MHRA study to use AI to predict side effects from drug interactions

A study by the Medicines and Healthcare products Regulatory Agency (MHRA) will use AI and NHS data to predict side effects from drug combinations before they reach patients.

In England, around one in seven people (8.4 million) are regularly prescribed five or more medicines, according to figures from the Department of Health and Social Care.

While most combinations are safe, some can interact in ways that cause harmful side effects meaning repeated GP visits, changes to prescriptions, or hospital stays before treatments are adjusted.

Scientists from the MHRA, working with PhaSER Biomedical and the University of St Andrews, will use AI to help spot these interactions over the next 12 months, from October 2025 to October 2026.

Julian Beach, interim executive director healthcare quality and access at the MHRA, who is supervising the study, said: “The launch of this project will demonstrate how AI and advanced modelling can be built into drug development to design smarter, more efficient clinical trials.

“By understanding how medicines work together, we can generate stronger, more realistic evidence to support new treatments and ultimately reduce avoidable harm for patients.

“We encourage researchers and industry to share pilot data, methods or ideas, and get in touch with us early – so we can work together to develop these approaches and shape the next generation of clinical trials.”

The research is backed with £859,650 funding from the UK government’s Regulatory Innovation Office’s AI Capability Fund, which supports regulators to test faster ways of bringing safe innovation.

It will look for patterns in anonymised NHS data showing how different medicines behave when used together, focusing on cardiovascular medicines. These signals will then be tested in the lab using human-based models that mimic how drugs are processed in the body.

Chris Wardhaugh, chief executive of PhaSER Biomedical, said: “This collaboration demonstrates a shared commitment between regulators and innovators to redefine how medicines are developed.

“Our model provides a uniquely human-relevant lens on drug metabolism and safety, while our work with the MHRA ensures that these insights can translate directly into regulatory practice.”

The research is among three MHRA projects backed by government funding to modernise how medicines and medical technologies are tested and approved, with the aim of ensuring faster access for patients while maintaining safety standards.

MHRA will also pilot the use of AI-assisted tools to support experts in scientific advice, clinical trial assessments and licensing decisions with the aim of improving efficiency and consistency while keeping final decisions in human hands.

Funded by £1m via the Regulators’ Pioneer Fund, the AI for Regulatory Insight, Safety, and Efficiency (ARISE) programme will demonstrate how regulators can responsibly use AI to strengthen medicine safety, streamline the development of new treatments and enable faster access to new therapies.

Another MHRA project, which has received £259,250 in funding, will pilot the use of synthetic (artificial) patient data to support clinical trials in cancer, inflammatory bowel disease and rare paediatric seizure conditions.

The projects support the government’s ambition to make the UK the most AI-enabled health system in the world, as set out in the 10 year health plan.