By Lucy Radley, Head of EU Regulatory Development, ProPharma.
A rare disease is defined as a condition which affects less than one in 2000 people. Although individually they are very rare, collectively they are common with one in 17 people (around 3.5 million) in the UK being affected by a rare disease at some point in their lives.
Rare disease drugs can be complicated and expensive to produce, with a limited patient pool their development is often slow and their cost price to the UK’s health service high. This has left many living with rare diseases without available or approved treatments and support for their conditions.
The UK Government launched its rare disease action plan in 2022 which followed on from the 2021 launch of the Life Sciences Vision which was designed to “build on the UK’s world class science and research capabilities – making the UK the best place in the world to trial and test products at scale, underpinned by an ever improving genomic and health data infrastructure.”
The role of AI in rare disease clinical trials might hold the key to helping the UK achieve this vision. AI is revolutionising clinical trials and drug developments just as it is transforming other sectors, but in order for AI to make progress in rare diseases, the UK needs further investment to increase uptake and use. Investing into AI in healthcare is therefore crucial for those living with a rare disease in the UK and the development of life-changing drugs.
The current approach to drug development
Developing drugs for rare diseases presents a cost challenge for pharmaceutical companies. As these diseases affect a small proportion of the population as a whole, it means it can sometimes be difficult to justify the high cost of rare disease drug development. In the UK, Contract research organisations (CROs) form an important part of the drug discovery and development process, with many organisations reliant on CROs and their experience to help bring drugs to market, quicker and more cost effectively. However, this traditional approach often prioritises diseases which have larger patient pools and which are better understood, and smaller, less common diseases are overlooked. This needs to change.
Changing the business model behind drug development is the first step. It’s crucial that other more nimble firms move to break the mould of the larger CROs and the traditional approach. Those firms must accommodate smaller and mid-sized innovators who need more personalised solutions to develop their drugs and change lives for those living with rare diseases globally.
The second is looking to existing technologies to change the current approach. Recent advancements in AI have provided a host of tools that can improve the efficiency and accuracy of drug development, especially for rare diseases, and bring much needed drugs to market more quickly, efficiently and cost effectively.
How AI can transform drug development
One way AI can aid drug development is through the use of machine learning (ML) algorithms. ML has the capabilities to analyse large amounts of data including patient health data and the data collected across the clinical trial. Through this analysis organisations are able to have a better understanding of how a drug will interact with the human body and how effective it may be in treating the disease.
AI can be utilised to support patient identification of rare disease patients by analysing electronic health records, medical images and genetic data for example. This can aid early diagnosis and treatment of rare diseases. AI can also help personalise treatments for patients, by analysing their genetic and other health data to identify the most effective treatments.
AI can analyse vast amounts of data from clinical trials, scientific literature and other sources to simulate the interactions between drugs and their target molecules which can help to identify potential drug candidates, repurpose existing drugs and potentially reduce the need for preclinical and clinical testing.
This technology can also be used to design more effective and efficient clinical trials for rare diseases by identifying the most suitable patents for clinical trials, predicting outcomes and optimising dosages and regimens of drugs.
Synthetic data sets
Synthetic data sets can play a crucial role in clinical trials, especially in the early stages of drug development, when there may be a shortage of real-world data. Synthetic data sets are artificially generated data that can mimic the statistical characteristics of real-world data.
Risk based monitoring
Also known as RBM, risk based monitoring is used to detect risks that could affect the clinical trial and minimise them. Using AI and ML features, RBM uses predictive analytics, such as compliance, data quality and enrollment throughout the clinical trial to help to determine the performance at different stages. This can minimise risks that may slow down or prove costly to clinical trials for rare diseases which are already underfunded and have a low success rate.
AI therefore has the potential to revolutionise the development of drugs for rare diseases. By leveraging machine learning, virtual drug screening, and other AI tools, pharmaceutical companies can accelerate the drug development process, reduce costs, and improve the accuracy of drug design and clinical trials. This will potentially lead to more effective treatments for patients with rare diseases, who often have few options for treatment.
About the author
Lucy is the lead for European Regulatory Development, with a team of over 40 highly skilled nonclinical, clinical, CMC and regulatory consultants who support ProPharma’s clients in navigating the regulatory maze within Europe. Lucy’s role is to ensure that the unique needs of each client are exceeded by building exceptional project teams, who use science to further client’s objectives. Collectively, the team dive deeps into client data to develop tailored strategies to ensure successful negotiation of the rigid and often inflexible regulatory landscape in Europe.