Beyond early discovery, LLMs deliver significant value in clinical trials. They accelerate timelines by automating months of post-trial documentation work. More strategically, they can improve trial success rates by analyzing genomic data to identify patient populations with a higher likelihood of responding to a treatment.

The industry's standard practice of selecting sites based on pre-existing relationships and convenience—the "easy button"—is a primary driver of failure. This leads to 80% of activated sites missing enrollment targets and 30% enrolling zero patients, a massive, systemic inefficiency that data-driven approaches can solve.

Contrary to fears of job replacement, AI's primary purpose in clinical trials is to automate low-value work like coordination and documentation. This frees up experts like CRAs and data reviewers to focus on high-value activities such as interpreting signals, managing risks, and making critical decisions, thereby amplifying their expertise.

Clinical trial delays stem not from slow individual tasks but from the handoffs, reviews, and data transfers between them. Agentic AI's primary benefit is orchestrating these fragmented workflows, addressing the root cause of inefficiency by connecting previously siloed steps and reducing manual interventions.

While most focus on AI for drug discovery, Recursion is building an AI stack for clinical development, where 70% of costs lie. By using real-world data to pinpoint patient locations and causal AI to predict responders, they are improving trial enrollment rates by 1.5x. This demonstrates a holistic, end-to-end AI strategy that addresses bottlenecks across the entire value chain, not just the initial stages.

The highest-value application of AI in clinical development is in the design phase. By simulating trial outcomes with historical data and virtual patient cohorts, companies can identify and resolve potential bottlenecks, like flawed protocols or recruitment issues, before committing massive resources. This

Instead of a total overhaul, we can accelerate trials with three changes: 1) A simple patient opt-in registry for trial participation. 2) Collaborative platform trials testing multiple drugs against one control group. 3) A shared database for all trial data, including failures.

While AI for novel drug discovery has lofty goals, its most practical value lies in accelerating development. This includes applying AI to de-risked assets for new indications, improving delivery methods, and designing faster, more effective clinical trials, which is where the real bottleneck lies.

While AI is on the verge of cracking preclinical challenges, the biggest problem is the high drug failure rate in human trials. The next wave of innovation will use AI to design molecules for properties that predict human efficacy, addressing the fundamental reason drugs fail late-stage.