Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use

2024-10-24

arXiv.org

AI Summary

This study investigates the clinical applicability of large language models (LLMs) in identifying psychiatric adverse drug reactions (ADRs) and generating harm-reduction strategies. To address the lack of domain-specific evaluation resources, we introduce Psych-ADR—the first high-quality, manually annotated dataset focused exclusively on psychiatric ADRs—and propose ADRA, a strategy-driven evaluation framework that quantifies model performance across four dimensions: ADR detection accuracy, sentiment/tone consistency, clinical actionability of generated strategies, and alignment with expert recommendations. Experimental results reveal critical limitations: LLM outputs exhibit poor readability and excessive complexity; expert alignment rates average only 70.86%, falling significantly short of clinical standards; and responses systematically underperform experts in conciseness and clinical operability. This work establishes the first open-source benchmark and methodology dedicated to evaluating LLMs in psychiatric ADR management, setting a new standard for assessing expert alignment in high-stakes healthcare applications.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Adversarial Agents
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Adverse Drug Reactions (ADRs) from psychiatric medications are the leading cause of hospitalizations among mental health patients. With healthcare systems and online communities facing limitations in resolving ADR-related issues, Large Language Models (LLMs) have the potential to fill this gap. Despite the increasing capabilities of LLMs, past research has not explored their capabilities in detecting ADRs related to psychiatric medications or in providing effective harm reduction strategies. To address this, we introduce the Psych-ADR benchmark and the Adverse Drug Reaction Response Assessment (ADRA) framework to systematically evaluate LLM performance in detecting ADR expressions and delivering expert-aligned mitigation strategies. Our analyses show that LLMs struggle with understanding the nuances of ADRs and differentiating between types of ADRs. While LLMs align with experts in terms of expressed emotions and tone of the text, their responses are more complex, harder to read, and only 70.86% aligned with expert strategies. Furthermore, they provide less actionable advice by a margin of 12.32% on average. Our work provides a comprehensive benchmark and evaluation framework for assessing LLMs in strategy-driven tasks within high-risk domains.

Problem

• Large Language Models
• Psychopharmacological Side Effects
• Expertise Comparison

Innovation

• Psych-ADR Testing
• ADR Assessment Framework
• Large Language Model Evaluation