JMIR Publications

ABSTRACT

Decentralized clinical trials (DCTs) have advanced rapidly in concept and continue to grow in demand, but they remain difficult to scale in practice. The primary barrier is not simply a technology problem, but a systems problem: the absence of an integrated operating model that aligns protocol design, workforce and service delivery models, investigator oversight, regulatory and quality requirements, and participant experience all with decentralized delivery. We argue that sustainable DCT scale depends on four interdependent capabilities that must be designed into protocols and operating models from the outset: (1) orchestrated operational infrastructure designed for mobility and remote execution; (2) regulatory and quality frameworks adapted to distributed oversight; (3) community-integrated models that prioritize equitable access and participant-centered flexibility; and (4) technology and data systems that coordinate these components in real time. Drawing on real-world implementation across large-scale decentralized and hybrid clinical trials, we distill practical lessons and design requirements that distinguish reproducible models from one-off successes. We further propose that artificial intelligence is emerging as a critical enabler of this model, not as a standalone tool but as a coordinating layer that can help automate patient to trial matching, optimize operational workflows, and support continuous oversight across distributed environments. Embedding AI within the DCT architecture has the potential to transform decentralization into a scalable, learning system by augmenting human efforts and preserving the essential role of clinical professionals. By reframing DCTs as an integrated, AI-enabled operating model, here we outline a path toward trials that are more scalable, resilient, and inclusive, while maintaining scientific rigor and regulatory confidence.