EMA Reflection Paper on AI in the Medicinal Product Lifecycle
- Date
- September 30, 2024
- Category
EU Regulations
- Description
On September 30, 2024, the EMA published a ‘Reflection paper on the use of Artificial Intelligence (AI) in the medicinal product lifecycle’. This paper is adopted by both the CHMP and the CVMP. This paper starts by stating that “The utilization of artificial intelligence (AI) is an important part of the digital transformation. Such systems are often developed through the process of machine learning (ML) where models are trained from data, with or without human input. However, new risks are introduced that need to be mitigated to ensure the safety of patients and integrity of clinical study results.”
The reflection paper provides considerations on the use of AI/ML in the lifecycle of medicinal products, including medicinal products development, authorization, and post-authorization.
Section 2.3 looks at AI in the lifecycle of medicinal products and has the following sub-sections:
- Drug Discovery
- Non-clinical development
- Clinical Trials
- Precision medicine
- Product information
- Post-authorisation phase
Section 2.4 covers ‘Regulatory interactions’ and section 2.5 looks at ‘Technical aspects’ with the following sub-headings:
- Data acquisition and augmentation
- Training, validation, and test datasets
- Model development
- Performance assessment
- Interpretability and explainability
- Model deployment
This is followed by sections on:
- Governance
- Integrity aspects and data protection
- Ethical aspects and trustworthy AI
The paper ends by concluding that the quickly developing field of AI/ML shows great promise for enhancing all phases of the medicinal product lifecycle. As the overarching approach has to be inherently data-driven, active measures must be taken to avoid the integration of bias into AI/ML applications and promote AI trustworthiness. A human-centric approach should guide all development and deployment of AI and ML.
The reflection paper also has a glossary and a comprehensive bibliography of guidelines and other documents may provide useful recommendations for implementing AI/ML applications in the product lifecycle of human medicines.
This reflection paper can be found at https://www.ema.europa.eu/en/use-artificial-intelligence-ai-medicinal-product-lifecycle