AI in the development of medicines

AI in the development of medicines

Image by Freepik

It’s not breaking news that the use of Artificial Intelligence (AI) is spreading across the globe, and medicines development and registration is no exception.

The European Medicines Agency (EMA) released a draft reflection paper on the use of AI in the development of medicines and wrote in a press release that ‘The use of artificial intelligence is rapidly developing in society and as regulators, we see more and more applications in the field of medicines. AI brings exciting opportunities to generate new insights and improve processes. To embrace them fully, we will need to be prepared for the regulatory challenges presented by this quickly evolving ecosystem’.

The Organisation for Professionals in Regulatory Affairs (TOPRA) described the paper as ‘reflect(ing) on all areas of the medicinal product lifecycle where AI and ML (Machine Learning) may be applicable, from drug discovery through to post-authorisation phase’.

How can AI be used in the medicinal product lifecycle?

Artificial intelligence (AI) is a technology-based system involving various advanced tools and networks that can mimic human intelligence enabling machines to perform functions such as logic, reasoning, planning, and perception. The use of AI has been increasing within the pharmaceutical sector with potential future uses in aiding drug design, assisting in decision-making, determining patient therapies, and managing clinical data.

‘Their application can include, for example, AI/ML modelling approaches to replace, reduce, and refine the use of animal models during the preclinical development’. Additionally, ‘in clinical trials, AI/ML systems may support the selection of patients based on certain disease characteristics or other clinical parameters’.

In the MA stages of a product, AI tools could be used to draft, gather, translate, and review data that can be included in the product information of medicines. Similar tools could also be used to support pharmacovigilance activities such as the management of adverse event reporting and signal detection.

It is important to note that the paper highlights that a ‘human-centric approach’ should be used to guide the development and deployment of AI and ML use in the medicinal product lifecycle. Use should comply with existing legal requirements and take ethics and fundamental rights into consideration. Furthermore, is AI/ML use in medicine development could impact the benefit: risk balance, then the EMA has advised MAH’s to seek scientific advice.

Overall, AI could have positive impacts in medicinal development, although there are still hurdles to overcome, to ensure organisations can use AI pathways in future drug development programs to their full potential. The draft reflection paper produced by EMA is a promising start to the acceptance of the use of AI in all stages of drug development and within the regulatory framework.

Other uses within regulatory?

The Advertising Standards Authority (ASA) released a blog post about the use of AI to monitor the promotion of prescription-only medicines.

The Advertising Standards Authority (ASA) is utilising artificial intelligence (AI) to combat illegal advertisements for prescription-only medicines on social media. The use of machine learning, particularly large language models (LLMs), can enable accurate identification of rule-breaking posts, as part of their broader “Active Ad Monitoring” system.

Advertising prescription-only medicines to consumers is illegal in the UK, but some businesses unknowingly or intentionally violate these rules. The ASA addresses this issue by working with various stakeholders and taking a direct approach on platforms like Instagram. In 2020, they began using social media listening tools, leading to the removal of over 25,000 problematic posts in 2022.

To enhance efficiency, the Data Science team developed tools using LLMs, significantly improving the identification of paid advertisements, which promote prescription-only medicines. This has not only resulted in better protection for consumers but also allows experts to review content 2-3 times faster than before, showcasing the positive impact of their investment in AI and data science on effective ad regulation in the UK.

However, having an online presence without promoting prescription-only medicines is entirely achievable, provided that the APBI code is strictly followed. Promotional content that isn’t part of paid advertising must also still adhere to the code, ensuring compliance by following the correct process, through copy approval.

Want to know more?

For further reading, the draft reflection paper can be found here: Draft Reflection paper on the use of Artificial Intelligence (AI) in the medicinal product lifecycle.

The ASA’s blog post can be accessed here: Using AI to monitor the promotion of prescription-only medicines

Faizah Rasul
Latest posts by Faizah Rasul (see all)