EP 3

FDA Guidance: AI in Drug and Biological Product Regulatory Decisions

The FDA's new draft guidance on the use of artificial intelligence in drug development has significant implications for the industry. This episode breaks down the guidance and explores its potential impact on regulatory decisions. The FDA's risk-based credibility assessment framework is a key component of the guidance, and understanding it can help companies navigate the regulatory landscape.

FDAAIdrug developmentregulatory decisionsrisk-based credibility assessment

play_arrowListen to episode

Key Concepts

Artificial Intelligence in Drug Development

AI can be used to predict pharmacokinetics and pharmacodynamics
AI can help integrate different data sources, such as natural history studies and clinical trial data
AI can be used to analyze real-world data and track outcomes

Risk-Based Credibility Assessment Framework

The framework consists of seven steps
The level of scrutiny for AI models depends on the model's influence and decision consequence
High model risk requires more evidence to establish credibility

Data Quality and Transparency

Data quality is critical for AI models
Transparency is essential for understanding how AI models work
Data sources and cleaning processes should be documented

Early Engagement with the FDA

Early engagement can help companies ensure they are on the right track
The FDA encourages companies to engage with them early in the development process
Early engagement can help companies avoid costly mistakes

Competitive Edge

Understanding the FDA's thinking on AI in drug development can help companies gain a competitive edge
Companies that can demonstrate a clear understanding of the FDA's guidance can build trust with regulators and partners
A competitive edge can be achieved by sharpening science, focusing resources, and navigating the regulatory landscape

Episode Summary

check_circleThe FDA has released a draft guidance on the use of artificial intelligence in drug development
check_circleThe guidance covers the use of AI in various stages of drug development, including predictive modeling in clinical trials and integrating different data sources
check_circleThe FDA's risk-based credibility assessment framework is a key component of the guidance
check_circleThe framework consists of seven steps, including defining the question of interest, assessing the AI model risk, and determining the adequacy of the AI model
check_circleThe level of scrutiny for AI models depends on the model's influence and decision consequence
check_circleHigh model risk requires more evidence to establish credibility
check_circleThe guidance emphasizes the importance of data quality, transparency, and uncertainty in AI models
check_circleEarly engagement with the FDA is encouraged to ensure that companies are on the right track
check_circleUnderstanding the FDA's thinking on AI in drug development can help companies sharpen their science, focus their resources, and gain a competitive edge

Full Transcript

Discussion

Join the discussion — sign in to leave a comment.