CDER’s Emerging Drug Safety Technology Meeting Program
The pharmaceutical industry is expanding its use of artificial intelligence (AI) and other emerging technology across the drug product lifecycle. The Emerging Drug Safety Technology Meeting (EDSTM) program offers applicants with an approved application, and/or other relevant parties (e.g., academia, contract research organizations, pharmacovigilance (PV) vendors, software developments) who meet the eligibility and selection criteria, with an opportunity to meet with CDER staff to discuss their research, development, and use of AI and other emerging technology in PV. PV is all scientific and data gathering activities relating to, the detection, assessment, and understanding of adverse events (AE). All medicines and vaccines undergo rigorous FDA testing for safety and efficacy through clinical trials before they are authorized for use.
In this CDER Conversation, Robert Ball, M.D., M.P.H., ScM, Deputy Director of CDER’s Office of Surveillance and Epidemiology, explains the EDSTM program and the application of AI in PV based on his experience of more than a decade researching and developing AI systems in PV.
How have you observed artificial intelligence (AI) being used for PV and what are the challenges?
At present, one area being explored by the pharmaceutical industry is the application of AI to the processing of individual case safety reports (ICSRs). Case processing includes intake, evaluation, follow up, and the submission of ICSRs. There is great interest in applying AI to case causality assessment, which is the determination of whether there is a reasonable possibility that a drug caused the reported AE. Case causality assessment is challenging because it involves expert judgment and the application of highly specialized knowledge.
Currently AI cannot replicate or make as nuanced judgments as a human expert, leading to inadequate performance in ICSR evaluation, such as in predicting whether a drug may have caused an AE. In other tasks, such as identifying the reporter’s occupation during ICSR intake, AI may be adequate, though its performance still is not at the threshold needed for full automation. Given the risk that an AI model will miss important information, human oversight over the process is crucial. Important quality checks will be needed to ensure that the performance of combined human-AI systems are at least as effective as human-only systems.
Though AI is promising and can play a role in PV, human expertise remains essential. As AI evolves, striking the right balance between leveraging its potential and ensuring its safe application is important. To address some of these challenges, FDA is collaborating with international colleagues through initiatives such as the Council for International Organizations of Medical Sciences (CIOMS) working group on AI in PV, which is developing principles for the use of AI in PV. Within CDER, we are launching the EDSTM program to foster discussions with participants on their use of emerging technology in PV.
What is the EDSTM program seeking to accomplish?
In the initial phase, EDSTMs will provide a forum to facilitate mutual learning and discussion of participants’ application of emerging technology to PV. FDA plans to leverage these learnings to inform potential regulatory and policy approaches within PV and consider providing regulatory advice on specific technologies to facilitate their adoption, when appropriate.
Why is this program important? Why now?
Emerging technologies, such as AI, are impacting both industry and regulatory authorities as both strive to improve the efficiency of managing ever-increasing volumes of safety data. We recognize that industry is eager to begin applying these technologies but that there may also be uncertainties around whether they are sufficient to help support compliance with statutory and regulatory obligations, which ultimately impacts their adoption. We also recognize that technology is evolving rapidly – what we understand today may change in the very near future. Considering this, CDER feels it is important to launch this program to engage with the broader pharmaceutical industry and other relevant parties and facilitate mutual learning of how and when these technologies may be applied to PV and how challenges may be addressed.
What areas is the program focused on?
The program is focused on the use of emerging technology in PV. AI is currently in the spotlight due to the amount of attention and investment it has received, alongside its potential for use in PV. However, the program encompasses a multitude of emerging technologies and potential data sources used in PV, from the use of advanced automation to the most cutting-edge large language models. There are many potential questions emerging technology may help to address in PV. For example, how might emerging technology be used to improve case processing or to support causality assessment? Or how could emerging technology, such as AI, be used to analyze scientific literature or social media, to identify potential drug safety issues? These are some examples of areas CDER is interested in exploring through the EDSTMs.
Because this is an area filled with exciting innovation, we foresee the use of emerging technology in PV being explored in areas we may not have yet considered. As such, we designed our criteria for the EDSTM program with flexibility in mind to have discussions on a wide range of innovative approaches. It’s also worth noting this program is only one aspect of FDA’s multi-faceted approach to AI. While the program is focused on PV, FDA is actively also working in many other areas to understand how this technology can best be used throughout the drug product lifecycle.
What do participants gain from participation in the program?
The use of emerging technology, such as AI, has the potential to bring about transformative benefits for the way organizations approach PV by lowering administrative burdens and costs, and improving the efficiency and effectiveness of safety surveillance. However, accomplishing this may involve substantial investment in technologies that still bear significant amounts of uncertainty around aspects such as the credibility and trustworthiness of AI models, and how they may be integrated into existing PV workflows.
Through the EDSTM program, CDER set out to establish a learning environment, which will enable CDER and participants to engage in mutual learning of how emerging technology can be applied to PV. We expect that the knowledge gained through EDSTMs will help inform potential future regulatory and policy approaches related to the challenges surrounding emerging technology and help foster confidence in their continued investment.