Raja Shankar, VP of machine learning at IQVIA, explains how AI-driven trial simulation and automation are beginning to influence decision-making across every phase of clinical development.
In a video interview prior to the 2026 SCOPE Summit with Applied Clinical Trials, Raja Shankar, VP of machine learning at IQVIA, discussed how artificial intelligence is beginning to reshape research and development across the clinical trial lifecycle. Shankar outlined how AI-enabled trial simulation and automation are influencing protocol design, site activation, monitoring, and closeout, while also pointing to emerging applications such as synthetic control arms and digital twins that could significantly alter trial design in the years ahead.
Editor's note: This transcript is a lightly edited rendering of the original audio/video content. It may contain errors, informal language, or omissions as spoken in the original recording.
ACT: At each phase of drug development, can you share one key way you see a realistic impact on how R&D is done with AI?
Shankar: I think AI is going to have an impact on R&D in two big ways. One is clinical trial simulation, and the second is clinical trial automation, and both will influence every stage of clinical development.
Before a trial even starts, AI can be applied to real-world data, clinical trial data, and other data sources to simulate, in silico, what might happen in vivo. That allows sponsors to make better clinical trial decisions and write stronger protocols that increase the chances of success, both from an efficacy and an operational perspective.
Once a trial begins, AI can support each phase, from design and planning through startup, conduct, and closeout. In the early stages, AI can help define trial strategy, including country and site selection, and evaluate protocols to minimize downstream deviations that can delay trials. During startup, AI can help accelerate site activation, for example by supporting faster development of informed consent forms at the master, country, and site levels.
During trial conduct, AI can support centralized and risk-based monitoring, assist CRAs with visit preparation and report writing, and reduce issues that often slow trials down. Finally, during closeout, AI can help with clinical study report generation as well as biostatistics and data analysis in new ways. Altogether, these applications can both accelerate trials and improve outcomes.
