Blog

The Best 15 Minutes You’ll Spend on Clinical Trials Today

By
Unlearn

June 24, 2025

What if you could see into the future of every patient in your trial?


At the 2025 “Digital Breakthrough for Pharma” Summit hosted by Bristol Myers Squibb, Unlearn’s co-founder and machine learning scientist, Aaron Smith, took the stage to explain exactly how that vision is now a reality. His talk, “AI-Powered Digital Twins: Practical Applications in Clinical Development,” moves from the math behind trial inefficiencies to a compelling case study showing how AI-generated digital twins reduce sample sizes, shorten recruitment by months, and save tens of millions.

Using a real Phase 2 Alzheimer’s disease trial from AbbVie, Aaron demonstrates how digital twins can reduce variance in treatment effect estimates, not just for the primary endpoint, but across all outcomes. That increase in precision gives sponsors options: more power without a larger sample, or fewer patients without losing power. In the Phase 3 scenario he outlines, it amounts to a potential savings of 280 patients and nearly four months of recruitment time, or the equivalent of 380 “virtual” patients’ worth of statistical power, without changing the protocol.

But the value goes beyond performance metrics. Unlearn’s approach lines up with the FDA’s new seven-step framework for evaluating AI in trials, making it both powerful and regulatorily ready.

Key Takeaways

  • Disease-specific machine learning models, called Digital Twin Generators (DTGs), are trained on extensive patient-level clinical trial data. These models generate “digital twins”—forecasts of how each participant is likely to progress under standard of care, using only their baseline data.
  • Digital twins help sponsors answer “what if” questions with statistical confidence—like how a given patient would do without treatment—enabling better go/no-go decisions, faster development, and smarter resource use.
  • Unlearn’s PROCOVA method for incorporating digital twins into randomized controlled trials is proven, qualified by the EMA, and supported by the FDA.
  • While Aaron’s talk highlights Alzheimer’s, Unlearn’s digital twins are being used across multiple therapeutic areas.

Watch Aaron Smith’s full presentation to see what the future of clinical trials looks like and how close we already are.

Heading 1

Heading 2

Heading 3

Heading 4

Heading 5
Heading 6

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.

Example of a caption
Block quote that is a longer piece of text and wraps lines.

Ordered list

  1. Item 1
  2. Item 2
  3. Item 3

Unordered list

  • Item A
  • Item B
  • Item C

Text link

Bold text

Emphasis

Superscript

Subscript