Large Language Models as Clinical Support Tools in Drug Information Services: Performance Comparison With Pharmacists

Engineering notes

Engineering notes will be added by the aipentium editorial team.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为大语言模型、生成式AI、ChatGPT相关技术、计算机视觉、深度学习等高价值论文补充中文说明。

Original abstract

ABSTRACT Background Large language models (LLMs) are increasingly explored for drug information support, yet their reliability and clinical applicability remain uncertain. This study evaluated multiple LLMs in responding to real‐world drug information questions retrieved from a university hospital in Thailand, focusing on clarity in Thai, concordance with pharmacist responses, relevance, context awareness, and citation credibility. Methods A total of 102 drug information questions were submitted to seven LLMs, generating 714 responses. In the inter‐rater reliability phase, 10 pilot questions were submitted to all seven LLMs, and the resulting 70 responses were evaluated by three assessors, yielding 210 rating instances. Agreement was measured using intra‐class correlation coefficient and Fleiss' kappa. Following satisfactory agreement, the 102 questions were divided into three subsets, each assessed by one assessor using a predefined rubric. Binary outcomes were coded to calculate sensitivity and domain fulfillment rates, with pharmacist‐provided answers serving as the reference standard for concordance. Model performance was compared using Cochran's Q test, and citation‐related issues were identified from qualitative comments. Results Inter‐rater reliability demonstrated substantial to almost perfect agreement, with coefficients ranging from 0.79–0.86. Overall, most LLMs performed well in clarity, relevance, and context awareness. Clarity scores ranged from 85.25%–92.75%, while fulfillment rates ranged from 0.97–1.00 for relevance and 0.90–0.99 for context awareness. Concordance was more variable, ranging from 0.70–0.86, whereas citation credibility was consistently weak, ranging from 0.03–0.36. A significant difference between LLMs was observed only in the concordance, with post hoc analyses identifying a significant difference between ChatGPT‐5.2 Thinking (OpenAI, San Francisco, CA, USA) and Copilot Think Deeper (Microsoft, Redmond, WA, USA). (McNemar test, adjusted p = 0.0178). Conclusions LLMs show potential as tools for preliminary drug information retrieval and rapid responses generation in drug information services. However, variable concordance and persistent limitations in citation credibility indicate the need for continued pharmacist oversight.

Links and sources

Comments