linical research in the United States is at a crossroads. While scientific advances accelerate the discovery of new treatments and bring new hope to patients, millions of eligible patients remain excluded from clinical trials for those treatments, not because of clinical ineligibility but because they receive care in rural and community settings, without sufficient research infrastructure.

This disconnect undermines equitable access, limits trial data representativeness, and overwhelms a research enterprise concentrated in urban academic centers. Over the past three years, regulatory evolution and technological innovation have shown that it is possible to reimagine where trials occur. But turning this possibility into action requires a systematic framework and diverse operational partners to bring this framework to life.

Two organizations are working to turn this possibility into reality. One organization operates at the frontier of cancer immunotherapy, advancing potentially curative therapeutics from bench to bedside, and recognizes that it is imperative to increase patient access to cancer breakthroughs. The other solves for this challenge by combining AI-enabled solutions with human expertise, a large, distributed network of health systems, and trial sponsors who prioritize speed and efficiency, to bring clinical research to more Americans without compromising data quality or innovation.

The Current Trial Access Challenge

Despite decades of efforts to make clinical trials more inclusive, geography remains a major determinant of whether a patient can take part in clinical research. Millions of eligible US patients cannot participate because of where they receive care. As an example, between 2017 and 2022, 86% of nonmetropolitan counties had zero oncology clinical trials.

Rural communities and community health centers face systemic barriers to conducting trials, including research workforce shortages, overly complex trial protocols, and burdensome regulatory documentation. The result: a US research ecosystem that applies unevenly across Americans.

This not only contributes to geographic health disparities, but it also limits researchers in understanding the full therapeutic value of their drug candidates. You cannot have high-quality, generalizable evidence if that evidence reflects only 10% of the population. With increasing demand for trials and growing regulatory pressure to conduct trials in representative patient populations, enrolling patients in rural communities may be the difference between a successful US drug launch and a costly regulatory reboot. Increasing access to trials outside traditional academic centers is a moral, scientific, and business imperative.

Vision for Expanded Trial Access

Our organizations approach this clinical research divide with the guiding principle that research should meet patients where they are. We have built a collaborative network of partners to bring cutting-edge trials closer to more patients, including patients outside urban academic hubs, while providing AI-based solutions to ease operational and administrative burdens.

To implement our shared vision, we have built a scalable, evidence-based framework that aligns therapeutic innovation with operational realities. The framework is built on three pillars:

1. Large, Distributed Research Networks
2. AI-Native, EHR-Integrated Infrastructure
3. Community-Centric Research Models

Together, these pillars address the long-standing barriers to expanding trial access to more Americans.

1) Large, distributed research networks
Trial sponsors have historically preferred to work with specific academic sites because of deep, productive relationships they have built with individual principal investigators over many years. Overreliance on these relationships has led to investigator burnout and attrition, causing both inefficiency in trial operations and severe inequities in access.

Rural and community clinics cannot break into this tight-knit research network without support. Our organizations help to make these connections and demonstrate to sponsors that community health centers have the tools and support required to successfully conduct trials. For example, Altru Health System in North Dakota and Minnesota partnered to achieve a 175% increase in active patients enrolled in trials, and Florida Cancer Specialists saw their successful patient screening rate multiply by 10 after launching their partnership. Collaboration with rural and local community clinics provides them with enterprise-grade tools to efficiently manage all aspects of conducting clinical research; the large, distributed research network offers centralized and standard processes (i.e., trial sourcing, feasibility evaluation, recruitment), which, combined with our platform, levels the playing field for smaller institutions.

2) AI-native, EHR-integrated infrastructure
This network’s AI-enabled platform reduces administrative work, freeing up research and clinical staff at health provider organizations to focus on their clinical activities, increasing the overall capacity of our US medical system to conduct trials. Key, concrete capabilities resulting from AI-enabled infrastructure include:

• Continuous surveillance for patient eligibility. An always-on, real-time engine powered by AI agents monitors electronic health records (EHRs) and other clinical source systems to identify, track, and navigate patients who are likely eligible (or likely to become eligible) for trials, surfacing the best candidates in real time. This shifts recruitment from episodic chart hunts and new site opens that do not necessarily enroll patients to continuous, predictable identification of potentially eligible patients.
• LLM matching and prescreening. Specially trained large language models (LLMs) read and interpret both structured and unstructured medical record data to assess patient eligibility for each trial. The ability of LLMs to interpret complex eligibility criteria and clinical factors has improved dramatically over the past two years. This evolution means that LLM-based systems can be true copilots in surfacing likely patients for research and clinical teams, who then review and confirm trial eligibility. Our specially trained models have eliminated a substantial amount of unnecessary review, allowing research teams to focus their time on the most relevant patients. For example, these solutions helped Ochsner Health clinical staff pre-screen 41% more patients for a trial than the site did on its own. This led to 3.6x as many patients being followed for eligibility. And in a 4-month period, this site converted 100% of the matched patients to enrolled.
• Automated study data collection and monitoring. Providers and sponsors face significant operational, financial, and clinical challenges in today’s traditional study conduct model. An LLM-first approach automates data collection from the point of care, allowing research staff to more quickly review and validate data before submitting it into a sponsor’s database. Researchers recently used this technology for a pilot study in four community oncology settings to assess the quality of data captured. Results showed substantially reduced manual data entry time while transferring a high volume of high-quality data, reducing time for data cleaning and clarification. Importantly, trial sponsors can expand late-stage clinical research into community settings and, by broadening patient populations, produce more generalizable evidence for their therapies.

3) Community-centric research models
Provider-focused design, recruitment, and approaches to study conduct help make research a long-term, locally sustainable part of care.

• Provider-centric trial operations. Trial sponsors must design trials with provider sites in mind, to optimize their protocols to better suit the workflows and capabilities of nonacademic trial sites. Making protocols as pragmatic as possible reduces the burden of the study on both providers and their patients, often allowing the trial to be incorporated into routine care. This also mitigates clinician resistance and research staff burnout. This approach to pragmatic design has supported efficient enrollment and execution of late-stage clinical research in community settings.
• Longitudinal site relationships. Moving from a transactional, trial-by-trial model to ongoing engagement with trial sites helps establish research as a care option for more patients and increases trust and repeat site participation.
• Public-private alignment. All stakeholders must work in concert with federal and state programs, such as the Rural Health Transformation Program, and form local partnerships, so trials bolster rural health priorities and workforce development and create both economic and clinical value for communities.

Scaling for Impact

Taken together, these pillars can transform clinical research deserts into functioning, scalable systems that facilitate continuous, AI-driven patient discovery; regulatory-grade data; and community knowledge that makes research durable. They measure success the same way sponsors and health systems do: rural enrollment growth, time to first patient, time to database lock, protocol adherence, and site retention. These metrics allow sponsors, regulators, and partners to evaluate not just participation but performance.

A Defining Moment for the Clinical Research Enterprise

The rural-urban research divide is not inevitable. It reflects outdated infrastructure and fragmented operational models. Both can be addressed through thoughtful trial and network design, regulatory alignment, and technological innovation. As more of the US clinical research industry joins these two organizations in bringing this framework to life, collaborations should prioritize formalizing urban-rural hospital exchanges that nurture a rural health workforce; advocating for data interoperability enforcement; and designing trials to be embedded into routine patient visits to minimize burdens on patients and clinical researchers.

The above framework provides a path forward where clinical research is inclusive by design, scalable through technology, and grounded in quality and trust. This is an opportunity for regulators, sponsors, healthcare providers, and patients to reduce health disparities, maximize the impact of therapeutic innovation, and reboot clinical research capacity in the US.