Recently FDA releases two discussion papers to spur conversation about artificial intelligence and machine learning in drug development and manufacturing.
Artificial intelligence (AI) and machine learning (ML) are no longer futuristic concepts; they are now part of how we live and work. The U.S. Food and Drug Administration uses the term AI to describe a branch of computer science, statistics, and engineering that uses algorithms or models to perform tasks and exhibit behaviors such as learning, making decisions, and making predictions. ML is a subset of AI that uses data and algorithms, without being explicitly programmed, to imitate how humans learn.
This article provides a high-level overview of the diverse and evolving uses of AI/ML being employed throughout the drug development process. These examples are not comprehensive of all AI/ML uses and include uses where FDA oversight may or may not be applicable.
Although the overall drug development process is an iterative continuum of activities and not strictly linear in nature, for simplicity, this section utilizes different phases of drug development to highlight several uses of AI/ML, ranging from drug discovery and clinical research to postmarked safety surveillance and advanced pharmaceutical manufacturing.
Drug Discovery
Drug Target Identification, Selection, and Prioritization
While early target identification and prioritization is a critical step where AI/ML could help improve the efficiency and effectiveness of drug development, it is important to validate the role of the biological target in the disease of interest through subsequent studies
Compound Screening and Design
In the area of compound screening, potential AI/ML uses include predicting the chemical properties and bioactivity of compounds and predicting efficacy and potential adverse events based on the compound’s specificity and affinity for a target.
Nonclinical Research
Nonclinical research refers to in vitro and in vivo studies and is designed to further advance potential therapeutics towards clinical research in humans. Nonclinical studies, in support of new drug development, can be conducted at all phases of development: prior to clinical studies, in parallel with clinical development, and even in postmarketing environments.
Data from pharmacokinetic, pharmacodynamic, and toxicological studies conducted in animals; exploratory in vitro and in vivo mechanistic studies conducted in animal models; organ-on-chip and multi-organ chip systems; and cell assay platforms may be leveraged using AI/ML (e.g., computational modeling and simulation techniques) for evaluating toxicity, exploring mechanistic models, and developing in vivo predictive models.
Clinical Research
Clinical research typically involves a series of phases of clinical trials in increasing numbers of human subjects to assess the safety and effectiveness of a drug. One of the most significant applications of AI/ML in drug development is in efforts to streamline and advance clinical research. For example, AI/ML is being utilized to analyze vast amounts of data from both interventional studies (also referred to as clinical trials) and non-interventional studies (also referred to as observational studies) to make inferences regarding the safety and effectiveness of a drug.
Postmarketing Safety Surveillance
Pharmacovigilance (PV) refers to the science and activities related to the detection, assessment, understanding, and prevention of adverse events or any other drug-related problems (including medication errors and product quality issues). There are potential opportunities to use AI/ML for automation during individual case safety report (ISCR) processing.
AI/ML has also been applied to determine seriousness of the outcome of ICSRs, which not only supports case evaluation, but also the timeliness of individual case submissions that require expedited reporting.
Advanced Pharmaceutical Manufacturing
A critical aspect of drug development includes the methods, facilities, and controls used in manufacturing, processing, packing, and holding of a drug to help ensure that the drug meets the requirements of safety and effectiveness, has the identity and strength it is represented to possess, and meets quality and purity characteristics. Advanced analytics leveraging AI/ML in the pharmaceutical manufacturing industry offers many possibilities, including, but not limited to:
- enhancing process control,
- increasing equipment reliability and throughput,
- monitoring early warnings or signals that the manufacturing process is not in a state of control,
- detecting recurring problem clusters, and
- preventing batch losses.
The use of AI/ML to support pharmaceutical manufacturing can be deployed together with other advanced manufacturing technologies (e.g., process analytical technology, continuous manufacturing) to achieve the desired benefits.
Use of AI/ML based approaches in pharmaceutical manufacturing can be broadly grouped into the areas outlined below:
- Optimization of Process Design
- Advanced Process Control
- Smart Monitoring and Maintenance
- Trend Monitoring
AI/ML’s growth in data volume and complexity, combined with cutting-edge computing power and methodological advancements, have the potential to transform how stakeholders develop, manufacture, use, and evaluate therapies. Ultimately, AI/ML can help bring safe, effective, and high-quality treatments to patients faster.
