LLM Chatbot-Based Clinical Trial Participation Information Query System

Overview

Patients seeking to participate in clinical trials currently struggle to understand complex medical terminology and vast amounts of information. Existing search systems rely on rigid keyword-based searches, making it difficult for users to quickly find the information they need. This project aims to provide clinical trial information in a more intuitive and user-friendly manner by leveraging an LLM-based chatbot.

Project description

This system analyzes patient questions using a large language model and provides personalized clinical trial information. Key features include:

It provides an AI-based question-answering system that analyzes user queries using natural language processing technology to deliver the most appropriate clinical trial information. By linking with specialized medical data, it provides reliable answers and supports explanations tailored to patient comprehension.

To provide clinical trial information, it updates the latest clinical trial data by linking with the National Clinical Trial Information System. It collaborates with major hospitals and research institutions to provide reliable information, helping patients easily find suitable clinical trials.

It also provides personalized accessibility information, such as public transportation and convenience facilities. By analyzing patient health status, age, location, and other information, it recommends the optimal clinical trial. It continuously improves its recommendation algorithm based on user feedback, increasing the likelihood of patient participation.

Key technological features

• Large Language Model (LLM)-Based Question-Answering System: Provides natural language responses to user queries using AI models specialized for the medical field
  • Clinical Trial Database Integration: Linked to the National Clinical Trial Information System to reflect the latest clinical trial information
  • Personalized Recommendation System: Provides optimal clinical trial information tailored to the patient's health status, location, and areas of interest

Expected outcomes

Once this system is implemented, patients will be able to access complex medical information more easily and find clinical trials suited to their health status more efficiently.

It is also expected to provide researchers with a larger pool of potential participants, thereby accelerating the pace of clinical trial progress.

Enhance clinical trial success rates by removing barriers to participation, providing personalized accessibility information, and ensuring participation accessibility.

Launch year: 2024

Attribution

Case study courtesy of the National Information Society Agency, Republic of Korea, Apolitical's Content Partner. Sourced from Use Cases of Public AI Service, Vol.1,  https://eng.nia.or.kr/site/nia_eng/ex/bbs/View.do?cbIdx=31975&bcIdx=28997&parentSeq=29032