Saved in:
Bibliographic Details
Main Authors: Van, Phuc Phan, Minh, Dat Nguyen, Ngoc, An Dinh, Thanh, Huy Phan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.03440
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909306329235456
author Van, Phuc Phan
Minh, Dat Nguyen
Ngoc, An Dinh
Thanh, Huy Phan
author_facet Van, Phuc Phan
Minh, Dat Nguyen
Ngoc, An Dinh
Thanh, Huy Phan
contents To protect patient safety, modern pharmaceutical complexity demands strict prescription verification. We offer a new approach - Rx Strategist - that makes use of knowledge graphs and different search strategies to enhance the power of Large Language Models (LLMs) inside an agentic framework. This multifaceted technique allows for a multi-stage LLM pipeline and reliable information retrieval from a custom-built active ingredient database. Different facets of prescription verification, such as indication, dose, and possible drug interactions, are covered in each stage of the pipeline. We alleviate the drawbacks of monolithic LLM techniques by spreading reasoning over these stages, improving correctness and reliability while reducing memory demands. Our findings demonstrate that Rx Strategist surpasses many current LLMs, achieving performance comparable to that of a highly experienced clinical pharmacist. In the complicated world of modern medications, this combination of LLMs with organized knowledge and sophisticated search methods presents a viable avenue for reducing prescription errors and enhancing patient outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03440
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rx Strategist: Prescription Verification using LLM Agents System
Van, Phuc Phan
Minh, Dat Nguyen
Ngoc, An Dinh
Thanh, Huy Phan
Computation and Language
To protect patient safety, modern pharmaceutical complexity demands strict prescription verification. We offer a new approach - Rx Strategist - that makes use of knowledge graphs and different search strategies to enhance the power of Large Language Models (LLMs) inside an agentic framework. This multifaceted technique allows for a multi-stage LLM pipeline and reliable information retrieval from a custom-built active ingredient database. Different facets of prescription verification, such as indication, dose, and possible drug interactions, are covered in each stage of the pipeline. We alleviate the drawbacks of monolithic LLM techniques by spreading reasoning over these stages, improving correctness and reliability while reducing memory demands. Our findings demonstrate that Rx Strategist surpasses many current LLMs, achieving performance comparable to that of a highly experienced clinical pharmacist. In the complicated world of modern medications, this combination of LLMs with organized knowledge and sophisticated search methods presents a viable avenue for reducing prescription errors and enhancing patient outcomes.
title Rx Strategist: Prescription Verification using LLM Agents System
topic Computation and Language
url https://arxiv.org/abs/2409.03440