Data interoperability for a systems approach to developmental conditions

Abstract

The rising prevalence of developmental conditions such as autism, ADHD, and learning disorders underscores the urgent need for an integrated approach to account for the dynamic interaction between genetic, environmental, and societal factors. At present, the information on these factors is scattered and fragmented across a wide range of caregivers using different systems, structures and semantics. As a result, healthcare providers often face excessive administrative burdens to gather relevant information from disparate sources, and in many cases, must repeat diagnostic tests due to a lack of accessible prior records. This fragmentation also has a significant impact on patients and families, who may experience delays in care, repeated procedures, inconsistent treatment, and ultimately poorer health outcomes, which highlights the urgent need for an interoperable foundation. In this perspective, we emphasize the transformative potential of data interoperability as a prerequisite for adopting a complex systems approach to developmental conditions. We discuss key concepts, implementation barriers, and strategies for achieving interoperability, including standards like FHIR and SNOMED CT, while addressing security and regulatory concerns. Our research proposes crucial steps to realize interoperability that require collaborative efforts across healthcare providers, technology developers, policymakers, and researchers. Through practical case examples, we demonstrate how interoperability enhances cross-disciplinary collaboration, reduces duplicative data entry, and provides a more comprehensive view of patient health trajectories, particularly valuable for complex conditions requiring multiple specialists and long-term care. Furthermore, our research shows that interoperable systems lay the foundation for advanced analytics and artificial intelligence initiatives, enabling more accurate diagnoses, personalized treatment plans, and improved prediction of clinical outcomes for developmental conditions.

Keywords: Artificial, intelligence; Complex systems; Data governance; Data interoperability; Developmental conditions; Health information systems; Systems approach.