Kim John, Kincaid John W R, Rao Arya S, Lie Winston, Fuh Lanting, Landman Adam B, Succi Marc D
J Am Pharm Assoc (2003). 2025 Jan-Feb;65(1):102304. doi: 10.1016/j.japh.2024.102304. Epub 2024 Nov 27.
As polypharmacy, the use of over-the-counter (OTC) drugs, and herbal supplements becomes increasingly prevalent, the potential for adverse drug-drug interactions (DDIs) poses significant challenges to patient safety and health care outcomes.
This study evaluates the capacity of Generative Pre-trained Transformer (GPT) models to accurately assess DDIs involving prescription drugs (Rx) with OTC medications and herbal supplements.
Leveraging a popular subscription-based tool (Lexicomp), we compared the risk ratings assigned by these models to 43 Rx-OTC and 30 Rx-herbal supplement pairs.
Our findings reveal that all models generally underperform, with accuracies below 50% and poor agreement with Lexicomp standards as measured by Cohen's kappa. Notably, GPT-4 and GPT-4o demonstrated a modest improvement in identifying higher-risk interactions compared to GPT-3.5.
These results highlight the challenges and limitations of using off-the-shelf large language models for guidance in DDI assessment.
随着多重用药、非处方药（OTC）的使用以及草药补充剂越来越普遍，药物不良相互作用（DDIs）的可能性对患者安全和医疗保健结果构成了重大挑战。
本研究评估生成式预训练变换器（GPT）模型准确评估涉及处方药（Rx）与非处方药和草药补充剂之间药物相互作用的能力。
利用一个流行的基于订阅的工具（Lexicomp），我们比较了这些模型对43对Rx-OTC和30对Rx-草药补充剂组合给出的风险评级。
我们的研究结果表明，所有模型的表现普遍不佳，准确率低于50%，并且根据科恩kappa系数衡量，与Lexicomp标准的一致性较差。值得注意的是，与GPT-3.5相比，GPT-4和GPT-4o在识别高风险相互作用方面有适度改善。
这些结果凸显了使用现成的大语言模型进行药物相互作用评估指导的挑战和局限性。
