AstraZeneca and Oracle Outline AI Collaboration for Clinical Trial Recruitment and Safety Monitoring

AstraZeneca and Oracle Health and Life Sciences have announced a collaboration that combines the drugmaker's clinical development and regulatory expertise with Oracle's real-world data, cloud infrastructure and artificial intelligence (AI) tools, with early work aimed at trial recruitment, earlier diagnosis and drug-safety monitoring.¹ The companies signed a non-binding term sheet and did not disclose financial terms.¹

For sponsors and clinical operations teams, the announcement is a statement of intent rather than a result: the partners describe the effort as designed to test practical ways of connecting research to clinical workflows.¹

Pascal Soriot, Chief Executive Officer, AstraZeneca said: “This unique collaboration brings leaders in healthcare and AI together at a global scale to accelerate the journey from the discovery of medicine to patient care. Combining AstraZeneca’s world class science with Oracle’s deep data and technology expertise, we can help clinicians identify patients sooner, optimise clinical trials, and generate evidence continuously across the lifecycle of a medicine.”¹

What will the AstraZeneca-Oracle AI collaboration cover?

Oracle will contribute real-world data, cloud infrastructure and AI-enabled clinical capabilities, while AstraZeneca provides scientific, clinical development and regulatory expertise.¹ Initial areas of exploration include clinical trial recruitment, earlier diagnosis, drug-safety monitoring and the use of real-world evidence across a medicine's lifecycle, spanning oncology, cardiovascular, renal and metabolic diseases, respiratory and immunology, and rare disease.¹

Projects will run in several regions, including the U.S., the Middle East and Europe, working with local governments and within applicable regulations so they could be scaled later.¹ The first program will support hypertension care and clinical research in Abu Dhabi with the healthcare company M42, helping clinical teams identify patients with uncontrolled hypertension, implement guideline-directed care and improve trial recruitment.¹

The companies did not report efficacy or safety results, pilot timelines or enrollment targets.

Why is patient recruitment central to AI use in clinical trials?

The release points to late diagnosis, long waits for referral and gaps in translating scientific advances into practice as the problems the collaboration targets.¹ For trial operations, those gaps surface as recruitment difficulty.

Published research illustrates both the interest and the evidence base. National Institutes of Health researchers developed TrialGPT, a large language model framework that retrieves candidate trials, assesses eligibility criterion by criterion and ranks trials for a patient.²

In their evaluation, the retrieval module recalled more than 90% of relevant trials using less than 6% of the initial collection, and a user study showed a 42.6% reduction in screening time.² The evaluation used 183 synthetic patients, however, which limits how directly the results translate to routine site workflows.²

The study does not involve the AstraZeneca-Oracle collaboration.

How will patient data be governed in the collaboration?

The collaboration will use deidentified real-world data under governance, privacy and security arrangements, and AstraZeneca will not receive patient-identifiable information.¹ Each proposed project will be reviewed separately and will proceed only after legal, privacy, regulatory, ethical and institutional safeguards are in place.¹

Seema Verma, executive vice president and general manager, Oracle Health and Life Sciences, said: “Healthcare progress depends on shortening the distance between scientific insight and the decisions clinicians make every day. AstraZeneca brings deep scientific and therapeutic expertise, and Oracle will deliver the secure data, cloud, AI, and clinical workflow capabilities. This collaboration has the potential to help health systems identify eligible patients sooner, broaden access to clinical trials, and generate evidence that supports the next decision, all under the governance of the health systems delivering care.”¹

Regulators are also shaping expectations for AI in drug development. In January 2025, the FDA issued a draft guidance proposing a risk-based framework for assessing the credibility of AI models used to support regulatory decisions on drug safety, effectiveness or quality, based on each model's context of use.³

The draft is nonbinding, and the companies have not said how it would apply to any recruitment or safety-monitoring tools developed under this collaboration.

What are the limitations and open questions?

A non-binding term sheet leaves room for the scope to change, and the Abu Dhabi hypertension program is the only project the companies have described.¹ Several practical questions remain open: which recruitment and safety-monitoring metrics the partners will track, how results will be validated against standard site practice, and how participating health systems and sites will fold AI-generated insights into existing workflows.

Published evaluations such as TrialGPT's relied on synthetic patients, so performance on health-system data remains to be shown.² The stated goal of broadening access to trials will also depend on the number and diversity of health systems that join, which the companies have not specified.¹

Sources

1. AstraZeneca and Oracle launch global AI collaboration to advance clinical trial optimisation and support better patient outcomes. News release. AstraZeneca. October 20, 2026. Accessed October 20, 2026. https://www.astrazeneca.com/media-centre/press-releases/2026/astrazeneca-oracle-launch-global-ai-collaboration-advance-clinical-trial-optimisation-support-better-patient-outcomes.html
2. Jin Q, Wang Z, Floudas CS, et al. Matching patients to clinical trials with large language models. Nat Commun. 2024;15. doi:10.1038/s41467-024-53081-z
3. Considerations for the use of artificial intelligence to support regulatory decision-making for drug and biological products. Draft guidance for industry and other interested parties. US Food and Drug Administration. January 2025. Accessed October 20, 2026. https://www.fda.gov/regulatory-information/search-fda-guidance-documents/considerations-use-artificial-intelligence-support-regulatory-decision-making-drug-and-biological