Keiji AI LogoKeiji AI

Research · medRxiv 2024

Panacea

Research on clinical trial foundation model. Panacea is a single language model for several clinical trial tasks: trial search, summarization, design and patient-trial matching. It was pre-trained on 793,279 trial documents and 1,113,207 related papers.

Who created Panacea?

Jiacheng Lin is the first author of Panacea. Its authors include Keiji AI co-founders Zifeng Wang and Jimeng Sun, Keiji AI's CEO.

What the paper found

  • Performed best on seven of eight clinical trial tasks against six generic or medicine-specific language models.
  • Improved patient-trial matching by 14.42% and trial search by 41.78% to 52.02%.

How Panacea 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: Competitive and portfolio intelligence.

The paper

Jiacheng Lin, Hanwen Xu, Zifeng Wang, Sheng Wang, Jimeng Sun. Panacea: A foundation model for clinical trial search, summarization, design, and recruitment. medRxiv, 2024. This is a preprint and has not been peer reviewed.

Details checked against the published record on 2026-11-01.

Frequently asked questions

Who created Panacea?
Jiacheng Lin is the first author of Panacea. Its authors include Keiji AI co-founders Zifeng Wang and Jimeng Sun, Keiji AI's CEO.
Is Panacea 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 Panacea paper find?
Performed best on seven of eight clinical trial tasks against six generic or medicine-specific language models. Improved patient-trial matching by 14.42% and trial search by 41.78% to 52.02%.

All publications

Every paper sits under its primary research area.