Research · Patterns 2024
FRAMM
Research on fair clinical trial site selection. FRAMM is a deep reinforcement learning framework that selects trial sites to improve both enrollment and diversity, and still works when data about a site is incomplete.
Who created FRAMM?
FRAMM was written by Brandon Theodorou, who works on AI at Keiji AI, and Jimeng Sun, Keiji AI's CEO, with Lucas Glass and Cao Xiao. The paper lists Sun at the University of Illinois Urbana-Champaign.
What the paper found
- On real historical trials it beat the leading baseline in enrollment-only settings while greatly improving diversity. The abstract does not state a single summary figure.
How FRAMM relates to TrialMind
It is research, not a TrialMind module or a separately sold product. Published methods like this one inform how TrialMind works; TrialMind is the product Keiji AI sells.
See how TrialMind handles this work: Clinical development and operations.
The paper
Brandon Theodorou, Lucas Glass, Cao Xiao, Jimeng Sun. FRAMM: Fair ranking with missing modalities for clinical trial site selection. Patterns, 2024.
Details checked against the published record on 2026-11-01.
Frequently asked questions
- Who created FRAMM?
- FRAMM was written by Brandon Theodorou, who works on AI at Keiji AI, and Jimeng Sun, Keiji AI's CEO, with Lucas Glass and Cao Xiao. The paper lists Sun at the University of Illinois Urbana-Champaign.
- Is FRAMM part of TrialMind?
- No. It is research, not a TrialMind module or a separately sold product. Published methods like this one inform how TrialMind works; TrialMind is the product Keiji AI sells.
- What did the FRAMM paper find?
- On real historical trials it beat the leading baseline in enrollment-only settings while greatly improving diversity. The abstract does not state a single summary figure.
All publications
Every paper sits under its primary research area.