December, 2024
December 2024
M T W T F S S
 1
2345678
9101112131415
16171819202122
23242526272829
3031  
Ken Kehl: A new open-source approach to match patients with cancer to potential clinical trials
Dec 27, 2024, 07:50

Ken Kehl: A new open-source approach to match patients with cancer to potential clinical trials

Ken Kehl, Assistant Professor of Medicine at Harvard Medical School and Physician at Dana-Farber Cancer Institute, shared a post on X:

“Excited to share our collaboration from Dana-Farber Dana-Farber Division of Population Sciences Division of Population Sciences & Knowledge Systems Group: MatchMiner-AI!

A new open-source approach to match patients with cancer to potential clinical trials.”

” The Challenge:

Clinical trials are crucial for advancing cancer care, yet many trials fail to recruit enough patients.

Existing trial-matching tools often struggle with the complexity of eligibility criteria.”

“Our Solution:

MatchMiner-AI focuses on core “clinical spaces”—combinations of cancer type, treatment history, and biomarkers—for trial matching.”

“Our goal is to help clinicians and ultimately patients identify clinical trials by disease context, not to fully automate screening.”

“Pipeline overview:

  • Condenses and summarizes patient EHR histories using LLMs.
  • Extracts trial “spaces” from eligibility criteria.
  • Uses embedding models to rank patient-trial matches.
  • Double-checks matches with a classifier.”

“Results:

  • The pipeline achieved precision @ 10 of 89% and mean average precision of 93% for patient-centric queries.
  • Embedding models clustered patients by cancer type, aligning clinical trial summaries with patient summaries.
  • Real-world application is fast & scalable!”

Check it out!

Code + Models for non-commercial use.”

Demo app for clinical trial search.”

Preprint.

MatchMiner-AI: An Open-Source Solution for Cancer Clinical Trial Matching.

Authors: Ethan Cerami, et al.

Ken Kehl: A new open-source approach to match patients with cancer to potential clinical trials

“We’re still actively refining and improving the pipeline, which will change frequently, but we wanted to share our approach given rapid progress in trial matching and in AI generally.

All feedback welcome!”

“Thanks to the whole clinical trials matching team in KSG at DFCI led by Ethan Cerami, Tali Mazor, James Lindsay, and many others.

And thanks to Meta and the Llama Impact Grants program for providing funding to help get this off the ground!”