Addressing Overprescribing Challenges: Fine-Tuning Large Language Models for Medication Recommendation Tasks

2025-03-05

AI Summary

Existing drug recommendation systems exhibit weak generalization, particularly across heterogeneous electronic health record (EHR) systems and when leveraging unstructured clinical text; large language model (LLM)-based approaches frequently suffer from over-prescription, compromising medication safety. This paper proposes LAMO (Language-Assisted Medication Optimization), a novel framework addressing these limitations. LAMO introduces the first safety-aware overfitting mitigation fine-tuning paradigm for medication recommendation, systematically identifying and alleviating prescription bias inherent in medical LLMs. It integrates parameter-efficient LoRA fine-tuning, semantic modeling of unstructured clinical text, and multi-source EHR alignment to enhance zero-shot generalization to unseen drugs. In internal validation, LAMO achieves >10% higher accuracy than state-of-the-art methods and demonstrates superior robustness and generalizability across temporal extrapolation, cross-institutional, and out-of-distribution drug recommendation tasks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

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

Abstract

Medication recommendation systems have garnered attention within healthcare for their potential to deliver personalized and efficacious drug combinations based on patient's clinical data. However, existing methodologies encounter challenges in adapting to diverse Electronic Health Records (EHR) systems and effectively utilizing unstructured data, resulting in limited generalization capabilities and suboptimal performance. Recently, interest is growing in harnessing Large Language Models (LLMs) in the medical domain to support healthcare professionals and enhance patient care. Despite the emergence of medical LLMs and their promising results in tasks like medical question answering, their practical applicability in clinical settings, particularly in medication recommendation, often remains underexplored. In this study, we evaluate both general-purpose and medical-specific LLMs for medication recommendation tasks. Our findings reveal that LLMs frequently encounter the challenge of overprescribing, leading to heightened clinical risks and diminished medication recommendation accuracy. To address this issue, we propose Language-Assisted Medication Recommendation (LAMO), which employs a parameter-efficient fine-tuning approach to tailor open-source LLMs for optimal performance in medication recommendation scenarios. LAMO leverages the wealth of clinical information within clinical notes, a resource often underutilized in traditional methodologies. As a result of our approach, LAMO outperforms previous state-of-the-art methods by over 10% in internal validation accuracy. Furthermore, temporal and external validations demonstrate LAMO's robust generalization capabilities across various temporal and hospital contexts. Additionally, an out-of-distribution medication recommendation experiment demonstrates LAMO's remarkable accuracy even with medications outside the training data.

Problem

• Overprescribing challenges in medication recommendation systems.
• Limited generalization in adapting to diverse EHR systems.
• Underutilization of unstructured clinical data in existing methods.

Innovation

• Fine-tunes LLMs for medication recommendations
• Uses clinical notes for enhanced accuracy
• Improves generalization across diverse EHR systems