The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem

TL;DR

This paper presents a set of guardrails designed to mitigate hallucinations and errors in large language models used for drug safety and pharmacovigilance, ensuring safer deployment in medical safety-critical settings.

Contribution

The authors develop and demonstrate a novel guardrail framework that detects anomalies, corrects errors, and conveys uncertainty in LLM outputs for medical safety applications.

Findings

Effective detection of anomalous documents

Accurate identification of incorrect drug and adverse event terms

Successful integration with a fine-tuned LLM for pharmacovigilance

Abstract

Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, LLM deployments in high-risk and safety-critical domains pose unique challenges, notably the issue of ``hallucination,'' where LLMs can generate fabricated information. This is particularly concerning in settings such as drug safety, where inaccuracies could lead to patient harm. To mitigate these risks, we have developed and demonstrated a proof of concept suite of guardrails specifically designed to mitigate certain types of hallucinations and errors for drug safety, and potentially applicable to other medical safety-critical contexts. These guardrails include mechanisms to detect anomalous documents to prevent the ingestion of inappropriate data, identify incorrect drug names or adverse event terms, and convey uncertainty in generated content. We integrated these guardrails with an LLM fine-tuned for a text-to-text task, which involves converting both structured and unstructured data within adverse event reports into natural language. This method was applied to translate individual case safety reports, demonstrating effective application in a pharmacovigilance processing task. Our guardrail framework offers a set of tools with broad applicability across various domains, ensuring LLMs can be safely used in high-risk situations by eliminating the occurrence of key errors, including the generation of incorrect pharmacovigilance-related terms, thus adhering to stringent regulatory and quality standards in medical safety-critical environments.