoring streams can all coexist within this architecture, linked by patient identifiers and governed by strict access controls. Real-time ingestion pipelines allow data from various sources—such as hospital EHRs, diagnostic devices, or external provider systems—to flow into the repository without delays. Automated ETL and data transformation services clean, normalize, and map data to FHIR resources, making it instantly usable for downstream analytics and clinical applications. Above this core layer, an orchestration framework coordinates workflows and ensures intelligent data movement between services. For example, a lab result can trigger a clinical decision support alert, update the patient’s EHR record, and notify the attending physician through an integrated application, all in real time. AI and machine learning models can be embedded into this layer to perform tasks such as predictive risk scoring, population health analysis, and triage automation. Because the architecture is event-driven, it can scale dynamically and support complex care pathways that span multiple organizations and care settings. The benefits of this model are profound. Cloud interoperability enables coordinated care models where patient data follows the individual across the entire continuum of care, improving outcomes and operational efficiency. It further supports advanced use cases such as personalized medicine, remote monitoring, and value-based care programs. Critically, by standardizing access through FHIR and DICOMweb APIs and enforcing strong security via OAuth 2.0 and OpenID Connect, the architecture achieves both interoperability and regulatory compliance. DATA ORCHESTRATION AND GOVERNANCE Once interoperability is established, the next critical layer in modern healthcare information systems is data and workflow orchestration, which ensures that information is not merely shared but meaningfully processed, routed, Vishnubhatla S Euro. J. Adv. Engg. Tech., 2022, 9(6):103-109 106 and utilized across systems and stakeholders. Interoperable data on its own provides a foundation, but without structured orchestration, it cannot fully support real-time clinical decision-making, advanced analytics, or automated care pathways. As data flows in from EHR systems, medical imaging platforms, IoT health devices, payer systems, and external provider networks, cloud-native orchestration frameworks provide the operational intelligence required to connect these moving parts into a cohesive, scalable system. Figure 2: Digital Health Data Strategy / Data Mesh Workflow Figure 2 illustrates how modern orchestration is structured in healthcare cloud architectures. In this model, data from multiple domains such as clinical, operational, research, and revenue cycle systems, is ingested in real time and routed through a data mesh architecture. Unlike traditional centralized data lakes, a data mesh allows domainspecific teams to own and manage their data pipelines while still adhering to common interoperability and governance standards. This decentralization is particularly powerful in healthcare, where data originates from highly specialized domains (such as imaging, lab results, genomics, or pharmacy records) and must be shared securely with other stakeholders. Cloud-native orchestration frameworks such as Apache Airflow, Kubernetes, AWS Step Functions, and Kubeflow enable healthcare organizations to design pipelines that span the entire data lifecycle—ingestion, transformation, enrichment, validation, analytics, and archival. For example, patient-generated health data from a wearable device can be ingested in real time, validated against interoperability standards like FHIR, enriched with clinical context from EHRs, and then processed by AI models that predict health deterioration or flag abnormal patterns. These results can then be automatically routed to the appropriate clinical system or care team without manual intervention. The orchestration layer also acts as the bridge between data operations and clinical or administrative outcomes. By embedding AI directly into workflows, healthcare organizations can automate complex tasks like triage routing, disease risk scoring, and population health surveillance. AI-enabled pipelines can detect anomalies in medical imaging, identify potential adverse events in near real time, or trigger personalized care pathways based on patient risk profiles. This level of automation not only improves operational efficiency but also enhances clinical precision and patient safety. Equally important to orchestration is governance and compliance. Healthcare operates in one of the most heavily regulated data environments in the world. Frameworks like TEFCA (Trusted Exchange Framework and Common Agreement) and Centers for Medicare & Medicaid Services (CMS) interoperability mandates require organizations to ensure that data flows are transparent, secure, and auditable. Cloud orchestration systems integrate governance controls that enforce access permissions, maintain detailed audit trails, and support automated compliance monitoring to meet regulatory requirements like HIPAA in the US and GDPR in the EU. This ensures that every automated action is not only technically sound but also legally defensible. By leveraging this orchestration-driven architecture, healthcare systems can move from fragmented, manual data handling toward real-time, intelligent workflows that scale across complex ecosystems. This approach allows data to flow fluidly between domains while preserving data integrity, security, and governance. It also enables adaptive systems capable of evolving as new data sources, standards, and clinical use cases emerge. Vishnubhatla S Euro. J. Adv. Engg. Tech., 2022, 9(6):103-109 107 SEMANTIC INTEROPERABILITY AND AI ENABLEMENT Achieving true interoperability in healthcare extends far beyond simply exchanging data in a common format. While syntactic alignment through standardized formats such as Fast Healthcare Interoperability Resources (FHIR) or HL7 ensures that systems can “talk” to each other, the more complex challenge lies in ensuring that the meaning of the data remains consistent and actionable across different platforms. This is where semantic interoperability plays a transformative role. By embedding AI-enhanced semantic layers into healthcare data infrastructures, organizations can ensure that concepts like lab results, diagnoses, medications, and imaging findings are understood in the same way regardless of the originating system. Figure 3: FHIR + openEHR Cloud Architecture for Interoperability Figure 3 provides a clear visualization of how this semantic layer operates within a modern cloud ecosystem. In this architecture, health data flows through a translation and normalization layer built on a combination of FHIR, openEHR, and Integrating the Healthcare Enterprise (IHE) profiles. The FHIR façade provides a standardized interface for external systems and applications, while the openEHR persistence layer ensures that the data model is semantically rich and clinically meaningful. This hybrid approach allows complex clinical information, such as problem lists, medications, diagnostic images, and lab values, to be mapped to well-defined concepts and terminologies. The translation services provided by cloud platforms further enhance this architecture. These services can ingest data from multiple sources—EHR systems, imaging repositories, laboratory information systems, and even patientgenerated health data—and automatically convert them into interoperable and semantically aligned formats. For example, a lab result from one vendor might use proprietary coding, but through semantic mapping to standardized terminologies such as LOINC or SNOMED CT, it becomes machine-readable and interoperable with other systems. This makes it possible to build truly connected healthcare environments where analytics, decision support, and research applications can operate on shared meaning, not just shared structure. When combined with AI and orchestration, the benefits of semantic interoperability multiply. AI models can process structured and semantically harmonized data to detect early signs of disease progression, predict hospital readmissions, or recommend personalized treatment plans. These insights can then be automatically routed through orchestrated workflows to clinicians, case managers, or population health dashboards, ensuring that the right intervention happens at the right time. This integration enables real-time clinical decision support, enhances care coordination, and drives better patient outcomes. Furthermore, semantic interoperability plays a critical role in maintaining regulatory compliance and data integrity. With standardized data semantics, it becomes easier to audit information flows, document provenance, and ensure that clinical decisions are based on accurate and traceable information. It also supports cross-border and multiinstitutional collaboration, a key requirement for modern research networks, precision medicine initiatives, and public health programs. This architectural model represents a shift from isolated data silos to intelligent, interoperable ecosystems where meaning is preserved throughout the data lifecycle. By leveraging the combined strengths of FHIR, openEHR, and IHE profiles, healthcare organizations can build infrastructures that are not only technically interoperable but also semantically aware—paving the way for scalable AI adoption and improved patient-centered care. Ultimately, semantic interoperability ensures that every piece of health data is not only accessible but also actionable, driving safer, more precise, and personalized care. Vishnubhatla S Euro. J. Adv. Engg. Tech., 2022, 9(6):103-109 108 GOVERNANCE, PRIVACY, AND COMPLIANCE Healthcare data is considered one of the most sensitive categories of information because it carries deeply personal details about individuals’ physical and mental health, medical histories, treatments, and genetic backgrounds. A breach or misuse of such data can have far-reaching consequences, not only for patients but also for the trustworthiness of healthcare institutions. As a result, healthcare data is subject to some of the most stringent privacy and security regulations in the world. Laws such as HIPAA in the United States, GDPR in the European Union, and mandates from Centers for Medicare & Medicaid Services (CMS) set strict expectations for how data must be collected, stored, transmitted, accessed, and audited. These frameworks demand full traceability of every transaction, granular access control, and the ability to demonstrate compliance during audits. In the modern cloud era, healthcare organizations must architect their systems with privacy and security built in from the ground up, rather than bolted on as an afterthought. This means implementing defense-in-depth strategies that include encryption in transit and at rest, strong identity and access management (IAM), role-based permissions, and continuous monitoring for unauthorized activity. Advanced privacy-preserving techniques, such as tokenization, pseudonymization, and automated de-identification, allow organizations to protect patient identity while still enabling data sharing for legitimate clinical, operational, and research purposes. This is particularly critical as AI and cloud orchestration frameworks enable larger, more complex ecosystems where data may be shared across institutions, states, or even international borders. Regulatory frameworks such as Trusted Exchange Framework and Common Agreement (TEFCA) and United States Core Data for Interoperability (USCDI v1) help establish common technical and policy standards for how healthcare data is exchanged securely. TEFCA focuses on creating a nationwide health information exchange framework that ensures trust, consistency, and security between different healthcare networks. USCDI v1 defines the core data elements required for standardized data exchange, ensuring that organizations have a clear baseline for interoperability while maintaining compliance with privacy requirements. Together, these frameworks create a shared language for both security and interoperability, reducing fragmentation and improving accountability across the healthcare ecosystem. A key innovation in this space is automated compliance monitoring, which allows organizations to track and enforce security policies in real time. AI and cloud platforms can continuously scan for violations, misconfigurations, or suspicious access patterns and trigger alerts or automated remediation actions before problems escalate. This proactive approach strengthens security posture while reducing the operational burden on compliance teams. In parallel, the use of explainable AI models ensures that automated decisions made within clinical workflows can be fully audited and justified. This is critical in regulated environments, where healthcare organizations must demonstrate not only that a decision was made securely but also how and why it was made. By maintaining transparency and traceability, explainable AI helps align intelligent systems with legal and ethical obligations, building trust among regulators, providers, and patients. Together, these privacy-preserving architectures, governance frameworks, and AI-driven compliance tools create a resilient and secure foundation for healthcare data management. They enable organizations to adopt advanced interoperability and analytics solutions without compromising patient privacy, regulatory compliance, or public trust. This alignment between technology, law, and ethics is what allows healthcare innovation to scale responsibly and sustainably. CONCLUSION By mid-2022, the healthcare industry had reached a pivotal inflection point in its digital transformation journey. Decades of fragmented systems—isolated EHR environments, manual data entry, and siloed reporting frameworks—gave way to a more integrated and intelligent ecosystem. The convergence of artificial intelligence (AI), interoperability standards like Fast Healthcare Interoperability Resources (FHIR) and DICOMweb, and advanced cloud orchestration frameworks marked a fundamental shift from static data systems to dynamic, learning healthcare environments. This transformation was not limited to technology alone—it fundamentally changed how data was exchanged, interpreted, and acted upon in real time, enabling more responsive and patient-centered care delivery. In earlier years, healthcare organizations struggled with outdated, fragmented infrastructures where clinical data lived in incompatible formats across multiple platforms. Integrating even basic workflows often required extensive manual intervention or bespoke interfaces that were slow, error-prone, and expensive to maintain. By contrast, the new cloud-native architectures provided scalable, secure, and standards-based frameworks capable of handling diverse health data streams from electronic health records and imaging data to remote patient monitoring and genomics. Managed interoperability services offered through major cloud providers allowed data to flow securely and efficiently, creating the foundation for real-time clinical decision-making and cross-institutional collaboration. Figures 1–3 depict this architectural progression clearly. Figure 1 presents the cloud interoperability layer, which acts as the backbone for secure data exchange using standardized APIs, identity frameworks, and FHIR repositories. Figure 2 highlights the data orchestration and mesh workflows that enable healthcare organizations to automate Vishnubhatla S Euro. J. Adv. Engg. Tech., 2022, 9(6):103-109 109 complex, multi-source data flows with AI embedded directly into operational pipelines. Figure 3 illustrates the semantic interoperability layer, where FHIR, openEHR, and Integrating the Healthcare Enterprise (IHE) profiles align to ensure data carries consistent meaning, making advanced AI analytics and personalized care possible. Together, these layers enable healthcare ecosystems to move from fragmented processes to unified, intelligent operations. This transformation has also redefined how healthcare organizations approach strategic goals such as population health, precision medicine, and value-based care. With real-time data availability and semantic alignment, AI models can provide actionable insights to clinicians, researchers, and administrators. Care teams can intervene earlier with predictive alerts, tailor treatment plans based on individual patient profiles, and monitor outcomes at both the individual and population level. Data-driven insights that once took weeks or months to aggregate and analyze can now be delivered in seconds through orchestrated workflows and AI-powered decision support systems. Equally important is the scalability and security inherent in these cloud-native architectures. As regulatory frameworks like Trusted Exchange Framework and Common Agreement (TEFCA) and United States Core Data for Interoperability (USCDI v1) continue to mature, organizations that have invested in interoperable and AI-ready infrastructures are better positioned to adapt quickly. They can integrate new standards with minimal disruption, extend their capabilities to new data types or care delivery models, and maintain strong compliance postures in the face of evolving security expectations. This convergence of AI, interoperability, and cloud orchestration does more than modernize IT infrastructure—it fundamentally enables precision medicine and operational excellence. By making healthcare data fluid, intelligent, and secure, organizations can deliver more personalized care, reduce administrative burden, improve clinical outcomes, and drive innovation at scale. Those that embrace this ecosystem early will be at the forefront of nextgeneration healthcare, setting the standard for a future where data truly powers patient care. REFERENCES [1]. U.S. Department of Health and Human Services. HIPAA Privacy Rule. 2000. Available at: https://www.hhs.gov/hipaa [2]. U.S. Department of Health and Human Services. HIPAA Security Rule. 2003. Available at: https://www.hhs.gov/hipaa [3]. National Institute of Standards and Technology. NIST Special Publication 800-66: An Introductory Resource Guide for Implementing the HIPAA Security Rule. 2013. Available at: https://csrc.nist.gov/publications/detail/sp/800-66/rev-1/final [4]. HL7 International. FHIR Overview. 2011–2019. Available at: https://www.hl7.org/fhir/overview.html [5]. HL7 International. SMART on FHIR. 2016. Available at: https://smarthealthit.org/ [6]. National Electrical Manufacturers Association. DICOMweb Standard. 2015. Available at: https://www.dicomstandard.org/ [7]. Internet Engineering Task Force. The OAuth 2.0 Authorization Framework (RFC 6749). 2012. DOI: 10.17487/RFC6749 [8]. OpenID Foundation. OpenID Connect Core 1.0. 2014. Available at: https://openid.net/specs/openidconnect-core-1_0.html [9]. Amazon Web Services. AWS Healthcare Industry Lens Documentation. 2019–2022. Available at: https://docs.aws.amazon.com/ [10]. Amazon Web Services. AWS Prescriptive Guidance: Modern Healthcare Data Strategy. 2022. Available at: https://docs.aws.amazon.com/prescriptive-guidance/ [11]. L&T Technology Services. Healthcare Digital Cloud Architecture. 2021. Available at: https://www.ltts.com/blog/healthcare-digital-cloud-architecture [12]. Topol, E. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 25, 44–56 (2019). DOI: 10.1038/s41591-018-0300-7 [13]. Esteva, A. et al. A guide to deep learning in healthcare. Nature Medicine, 25, 24–29 (2019). DOI: 10.1038/s41591-018-0316-z [14]. Rajkomar, A. et al. Scalable and accurate deep learning with electronic health records. npj Digital Medicine, 1(18), 2018. DOI: 10.1038/s41746-018-0029-1 [15]. U.S. Department of Health and Human Services. Trusted Exchange Framework and Common Agreement (TEFCA). 2022. Available at: https://www.healthit.gov/topic/interoperability/trusted-exchangeframework-and-common-agreement [16]. Office of the National Coordinator for Health Information Technology. United States Core Data for Interoperability (USCDI) v1. 2020. Available at: https://www.healthit.gov/isa/united-states-core-datainteroperability-uscdi