Sr. Director, Clinical Development Tolmar Inc Monmouth Junction, New Jersey
The use of Artificial Intelligence (AI) and Machine Learning (ML) in New Drug Application (NDA) or Investigational New Drug (IND) submissions to the Food and Drug Administration (FDA) has gained significant attention in recent years. While the technology is still in its early stages of implementation, there is a growing acceptance of AI and ML in the drug development process. Here are some ways in which AI and ML are being accepted in NDA or IND submissions:
Predictive modeling: AI and ML algorithms are being increasingly used to predict the success of drugs or biologics. These algorithms can analyze large datasets, including clinical trial data and preclinical research data, to identify potential safety issues, predict drug efficacy, and determine the likelihood of a drug’s success.
Clinical trial design: AI and ML are being used to design more efficient and effective clinical trials. By analyzing patient data, these technologies can identify patient populations that may be more responsive to certain treatments, and help determine optimal dosing strategies. This can reduce the time and cost of clinical trials while increasing their chances of success.
Safety and toxicity prediction: AI and ML are being used to predict the safety and toxicity of drugs or biologics. These technologies can analyze preclinical and clinical data to identify potential safety issues early in the drug development process, reducing the risk of adverse events in clinical trials and post-approval.
Labeling: AI and ML are being used to generate labeling information for drugs or biologics. By analyzing clinical trial data and preclinical research data, these technologies can generate accurate and comprehensive labeling information, reducing the time and cost of NDA or IND submissions.
Regulatory compliance: AI and ML are being used to ensure regulatory compliance throughout the drug development process. By analyzing data and identifying potential compliance issues early in the process, these technologies can help companies avoid delays in the NDA or IND submission process.
Post-market surveillance: AI and ML are being used to monitor drug safety and efficacy post-approval. These technologies can analyze real-world data to identify potential safety issues and make necessary changes to drug labeling or dosing strategies.
In conclusion, the use of AI and ML in NDA or IND submissions is gaining acceptance in the drug development industry. These technologies can help predict drug success, design more efficient clinical trials, predict safety and toxicity, generate accurate labeling information, ensure regulatory compliance, and monitor drug safety and efficacy post-approval. While there are still challenges to be overcome in the implementation of these technologies, there is a growing recognition of their potential to improve the drug development process and bring new treatments to patients faster and more efficiently. As AI and ML continue to advance, they will play an increasingly critical role in the drug development process, and their acceptance in NDA or IND submissions is likely to continue to grow.
This talk can be part of a symposium on AI/ML or part of a hot topic presentation/discussion
Learning Objectives:
Define key concepts related to AI/ML in drug development and describe how they can be applied in pharmaceutical research and development.
Describe the potential benefits and limitations of these technologies in improving the efficiency and effectiveness of the drug development process.
Examine the regulatory considerations associated with the use of AI/ML in drug development and describe best practices for implementing these technologies.
Learn about the views and concerns of regulatory agencies (FDA, EMA) about use of AI/ML in drug development and regulatory decision making.