Design and Evaluation of a CDSS for Drug Allergy Management Using LLMs and Pharmaceutical Data Integration

2024-09-24

arXiv.org

AI Summary

Traditional clinical decision support systems (CDSSs) rely on static knowledge bases and rule-based engines, leading to high false-positive rates in drug allergy identification, poor generalizability, and severe alert fatigue. To address these limitations, this paper introduces HELIO T—a novel large language model (LLM)-driven dynamic semantic reasoning framework. HELIO T tightly integrates foundation LLMs, biomedical ontologies, and heterogeneous pharmacological knowledge sources to enable real-time, context-aware interpretation of unstructured clinical text. It replaces rigid rules with adaptive inference and supports continual incremental learning. Evaluated on a synthetic patient dataset, HELIO T achieves 100% accuracy, precision, recall, and F1-score, while substantially reducing non-actionable alerts—demonstrating exceptional reliability, robust generalizability, and clinical scalability. Its core contribution is the establishment of the first LLM-native, dynamic CDSS paradigm specifically designed for drug allergy risk identification.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Medication errors significantly threaten patient safety, leading to adverse drug events and substantial economic burdens on healthcare systems. Clinical Decision Support Systems (CDSSs) aimed at mitigating these errors often face limitations, including reliance on static databases and rule-based algorithms, which can result in high false alert rates and alert fatigue among clinicians. This paper introduces HELIOT, an innovative CDSS for drug allergy management, integrating Large Language Models (LLMs) with a comprehensive pharmaceutical data repository. HELIOT leverages advanced natural language processing capabilities to interpret complex medical texts and synthesize unstructured data, overcoming the limitations of traditional CDSSs. An empirical evaluation using a synthetic patient dataset and expert-verified ground truth demonstrates HELIOT's high accuracy, precision, recall, and F1 score, uniformly reaching 100% across multiple experimental runs. The results underscore HELIOT's potential to enhance decision support in clinical settings, offering a scalable, efficient, and reliable solution for managing drug allergies.

Problem

• Managing adverse drug reactions using LLM-based CDSS
• Reducing false alerts in drug reaction warnings
• Processing unstructured clinical data for better decision support

Innovation

• LLM-based CDSS for drug reaction management
• Processes free-text clinical notes using LLMs
• Reduces false alerts by learning medication tolerances