Demo: Accelerating Patient Screening for Clinical Trials using Large Language Model Prompting
Presentation Type
Poster
Faculty Advisor
Hao Liu
Access Type
Event
Start Date
26-4-2024 2:15 PM
End Date
26-4-2024 3:15 PM
Description
This software presents the design of an end-to-end system that performs patient cohort screening for clinical trials through the integration of Large Language Model (LLM) Prompting. Leveraging the power of LLMs, we aim to accelerate and enhance the accuracy of patient matching with mono-logic blocks parsed from real trial participant criteria, and a vector database built from encoding critical sections of MIMIC-IV discharge notes: History of illness, Medication of admission, and Brief hospital course. We prompted LLMs to classify patient eligibility based on their medical history retrieved from the vector database. Through this exploration, we seek to demonstrate the potential of LLMs in expediting patient cohort screening, paving the way for more efficient and informed clinical trial recruitment.
Demo: Accelerating Patient Screening for Clinical Trials using Large Language Model Prompting
This software presents the design of an end-to-end system that performs patient cohort screening for clinical trials through the integration of Large Language Model (LLM) Prompting. Leveraging the power of LLMs, we aim to accelerate and enhance the accuracy of patient matching with mono-logic blocks parsed from real trial participant criteria, and a vector database built from encoding critical sections of MIMIC-IV discharge notes: History of illness, Medication of admission, and Brief hospital course. We prompted LLMs to classify patient eligibility based on their medical history retrieved from the vector database. Through this exploration, we seek to demonstrate the potential of LLMs in expediting patient cohort screening, paving the way for more efficient and informed clinical trial recruitment.