“rapid growth in the number of submissions that reference artificial intelligence and machine learning” has prompted the US Food and Drug Administration (FDA) to seek feedback on AI/ML in drug development.
The US Food and Drug Administration (FDA) has released a discussion paper to complement and inform future guidance on artificial intelligence (AI) and machine learning (ML) in drug development.
The paper is intended to initiate communication with stakeholders, including industry and academia, to foster mutual learning and discussion.
The questions in Section B aim to initiate a discussion with stakeholders and solicit feedback on three key areas in the context of AI/ML in drug development.
the organisation has seen “a rapid growth in the number of submissions that reference AI/ML” over the past few years”
These are:
- Human-led governance, accountability and transparency
- Quality, reliability and representativeness of data
- Model development, performance, monitoring and validation.
According to the FDA, the organisation has seen “a rapid growth in the number of submissions that reference AI/ML” over the past few years.
Advanced manufacturing
“Advanced analytics leveraging AI/ML in the pharmaceutical manufacturing industry offers… possibilities [such as]… enhancing process control… and preventing batch losses.”
The FDA’s paper acknowledged that AI/ML in pharmaceutical manufacturing can work alongside “other advanced manufacturing technologies (eg, process analytical technology, continuous manufacturing)”, helping to enable the implementation of Industry 4.0.
To make manufacturing more effective and efficient, AI/ML can facilitate “faster output, less waste, more informed decision-making, and enhanced quality control”. The paper also highlighted that AI/ML can enhance manufacturing supply chain.
Artificial intelligence and machine learning in clinical research
Also noted in the paper was: “One of the most significant applications of AI/ML in drug development is in efforts to streamline and advance clinical research.”
A key benefit of AI/ML identified in the paper was that these technologies can “analyse vast amounts of data”. For example, “digital health technologies (DHTs), such as wireless and smartphone-connected products, wearables, implantables, and ingestibles” are increasingly being used in clinical trials to “analyse the large and diverse data generated from the continuous monitoring of persons using these technologies.”
“AI/ML has the potential to inform the design and efficiency of non-traditional trials such as decentralised clinical trials, and trials incorporating the use of real-world data (RWD).”
On 2 May 2023, the FDA published draft guidance which included recommendations for delivering decentralised clinical trials.
The FDA stated it plans to develop and adopt a flexible, risk-based, innovation-promoting regulatory framework on AI/ML.
Comment on the discussion paper here.
Source link
#FDA #publishes #paper #AIML #drug #development
